| |
Last updated on August 24, 2022. This conference program is tentative and subject to change
Technical Program for Thursday July 14, 2022
|
ThAT1 |
Alsh-1 |
Theme 08. Robotics in Clinical and Assistive Environments |
Oral Session |
Chair: Noccaro, Alessia | Università Campus Bio-Medico Di Roma |
Co-Chair: Abeywardena, Sajeeva | Queen Mary University of London |
|
08:30-08:45, Paper ThAT1.1 | |
Design and Development of a Social Assistive Robot for Music and Game Activities: A Case Study in a Residential Facility for Disabled People |
|
Sorrentino, Alessandra | Scuola Superiore Sant'Anna, Pisa |
Fiorini, Laura | University of Florence |
La Viola, Carlo | Università Degli Studi Di Firenze |
Cavallo, Filippo | University of Florence |
Keywords: Assistive and cognitive robotics in rehabilitation, Assistive and cognitive robotics in aided living, Home robots
Abstract: Cognitive disability strongly reduces people’s autonomy in performing desired as well as daily activities. The use of Social Assistive Robots (SARs) for cognitive rehabilitation therapy for disabled people could be a valuable gateway for the residential facility of the future. In this work, we design and develop a SAR that can be used for cognitive therapy proposing music and game activities. The results confirm that participants were positively engaged during the proposed activities and satisfied by the robot, despite the low perception of its usability. Professional caregivers noticed and confirmed the high level of engagement and the positive acceptance of the robot within the session, suggesting future tasks for SAR
|
|
08:45-09:00, Paper ThAT1.2 | |
Individuals with Moderate to Severe Hand Impairments May Struggle to Use EMG Control for Assistive Devices |
|
Meier, Tess | Worcester Polytechnic Institute |
Brecheisen, Alison | Taylor University |
Gandomi, Katie | Worcester Polytechnic Institute |
Carvalho, Paulo | Worcester Polytechnic Institute |
Meier, Gretchen | Pine Bush Physical Therapy |
Clancy, Edward A. | Worcester Polytechnic Institute |
Fischer, Gregory | Worcester Polytechnic Institute |
Nycz, Christopher | Worcester Polytechnic Institute |
Keywords: Human machine interfaces and robotics applications, Wearable robotic systems - Orthotics and Exoskeletons, Hardware and control developments in rehabilitation robotics
Abstract: Neurological trauma, such as stroke, traumatic brain injury (TBI), spinal cord injury, and cerebral palsy can cause mild to severe upper limb impairments. Hand impairment makes it difficult for individuals to complete activities of daily living, especially bimanual tasks. A robotic hand orthosis or hand exoskeleton can be used to restore partial function of an intact but impaired hand. It is common for upper extremity prostheses and orthoses to use electromyography (EMG) sensing as a method for the user to control their device. However some individuals with an intact but impaired hand may struggle to use a myoelectrically controlled device due to potentially confounding muscle activity. This study was conducted to evaluate the application of conventional EMG control techniques as a robotic orthosis/exoskeleton user input method for individuals with mild to severe hand impairments. Nine impaired subjects and ten healthy subjects were asked to perform repeated contractions of muscles in their forearm and then onset analysis and feature classification were used to determine the accuracy of the employed EMG techniques. The average accuracy for contraction identification across employed EMG techniques was 95.4% ± 4.9 for the healthy subjects and 73.9% ± 13.1 for the impaired subjects with a range of 47.0% ± 19.1 -- 91.6% ± 8.5. These preliminary results suggest that the conventional EMG control technologies employed in this paper may be difficult for some impaired individuals to use due to their unreliable muscle control.
|
|
09:00-09:15, Paper ThAT1.3 | |
Tele-Impedance Control Approach Using Wearable Sensors |
|
Buscaglione, Silvia | Università Campus Bio-Medico Di Roma |
Tagliamonte, Nevio Luigi | Università Campus Bio-Medico Di Roma |
Ticchiarelli, Giulia | Università Campus Bio-Medico Di Roma |
Di Pino, Giovanni | Campus Biomedico University |
Formica, Domenico | Campus Bio-Medico University |
Noccaro, Alessia | Università Campus Bio-Medico Di Roma |
Keywords: Joint biomechanics, Modeling and simulation in musculoskeletal biomechanics, Dynamics in musculoskeletal biomechanics
Abstract: Tele-operational tasks often suffer from instability issues and limited reliability during unpredictable interactions. We propose a real-time control law reproducing the impedance and kinematic behaviour of a subject’s arm (shoulder and elbow) on a remote avatar in a 2-DoF task. The human arm impedance and kinematics are estimated respectively from EMG and M-IMU data and then mapped into the avatar arm through an impedance control. Contrary to literature methods, our portable tele-impedance controller relies only on wearable sensors and enables an easy use in unstructured environments. The good performance (R2 > 0.7) of the muscle model used to map on the robot the human stiffness of five healthy subjects indicates the possibility of applying the proposed algorithm for a tele-impedance control.
|
|
09:15-09:30, Paper ThAT1.4 | |
Preliminary Assessment of the Safety of a Fault-Tolerant Control-Based Wearable Tremor Suppression Glove |
|
Zhou, Yue | University of Western Ontario |
Jenkins, Mary | University of Western Ontario |
Naish, Michael D. | The University of Western Ontario |
Trejos, Ana Luisa | The University of Western Ontario |
Keywords: Wearable robotic systems - Orthotics and Exoskeletons, Exoskeleton applications
Abstract: The advent of wearable tremor suppression devices (WTSDs) has provided a promising alternative approach for parkinsonian tremor management, especially for individuals whose tremors are not managed by conventional treatment options. Currently, research in WTSDs has shown successful results with a tremor suppression ratio of up to 99%; however, the user safety of WTSDs has not been properly considered, especially in the occurrence of unexpected events, such as faults and disturbances. In this study, a fault-tolerant control system was developed and integrated into the control system of a WTSD for the first time. The safety and tremor suppression performance of the proposed system under the influence of a measurement loss fault were tested and evaluated on 18 tremor motion datasets, specifically by quantifying the tremor power suppression ratio and the error when tracking voluntary motion. The experimental evaluation showed that the proposed system could remain functional and safe to use in the existence of the fault, with an average user motion tracking error of 1.5◦. It was also found that the proposed system achieved significantly improved performance in both metrics when compared to the system without a fault-tolerant controller.
|
|
09:30-09:45, Paper ThAT1.5 | |
Human Balance Augmentation Via a Supernumerary Robotic Tail |
|
Abeywardena, Sajeeva | Queen Mary University of London |
Anwar, Eisa | Queen Mary University of London |
Miller, Stuart | Queen Mary University of London |
Farkhatdinov, Ildar | Queen Mary University of London |
Keywords: Wearable robotic systems - Orthotics and Exoskeletons, Design and development of robots for human-robot interaction, Mechanics of locomotion and balance
Abstract: Humans are intrinsically unstable in quiet stance from a rigid body system viewpoint; however, they maintain balance thanks to neuro-muscular sensory properties whilst still exhibiting postural sway characteristics. This work introduces a one-degree-of-freedom supernumerary tail for balance augmentation in the sagittal plane to negate anterior-posterior postural sway. Simulations showed that the tail could successfully balance a human with impaired ankle stiffness and neural control. Insights into tail design and control were made; namely, to minimise muscular load the tail must have a significant component in the direction of the muscle, mounting location of the tail is significant in maximising inertial properties for balance augmentation and that adaptive control of the tail will be best suited for different loads held by a wearer.
|
|
09:45-10:00, Paper ThAT1.6 | |
Object Localization Assistive System Based on CV and Vibrotactile Encoding |
|
Wei, Zhikai | Southeast University |
Song, Aiguo | Southeast University |
Hu, Xuhui | Southeast University |
Keywords: Assistive and cognitive robotics in aided living, Design and development of robots for human-robot interaction, Robot-aided mobility - Wheelchairs, canes, crutches, and mobility tools
Abstract: Intelligent assistive systems can navigate blind people, but most of them could only give non-intuitive cues or inefficient guidance. Based on computer vision and vibrotactile encoding, this paper presents an interactive system that provides blind people with intuitive spatial cognition. Different from the traditional auditory feedback strategy based on speech cues, this paper firstly introduces a vibration-encoded feedback method that leverages the haptic neural pathway and enables the users to interact with objects other than manipulating an assistance device. Based on this strategy, a wearable visual module based on an RGB-D camera is adopted for 3D spatial object localization, which contributes to accurate perception and quick object localization in the real environment. The experimental results on target blind individuals indicate that vibrotactile feedback reduces the task completion time by over 25% compared with the mainstream voice prompt feedback scheme. The proposed object localization system provides a more intuitive spatial navigation and comfortable wearability for blindness assistance.
|
|
ThAT2 |
Alsh-2 |
Theme 07. Cardiac Sensing |
Oral Session |
Chair: Noh, Yeon Sik | University of Massachusetts Amherst |
Co-Chair: Vanrumste, Bart | Katholieke Universiteit Leuven |
|
08:30-08:45, Paper ThAT2.1 | |
Arterial Pulse Localization with Varying Electrode Sizes and Spacings in Wrist-Worn Bioimpedance Sensing |
|
Phipps, Jesse | Texas A&M University |
Sel, Kaan | Texas A&M University |
Jafari, Roozbeh | Texas A&M University |
Keywords: Physiological monitoring - Instrumentation, Bio-electric sensors - Sensor systems, Wearable sensor systems - User centered design and applications
Abstract: Bioimpedance has emerged as a promising modality to continuously monitor hemodynamic and respiratory physiological parameters through a non-invasive skin-contact approach. Bioimpedance sensors placed at the radial zone of the volar wrist provide sensitive operation to the blood flow of the underlying radial artery. The translation of bioimpedance systems into medical-grade settings for continuous hemodynamic monitoring, however, presents challenges when constraining the necessary sensing components to a minimal form factor while maintaining sufficient accuracy and precision of measurements. Thus, it is important to understand the effects of electrode configuration on bioimpedance signals when reducing them to a wearable form factor. Previous work regarding electrode configurations in bioimpedance does not address wearable constraints, nor do they focus on electrodes viable for wearable applications. In this study, we present empirical evidence of the effects of dry silver electrode sizes and spacings on the specificity and sensitivity of a wrist-worn bioimpedance sensor array. We found that wrist-worn bioimpedance systems for hemodynamic monitoring would benefit from reduced injection electrode spacings (up to a 392% increase in signal amplitude with a 50% decrease in spacing), increased sensing electrode spacings, and decreased electrode surface areas.
|
|
08:45-09:00, Paper ThAT2.2 | |
RF-Free Infant ECG Monitoring: Performance and Signal Quality Assessment |
|
Chehbani, Amel | Univ. Limoges, XLIM, UMR 7252 , F-87000 Limoges, France |
Sahuguede, Stephanie | Univ.Limoges, XLIM, UMR 7252, F-87000 Limoges, France |
Julien-Vergonjanne, Anne | Univ. Limoges, XLIM, UMR 7252 , F-87000 Limoges, France |
Keywords: Wearable body sensor networks and telemetric systems, IoT sensors for health monitoring, Health monitoring applications
Abstract: Existing Electrocardiogram (ECG) systems are either wired or based on radiofrequency (RF) wireless devices when remote transmission is needed. However, the use of radiofrequencies has limitations especially for sensitive populations such as newborns and infants. In addition, due to electromagnetic interference problems, impairments in the RF transmission of the ECG signal can lead to diagnostic errors. To answer these problems, we propose in this article, an optical wireless monitoring system, using an infrared link between an ECG sensor placed on a baby's chest and receivers placed on the ceiling of a pediatric room. In addition, it is assumed that the infant can move around in his bed. Our main contribution is the evaluation of the quality of the ECG signal transmitted by the proposed system, in terms of classic Signal to Noise Ratio (SNR) and Bit Error Rate (BER) metrics but also in terms of Signal Quality Indexes (SQIs) calculated from the characteristics of the received ECG signal. Results show the ability to perform wireless infant ECG monitoring using the Optical Wireless Communication (OWC) with satisfactory quality for optimum power.
|
|
09:00-09:15, Paper ThAT2.3 | |
On the Value of MRI for Improved Understanding of Cuff-Based Oscillometric Measurements |
|
Bogatu, Laura | Philips Research, Eindhoven University of Technology |
Hoppenbrouwers, Jan | Catharina Ziekenhuis |
van den Bosch, Harrie | Catharina Hospital |
Turco, Simona | Eindhoven University of Technology |
Mischi, Massimo | Eindhoven University of Technology |
Schmitt, Lars | Philips |
Woerlee, Pierre | TUe Eindhoven |
Bouwman, R Arthur | Catharina Hospital, Eindhoven |
Korsten, Erik | Catharina Hospital Eindhoven |
Muehlsteff, Jens | Philips |
Keywords: Physiological monitoring - Novel methods, Physiological monitoring - Modeling and analysis, Mechanical sensors and systems
Abstract: Blood pressure (BP) is a key parameter in critical care and in cardiovascular disease management. BP is typically measured via cuff-based oscillometry. This method is highly inaccurate in hypo-and hypertensive patients. Improvements are difficult to achieve because oscillometry is not yet fully understood; many assumptions and uncertainties exist in models describing the process by which arterial pulsations become expressed within the cuff signal. As a result, it is also difficult to estimate other parameters via the cuff such as arterial stiffness, cardiac output and pulse wave velocity (PWV)-BP calibration. Many research modalities have been employed to study oscillometry (ultrasound, computer simulations, ex-vivo studies, measurement of PWV, mechanical analysis). However, uncertainties remain; additional investigation modalities are needed. In this study, we explore the extent to which MRI can help investigate oscillometric assumptions. Four healthy volunteers underwent a number of MRI scans of the upper arm during cuff inflation. It is found that MRI provides a novel perspective over oscillometry; the artery, surrounding tissue, veins and the cuff can be simultaneously observed along the entire length of the upper arm. Several existing assumptions are challenged: tissue compression is not isotropic, arterial transmural pressure is not uniform along the length of the cuff and propagation of arterial pulsations through tissue is likely impacted by patient-specific characteristics (vasculature position and tissue composition). Clinical Relevance— The cuff interaction with the vasculature is extremely complex; existing models are oversimplified. MRI is a valuable tool for further development of cuff-based physiological measurements.
|
|
09:15-09:30, Paper ThAT2.4 | |
Waveform Morphology Comparison in Wearable Blood Pressure Sensors |
|
Gomes, Elizabeth | Blumio, Inc |
Naima, Reza | Blumio, Inc |
Liao, Catherine | Blumio, Inc |
Shay, Oliver | Blumio, Inc |
Keywords: Wearable body sensor networks and telemetric systems, Physiological monitoring - Instrumentation, Health monitoring applications
Abstract: Wearable devices for continuous non-invasive blood pressure monitoring must be capable of providing a continuous waveform representative of arterial blood pressure. This paper establishes the distinctions in waveform morphology between wearable sensor modalities, specifically millimeter-wave radar and photoplethysmography, when compared to a reference continuous non-invasive blood pressure monitor. An analysis of a 115-subject dataset was conducted to assess waveform suitability. Millimeter-wave radar waveform morphology was found to more closely resemble continuous non-invasive blood pressure than photoplethysmography.
|
|
09:30-09:45, Paper ThAT2.5 | |
Physiological Features of Cardiac Ventricle and Valve Dynamics from Wearable Radio-Frequency Sensors |
|
Conroy, Thomas | Cornell University |
Zhou, Jianlin | Cornell University |
Kan, Edwin | Cornell University |
Keywords: Wearable low power, wireless sensing methods, New sensing techniques, Physiological monitoring - Novel methods
Abstract: Abstract— Early detection of cardiovascular diseases via non-invasive, convenient, and continuous monitoring is crucial to reducing preventable deaths. This paper illustrates such monitoring using wearable near-field radio-frequency sensors to analyze ventricle and valve transients, which can be used as indicators of myriad cardiac disorders. We applied a novel vector injection signal processing method to improve timing consistency in ventricular contraction, ventricular relaxation, and valve opening extraction. The median relative timing error in valve opening detection was 14.7ms and 37.8ms for semilunar and atrioventricular valves, respectively, as benchmarked by the S1 and S2 heart sounds from a synchronous phonocardiogram. Clinical Relevance— No wearable sensor currently exists to conveniently and reliably evaluate ventricular and valvular dynamics, specifically valvular opening. Beyond extraction of the heart rate and its variation, the method in this paper has the potential to enable non-invasive measurements of detailed cardiac cycle timing features including valve openings, isovolumetric contraction/relaxation times, and ejection periods, improving the monitoring of patient health away from clinical healthcare centers.
|
|
09:45-10:00, Paper ThAT2.6 | |
A Proof-Of-Concept Real-Time Processing to Characterize Vascular Flow |
|
Shah, Sahil | University of Maryland, College Park |
Töreyin, Hakan | San Diego State University |
Noyan, Utku | University of Maryland, College Park |
Lee, YooJin | University of California, San Francisco |
Keywords: Health monitoring applications, Physiological monitoring - Modeling and analysis, IoT sensors for health monitoring
Abstract: In dialysis patients, monitoring vascular flow of the surgically created arteriovenous fistula (AVF) is critical to indicate the success of the AVF as a dialysis access site. Current gold standard to quantify vascular flow involves external doppler evaluation which requires frequent visits to the clinic. In this paper, we present a proof-of-concept cost-efficient vascular flow monitoring system towards a wearable and robust blood flow monitoring system. The proposed system captures beat-to-beat blood flow from impedance plethysmography (IPG) signal and performs embedded computing to robustly map the changes in the IPG to peripheral blood flow. We present the proof-of-concept results for the embedded real-time blood flow computing from measurements obtained using a custom electrical bioimpedance hardware presented previously elsewhere. We anticipate the results serving as the first step towards potentially eliminating the need for using expensive and bulky systems that require specialized personnel to operate for peripheral blood flow monitoring.
|
|
ThAT3 |
Boisdale-1 |
Theme 04. Machine Learning and Neural Networks Applied to Biological
Systems |
Oral Session |
Chair: Barranco Garcia, Javier | University Hospital Zurich |
Co-Chair: Liang, Jie | University of Illinois at Chicago |
|
08:30-08:45, Paper ThAT3.1 | |
Predicting Drug Mechanics by Deep Learning on Gene and Cell Activities |
|
Dutta, Abhishek | University of Connecticut |
|
|
08:45-09:00, Paper ThAT3.2 | |
Identifying Transient Cells During Reprogramming Via Persistent Homology |
|
Petenkaya, Aydolun | University of Illinois at Chicago |
Manuchehrfar, Farid | University of Illinois at Chicago |
Chronis, Constantinos | University of Illinois at Chicago |
Liang, Jie | University of Illinois at Chicago |
Keywords: Computational modeling - Analysis of high-throughput systems biology data, Systems biology and systems medicine - RNA-seq analysis
Abstract: Single-cell RNA sequencing is a powerful method that helps delineate the regulatory mechanisms shaping the diverse cellular populations. Heterogeneous cell populations consist of individual cells, and the expression of distinct sets of genes can differentiate one sub-population of cells from another, as they are responsible for the emergence of distinct cellular phenotypes. Of particular importance are cells at transition states that bridge these different cellular phenotypes. In this study, we develop a method to identify the cells in transition states bridging different cellular phenotypes. Our approach is based on persistent homology, which enabled us to identify the group of cells located on the boundaries between different sub-populations of cells. We applied this method to study the reprogramming of human fibroblasts toward induced pluripotent stem cells using single-cell time-course data. Even though only the data that is representative of the early stages of the reprogramming process are analyzed, we are able to uncover transient cells bridging different cell sub-populations. The most prominent group of transient cells are found to be enriched for NANOG which is a known stem cell transcription factor that takes part in the maintenance of pluripotency and other stem cell marker genes. Overall, our method can identify cells in transient states bridging major cellular phenotypes, even though they are only a small fraction of the overall cell population. We also discuss how this approach can link the topology of the surface of cellular transcripts and bring order to the transition between cellular states, and how it automatically uncovers the underlying time process.
|
|
09:00-09:15, Paper ThAT3.3 | |
Identification of Children's Tuberous Sclerosis Complex with Multiple-Contrast MRI and 3D Convolutional Network |
|
Jiang, dian | Shenzhen Institutes of Advanced Technology, Chinese Academy of S |
Hu, Zhanqi | Shenzhen Children’s Hospital |
Zhao, Cailei | Shenzhen Children’s Hospital |
Zhao, Xia | Shenzhen Children’s Hospital |
Yang, Jun | Shenzhen Institutes of Advanced Technology, Chinese Academy of S |
Zhu, Yanjie | Shenzhen Institutes of Advanced Technology, Chinese Academy of S |
Liao, Jianxiang | Shenzhen Children’s Hospital |
Liang, Dong | Shenzhen Institutes of Advanced Technology |
Wang, Haifeng | Shenzhen Institutes of Advanced Technology, Chinese Academy of S |
Keywords: Systems modeling - Patient stratification, High throughput data - Machine learning and deep learning, High throughput data - Pattern recognition
Abstract: Identifying rare tuberous sclerosis complex (TSC) children is valuable and crucial. Magnetic resonance imaging (MRI) is used for rare TSC diagnoses. In this work, T2w and FLAIR were combined as a new modality named FLAIR3 to maximize the contrast between TSC lesions and normal-appearing brain tissues. After that, for the first time, we propose to use two different 3D CNN combined with late fusion strategies to diagnose TSC. A total of 520 children were enrolled in the study, including 260 health and 260 TSC children. The experiments had shown that the FLAIR3 could effectively improve the conspicuity of TSC lesions and classification performance. And the results showed the proposed late fusion method can improve the classification performance and achieve the state-of-the-art performance of the AUC of 0.994 and the accuracy of 0.971, which could be treated as an effective computer-aided diagnostic tool to help clinical radiologists diagnose TSC children.
|
|
09:15-09:30, Paper ThAT3.4 | |
Suspicious Skin Lesion Detection in Wide-Field Body Images Using Deep Learning Outlier Detection |
|
Barranco Garcia, Javier | University Hospital Zurich |
Tanadini-Lang, Stephanie | Department of Radiation Oncology, University Hospital Zurich |
Andratschke, Nicolaus | University of Zurich |
Gassner, Mathias | ETH Zürich |
Braun, Ralph P. | University Hospital Zürich |
Keywords: High throughput data - Machine learning and deep learning
Abstract: During consultation dermatologists have to address hundreds of lesions in a limited amount of time. They will not only evaluate the single lesion of interest but more importantly the context of it. Visually comparing the similarity of the majority of lesions within the same patient provides a strong indication for lesions with significantly differing aspects. Deep learning algorithms are capable to identify such outliers, i.e. images that differ considerably from the expected appearance on a larger cohort, and highlight the main differences in those cases. In the present study we evaluate the use of autoencoders as unsupervised tools to detect suspicious skin lesions based on evaluation of real world data acquired during consultation at the USZ Dermatology Clinic.
|
|
09:30-09:45, Paper ThAT3.5 | |
Classification of Seizure Termination Patterns Using Deep Learning on Intracranial EEG |
|
Agarwal, Shubham | University of Cincinnati |
Basu, Ishita | University of Cincinnati |
Kumar, Manish | University of Cincinnati |
Salami, Pariya | Massachusetts General Hospital |
Cash, Sydney | Massachusetts General Hospital |
Keywords: Model building - Signal and pattern recognition, Computational modeling - Analysis of high-throughput systems biology data
Abstract: Seizure termination has received significantly less attention than initiation and propagation and consequently, remains a poorly understood phase of seizure evolution. Yet,its study may have a significant impact on the development of efficient interventional approaches, i.e., it may be critical for the design of treatments that induce or reproduce termination mechanisms that are triggered in self-terminating seizures. In this work, we aim to study temporal and spectral features of intracranial EEG (iEEG) during epileptic seizures to find time-frequency signatures that can predict the termination patterns. We propose a deep learning model for classification of multi channel iEEG epileptic seizure termination pattern into burst suppression and continuous bursting. We decompose the raw time series seizure data into time-frequency maps using Morlet Wavelet Transform. A Convolution Neural Network(CNN) is then trained on cross-patient time-frequency maps to classify the seizure termination patterns. For evaluation of classification performance, we compared the proposed method with k-Nearest Neighbour (k-NN). The CNN is shown to achieve an accuracy of 90% and precision of 92% as compared to 70% accuracy achieved with the k-NN. The proposed model is thus able to capture the temporal and spatial patterns which results in high performance of the classifier. This method of classification can be used to predict how a particular seizure will end and can potentially inform seizure management and treatment.
|
|
09:45-10:00, Paper ThAT3.6 | |
Neural Mass Model-Based Study of Frontal-Temporal Theta Oscillations in Human Subjects During the Performance of a Cognitive Control Task |
|
Ross, Alexander | University of Cincinnati |
Paulk, Angelique C | Massachusetts General Hospital |
Cash, Sydney | Massachusetts General Hospital |
Widge, Alik | Massachusetts General Hospital |
Basu, Ishita | University of Cincinnati |
Keywords: Systems modeling - Clinical applications of biological networks, Computational modeling - Biological networks, Data-driven modeling
Abstract: Cognitive control, the ability to rapidly shift one's attention and behavioral strategy in response to environmental changes, is often compromised across psychiatric disorders. One of the well-validated behavioral paradigms for tapping into the cognitive control circuits is a cognitive interference task, where subjects must suppress a natural response to follow a less intuitive rule. Slower response times on these tasks indicate difficulty exerting control to overcome response conflict. Conflict evokes robust electrophysiological signatures, such as theta (4-8 Hz) oscillations in the prefrontal cortex (PFC). However, the underlying neural mechanisms of conflict-evoked theta oscillations in the PFC are not clear. The objective of this work is to use a neural mass model (NMM) to find feasible cortical networks generating theta oscillations during conflict processing in human subjects. We used intracranial EEG (iEEG) recorded from dorsolateral PFC (dlPFC) and lateral temporal lobe (LTL) of human subjects with intractable epilepsy undergoing invasive monitoring, while they performed a multi-source interference task (MSIT). We used a dynamic causal modeling (DCM) framework to simulate dlPFC-LTL theta using a Jansen-Rit NMM. We found significant evidence for an LTL input into the dlPFC during the initial 500 ms of conflict processing compared to a bidirectional connection between the dlPFC and LTL. We conclude that a neural mass modeling framework can be used to elucidate candidate mechanisms of neural oscillations underlying conflict resolution in human subjects.
|
|
ThAT4 |
Boisdale-2 |
Theme 01. Signal Processing and Classification in Sleep Studies |
Oral Session |
Chair: Mitsis, Georgios D. | McGill University |
Co-Chair: Sakkalis, Vangelis | Foundation for Research and Technology - Hellas (FORTH) |
|
08:30-08:45, Paper ThAT4.1 | |
End-To-End Deep Learning of Polysomnograms for Classification of REM Sleep Behavior Disorder |
|
Brink-Kjær, Andreas | Technical University of Denmark |
Gunter, Katarina Mary | Technical University of Denmark |
Mignot, Emmanuel | Stanford University |
During, Emmanuel Hossein | Center for Sleep Sciences and Medicine, Stanford University, Sta |
Jennum, Poul | University of Copenhagen, Demnar |
Sorensen, Helge B D | Technical University of Denmark |
Keywords: Data mining and big data methods - Machine learning and deep learning methods, Data mining and big data methods - Biosignal classification
Abstract: Rapid eye movement (REM) sleep behavior disorder (RBD) is parasomnia and a prodromal manifestation of Parkinson’s disease. The current diagnostic method relies on manual scoring of polysomnograms (PSGs), a procedure that is time and effort intensive, subject to interscorer variability, and requires high level of expertise. Here, we present an automatic and interpretable diagnostic tool for RBD that analyzes PSGs using end-to-end deep neural networks. We optimized hierarchical attention networks in a 5-fold cross validation directly to classify RBD from PSG data recorded in 143 participants with RBD and 147 age- and sex-matched controls. An ensemble model using logistic regression was implemented to fuse decisions from networks trained in various signal combinations. We interpreted the networks using gradient SHAP that attribute relevance of input signals to model decisions. The ensemble model achieved a sensitivity of 91.4 % and a specificity of 86.3 %. Interpretation showed that electroencephalography (EEG) and leg electromyography (EMG) exhibited most patterns with high relevance. This study validates a robust diagnostic tool for RBD and proposes an interpretable and fully automatic framework for end-to-end modeling of other sleep disorders from PSG data. Clinical relevance – This study presents a novel diagnostic tool for RBD that considers neurophysiologic biomarkers in multiple modalities.
|
|
08:45-09:00, Paper ThAT4.2 | |
Self-Organizing Maps for Contrastive Embeddings of Sleep Recordings |
|
Huijben, Iris | Eindhoven University of Technology |
Nijdam, Arthur A. | Eindhoven University of Technology |
Hermans, Lieke W. A. | Eindhoven University of Technology |
Overeem, Sebastiaan | Kempenhaeghe Foundation, Sleep Medicine Centre |
van Gilst, Merel | Eindhoven University of Technology |
van Sloun, Ruud | Eindhoven University of Technology |
Keywords: Data mining and big data methods - Pattern recognition, Neural networks and support vector machines in biosignal processing and classification
Abstract: Nowadays, high amounts of data can be acquired in various applications, spurring the need for interpretable data representations that provide actionable insights. Algorithms that yield such representations ideally require as little a priori knowledge about the data or corresponding annotations as possible. To this end, we here investigate the use of Kohonen’s Self-Organizing Map (SOM) in combination with data-driven low-dimensional embeddings obtained through self-supervised Contrastive Predictive Coding. We compare our approach to embeddings found with an auto-encoder and, moreover, investigate three ways to deal with node selection during SOM optimization. As a challenging experiment we analyze nocturnal sleep recordings of healthy subjects, and conclude that - for this noisy real-life data -contrastive learning yields a better low-dimensional embedding for the purpose of SOM training, compared to an auto-encoder. In addition, we show that a stochastic temperature-annealed SOM-training outperforms both a deterministic and a non-temperature-annealed stochastic approach. Clinical relevance: The hypnogram has for decades been the clinical standard in sleep medicine, despite the fact that it is a highly simplified representation of a polysomnography recording. We propose a sensor-agnostic algorithm that is able to reveal more intricate patterns in sleep recordings, which might teach us about sleep structure and sleep disorders.
|
|
09:00-09:15, Paper ThAT4.3 | |
Drowsiness Detection from Polysomnographic Data Using Multivariate Selfsimilarity and Eigen-Wavelet Analysis |
|
Lucas, Charles-Gérard | ENS De Lyon |
Abry, Patrice | ENS Lyon, CNRS |
Wendt, Herwig | CNRS, University of Toulouse |
Didier, Gustavo | Tulane University |
Keywords: Time-frequency and time-scale analysis - Wavelets, Physiological systems modeling - Multivariate signal processing
Abstract: Because drowsiness is a major cause in vehicle accidents, its automated detection is critical. Scale-free temporal dynamics is known to be typical of physiological and body rhythms. The present work quantifies the benefits of applying a recent and original multivariate selfsimilarity analysis to several modalities of polysomnographic measurements (heart rate, blood pressure, electroencephalogram and respiration), from the MIT-BIH Polysomnographic Database, to better classify drowsiness-related sleep stages. This study shows that probing jointly temporal dynamics amongst polysomnographic measurements, with a proposed original multivariate multiscale approach, yields a gain of above 5% in the Area-under-Curve quantifying drowsiness-related sleep stage classification performance compared to univariate analysis.
|
|
09:15-09:30, Paper ThAT4.4 | |
Sleep Dynamic Analysis Technology Based on Cross-Phase-Amplitude Transfer Entropy in Multiple Brain Regions |
|
Wang, Yufei | Beijing Institute of Technology |
Shi, Wenbin | Beijing Institute of Technology |
Yeh, Chien-Hung | Beijing Institute of Technology |
Keywords: Causality, Coupling and synchronization - Coherence in biomedical signal processing, Nonlinear dynamic analysis - Biomedical signals
Abstract: Information flow existed across brain regions, and varies dynamically during sleep. In evaluating brain communication and neural-oscillation connectivity across spatiotemporal scales, the phase-amplitude coupling (PAC) is well-explored. However, the directional connectivity is still a deficiency. In this work, we propose a cross-phase-amplitude transfer entropy method in quantifying the characteristics of multi-regional sleep dynamics. The simulation of multivariate nonlinear and nonstationary signals verifies both effectiveness and veracity of the proposed algorithm. The results achieved in sleep EEG of healthy adults indicate that the direction of PAC is from the occipital lobe to the frontal lobe in the Awake and N1 sleep stages. And the flow of PAC turns to the opposite direction for the other sleep stages, i.e., frontal-to-occipital lobe. Besides, the δ-θ/α PAC gradually strengthens with the deepening of the sleep. Of note, the PAC results in the REM sleep stage vary across different frequency pairs. The obtained results support the proposed method as a reliable tool in evaluating brain functions during sleep with brain signals.
|
|
09:30-09:45, Paper ThAT4.5 | |
Slow EEG Oscillation to Characterize Pediatric Sleep Apnea and Associated Cognitive Impairments |
|
Gutierrez, Gonzalo Cesar | University of Valladolid |
Gomez-Pilar, Javier | University of Valladolid, CIF: Q4718001C |
Kheirandish-Gozal, Leila | Section of Sleep Medicine, Department of Pediatrics, Pritzker Sc |
Martín-Montero, Adrián | University of Valladolid |
Álvarez González, Daniel | Biomedical Engineering Group, University of Valladolid, CIF Q471 |
Poza, Jesus | University of Valladolid |
del Campo, Félix | Hospital Del Río Hortega. Universidad De Valladolid |
Gozal, David | Section of Sleep Medicine, Department of Pediatrics, Pritzker Sc |
Hornero, Roberto | University of Valladolid |
Keywords: Physiological systems modeling - Signal processing in physiological systems, Multivariate methods, Signal pattern classification
Abstract: Previous studies have suggested that the typical slow oscillations (SO) characteristics during sleep could be modified in the presence of pediatric obstructive sleep apnea (OSA). Here, we evaluate whether these modifications are significant and if they may reflect cognitive deficits. We recorded the overnight electroencephalogram (EEG) of 294 pediatric subjects (5-9 years old) using eight channels. Then, we divided the cohort in three OSA severity groups (no OSA, mild, and moderate/severe) to characterize the corresponding SO using the spectral maximum in the slow wave sleep (SWS) band delta1 0.1-2 Hz (Max SO), as well as the frequency where this maximum is located (FreqMax SO). Spectral entropy (SpecEn) from delta1 was also included in the analyses. A correlation analysis was performed to evaluate associations of these spectral measures with six OSA-related clinical variables and six cognitive scores. Our results indicate that Max SO could be used as a moderate/severe OSA biomarker while providing useful information regarding verbal and visuo-spatial impairments, and that FreqMax SO emerges as an even more robust indicator of visuospatial function. In addition, we uncovered novel insights regarding the ability of SpecEn in delta1 to characterize OSA-related disruption of sleep homeostasis. Our findings suggest that the information from SO may be useful to automatically characterize moderate/severe pediatric OSA and its cognitive consequences.
|
|
09:45-10:00, Paper ThAT4.6 | |
Towards Sleep Scoring Generalization through Self-Supervised Meta-Learning |
|
Lemkhenter, Abdelhak | Institute of Informatics, University of Bern |
Favaro, Paolo | Institute of Informatics, University of Bern |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Data mining and big data methods - Inter-subject variability and personalized approaches, Data mining and big data methods - Biosignal classification
Abstract: In this work we introduce a novel meta-learning method for sleep scoring based on self-supervised learning. Our approach aims at building models for sleep scoring that can generalize across different patients and recording facilities, but do not require a further adaptation step to the target data. Towards this goal, we build our method on top of the Model Agnostic Meta-Learning (MAML) framework by incorporating a self-supervised learning (SSL) stage, and call it S2MAML. In our analysis, we show that S2MAML can significantly outperform MAML. The gain in performance comes from the SSL stage, which we base on a general purpose pseudo-task that limits the overfitting to the subject-specific patterns present in the training dataset. We show that S2MAML outperforms standard supervised learning and MAML on the SC, ST, ISRUC, UCD and CAP datasets.
|
|
ThAT6 |
Carron-2 |
Theme 10. Sensor Informatics - Behavioral and Physiological Monitoring |
Oral Session |
Chair: Naish, Michael D. | The University of Western Ontario |
Co-Chair: Sazonov, Edward | University of Alabama |
|
08:30-08:45, Paper ThAT6.1 | |
Unobtrusive Heart Rate Monitoring Using Near-Infrared Imaging During Driving |
|
Selvaraju, Vinothini | TU Braunschweig |
Spicher, Nicolai | TU Braunschweig |
Ramakrishnan, Swaminathan | IIT Madras, India |
Deserno, Thomas | TU Braunschweig |
Keywords: Sensor Informatics - Physiological monitoring, Sensor Informatics - Sensor-based mHealth applications, Imaging Informatics - Image registration, segmentation, and compression
Abstract: In-vehicle health monitoring allows for continuous vital sign measurement in everyday life. Eventually, this could lead to early detection of cardiovascular diseases. In this work, we propose non-contact heart rate (HR) monitoring utilizing near-infrared (NIR) camera technology. Ten healthy volunteers are monitored in a realistic driving simulator during resting (5 min) and driving (10 min). We synchronously acquire videos using an out-of-the-shelf, low-cost NIR camera and 3-lead electrocardiography (ECG) serves as ground truth. The MediaPipe face detector delivers the region of interest (ROI) and we determine the HR from the peak with maximum amplitude within the power spectrum of skin color changes. We compare video-based with ECG-based HR, resulting in a mean absolute error (MAE) of 7.8 bpm and 13.0 bpm in resting and driving condition, respectively. As we apply only a simple signal processing pipeline without sophisticated filtering, we conclude that NIR camera-based HR measurements enables unobtrusive and non-contact monitoring to a certain extent, but artifacts from subject movement pose a challenge. If these issues can be addressed, continuous vital sign measurement in everyday life could become reality.
|
|
08:45-09:00, Paper ThAT6.2 | |
HTIDB: Hierarchical Time-Indexed Database for Efficient Storage andAccess to Irregular Time-Series Health Sensor Data |
|
Scott, Grant | University of Missouri |
Saied-Walker, Jamal | University of Missouri |
Marchal, Noah | University of Missouri |
Yu, Hang | University of Missouri |
Skubic, Marjorie | University of Missouri |
Keywords: Sensor Informatics - Sensors and sensor systems, General and theoretical informatics - Data storage, Sensor Informatics - Wireless sensors and systems
Abstract: With the enormous amount of data collected by unobtrusive sensors, the potential of utilizing these data and applying various multi-modal advanced analytics on them is numerous and promising. However, taking advantage of the ever-growing data requires high-performance data-handling systems to enable high data scalability and easy data accessibility. This paper demonstrates robust design, developments, and techniques of a hierarchical time-indexed database for decision support systems leveraging irregular and sporadic time series data from sensor systems, e.g., wearables or environmental. We propose a technique that leverages the flexibility of general purpose, high-scalability database systems, while integrating data analytics focused column stores that leverage hierarchical time indexing, compression, and dense raw numeric data storage. We have evaluated the performance characteristics and tradeoffs of each to understand the data access latencies and storage requirements, which are key elements for capacity planning for scalable systems.
|
|
09:00-09:15, Paper ThAT6.3 | |
Multimodal Sensor-Based Identification of Stress and Compulsive Actions in Children with Obsessive-Compulsive Disorder for Telemedical Treatment |
|
Thierfelder, Annika | Hertie Institute for Clinical Brain Research |
Primbs, Jonas | University of Tübingen |
Severitt, Björn | University of Tübingen |
Hohnecker, Carolin Sarah | Psychiatry, University Hospital Tübingen |
Kühnhausen, Jan | Psychiatry, University Hospital Tübingen |
Alt, Annika Kristin | Psychiatry, University Hospital Tübingen |
Pascher, Anja | Psychiatry, University Hospital Tübingen |
Wörz, Ursula | University Hospital Tübingen |
Passon, Helene | University of Hohenheim |
Seemann, Jens | Hertie Institute for Clinical Brain Research |
Ernst, Christian | University of Hohenheim |
Lautenbacher, Heinrich | University Hospital of Tuebingen |
Holderried, Martin | University Hospital Tübingen |
Kasneci, Enkelejda | University of Tübingen |
Giese, Martin | Hertie Institute for Clinical Brain Research |
Bulling, Andreas | University of Stuttgart |
Menth, Michael | University of Tübingen |
Barth, Gottfried Maria | University Hospital Tübingen |
Ilg, Winfried | Hertie Institute for Clinical Brain Research |
Hollmann, Karsten | University Hospital Tübingen |
Renner, Tobias Johann | University Hospital Tübingen |
Keywords: Sensor Informatics - Wearable systems and sensors, Sensor Informatics - Physiological monitoring, Sensor Informatics - Sensor-based mHealth applications
Abstract: In modern psychotherapy, digital health technology offers advanced and personalized therapy options, increasing availability as well as ecological validity. These aspects have proven to be highly relevant for children and adolescents with obsessive-compulsive disorder (OCD). Exposure and Response Prevention therapy, which is the state-of-the-art treatment for OCD, builds on the reconstruction of everyday life exposure to anxious situations. However, while compulsive behavior predominantly occurs in home environments, exposure situations during therapy are limited to clinical settings. Telemedical treatment allows to shift from this limited exposure reconstruction to exposure situations in real life. In the SSTeP KiZ study (smart sensor technology in telepsychotherapy for children and adolescents with OCD), we combine video therapy with wearable sensors delivering physiological and behavioral measures to objectively determine the stress level of patients. The setup allows to gain information from exposure to stress in a realistic environment both during and outside of therapy sessions. In a first pilot study, we explored the sensitivity of individual sensor modalities to different levels of stress and anxiety. For this, we captured the obsessive-compulsive behavior of five adolescents with an ECG chest belt, inertial sensors capturing hand movements, and an eye tracker. Despite their prototypical nature, our results deliver strong evidence that the examined sensor modalities yield biomarkers allowing for personalized detection and quantification of stress and anxiety. This opens up future possibilities to evaluate the severity of individual compulsive behavior based on multi-variate state classification in real-life situations.
|
|
09:15-09:30, Paper ThAT6.4 | |
Multi-Modal Prosthesis Control Using sEMG, FMG and IMU Sensors |
|
Gharibo, Jason | Western University |
Naish, Michael D. | The University of Western Ontario |
Keywords: Sensor Informatics - Wearable systems and sensors, Sensor Informatics - Multi-sensor data fusion, Sensor Informatics - Intelligent medical devices and sensors
Abstract: In this work, a novel multi-modal device that allows data to simultaneously be collected from three noninvasive sensor modalities was created. Force myography (FMG), surface electromyography (sEMG), and inertial measurement unit (IMU) sensors were integrated into a wearable armband and used to collect signal data while subjects performed gestures important for the activities of daily living (ADL). An established machine learning algorithm was used to decipher the signals to predict the user's intent/gesture being held, which could be used to control a prosthetic device. Using all three modalities provided statistically-significant improvements over most other modality combinations, as it provided the most accurate and consistent classification results. Clinical relevance—The use of three sensing modalities can improve gesture-based control of upper-limb prosthetics.
|
|
09:30-09:45, Paper ThAT6.5 | |
Modeling Individual Differences in Food Metabolism through Alternating Least Squares |
|
Das, Anurag | Texas A&M University, College Station |
Mortazavi, Bobak | Texas A&M University |
Deutz, Nicolaas EP | Texas A&M University |
Gutierrez-Osuna, Ricardo | Texas A&M University |
Keywords: Sensor Informatics - Wearable systems and sensors, General and theoretical informatics - Machine learning
Abstract: Understanding how macronutrients (e.g., carbohydrates, protein, fat) affect blood glucose is of broad interest in health and dietary research. The general effects are well known, e.g., adding protein and fat to a carbohydrate-based meal tend to reduce blood glucose. However, there are large individual differences in food metabolism, to where the same meal can lead to different glucose responses across individuals. To address this problem, we present a technique that can be used to simultaneously (1) model macronutrients’ effects on glucose levels over time and (2) capture inter-individual differences in macronutrient metabolism. The technique performs a linear decomposition of glucose responses, alternating between estimating the macronutrients’ effect over time and capturing an individual’s sensitivity to macronutrients. On an experimental dataset containing glucose responses to a variety of mixed meals, the technique is able to extract basis functions for the macronutrients that are consistent with their hypothesized effects on PPGRs, and also characterize how macronutrients affect individuals differently.
|
|
09:45-10:00, Paper ThAT6.6 | |
A Comparative Study of Deep Learning Algorithms for Detecting Food Intake |
|
Ghosh, Tonmoy | University of Alabama |
Sazonov, Edward | University of Alabama |
Keywords: Sensor Informatics - Wearable systems and sensors, Sensor Informatics - Data inference, mining, and trend analysis, General and theoretical informatics - Pattern recognition
Abstract: The choice of appropriate machine learning algorithms is crucial for classification problems. This study compares the performance of state-of-the-art time-series deep learning algorithms for classifying food intake using sensor signals. The sensor signals were collected with the help of a wearable sensor system (the Automatic Ingestion Monitor v2, or AIM-2). AIM-2 used an optical and 3-axis accelerometer sensor to capture temporalis muscle activation. Raw signals from those sensors were used to train five classifiers (multilayer perceptron (MLP), time Convolutional Neural Network (time-CNN), Fully Convolutional Neural Network (FCN), Residual Neural Network (ResNet), and Inception network) to differentiate food intake (eating and drinking) from other activities. Data were collected from 17 pilot subjects over the course of 23 days in free-living conditions. A leave one subject out cross-validation scheme was used for training and testing. Time-CNN, FCN, ResNet, and Inception achieved average balanced classification accuracy of 88.84%, 90.18%, 93.47%, and 92.15%, respectively. The results indicate that ResNet outperforms other state-of-the-art deep learning algorithms for this specific problem.
|
|
ThAT8 |
Dochart-2 |
Theme 09. Diagnostic and Therapeutic Devices I |
Oral Session |
Chair: Linte, Cristian A. | Rochester Institute of Technology |
Co-Chair: Prakash, Punit | Kansas State University |
|
08:30-08:45, Paper ThAT8.1 | |
Investigating Uncertainty in Augmented Reality Enhanced Renal Navigation Using in Vitro Patient-Specific Tissue-Mimicking Phantoms |
|
Jackson, Peter | Rochester Institute of Technology |
Merrell, Kelly | Rochester Institue of Technology |
Simon, Richard A. | Rochester Institute of Technology |
Linte, Cristian A. | Rochester Institute of Technology |
Keywords: Robotic-aided therapies - Computer-assisted surgery systems, Image-guided therapies - Biopsy systems & technologies
Abstract: To improve the outcome of minimally invasive renal interventions, traditional video-guided needle navigation can be enhanced by tracking the needle, guiding the needle using video imaging, and augmenting the surgical scene with pre-procedural images or models of the anatomy. In our previous work we studied, both through simulations and in vitro experiments, the uncertainty associated with the model-to-phantom registration, as well as the camera-tracker calibration and video-guided navigation. In this work, we characterize the overall navigation uncertainty using tissue emulating patient-specific kidney phantoms featuring both virtual and physical internal targets. Pre-procedural models of the kidney phantoms and internal targets are generated from cone-beam CT images, and are registered to their intra-operative physical counterparts. The user then guides the needle insertion to reach the internal targets using video-based imaging augmented with a virtual representation of the needle tracked in real time. Following navigation, we acquire post-procedural cone-beam CT images of the phantoms and inserted needles. These images are used to determine the ground truth needle navigation accuracy (i.e., needle to target distance) against which the intra-operative navigation accuracy (i.e., intra-op needle tip to target distance) is assessed. We also explore a method to update the pre-procedural model to physical phantom registration intra-operatively using tracked video imaging, with the overall goal to improve overall navigation accuracy in the event of sub-optimal initial image-to-phantom registration. Our results showed a navigation error of less than 3.5 mm in gelatin phantoms and less than 6.5 mm in PVA phantoms. Following registration correction intra-operatively, we showed an overall improvement in navigation from roughly 6 mm RMS to approximately 2 mm RMS error, which is acceptable given the inherent tracking, 3D printing and phantom manufacturing limitations.
|
|
08:45-09:00, Paper ThAT8.2 | |
Diffuse Reflectance Spectroscopy for the Assessment of Steatosis in Liver Phantom and Liver Donors - a Pilot Study |
|
S. Rajamani, Allwyn | Indian Institute of Technology Madras |
J, Kuzhandai Shamlee | Indian Institute of Technology Madras |
Rammohan, Ashwin | Dr. Rela Institute & Medical Centre |
Sai, V.V.R. | Indian Institute of Technology Madras |
Rela, Mohamed | Dr. Rela Institute & Medical Centre |
|
|
09:00-09:15, Paper ThAT8.3 | |
Digital-Twin-Based Online Parameter Personalization for Implantable Cardiac Defibrillators |
|
Lai, Mincai | ShanghaiTech University |
Yang, Haochen | ShanghaiTech University |
Gu, jicheng | ShanghaiTech University |
Chen, Xinye | The University of Manchester |
Jiang, Zhihao | ShanghaiTech University |
Keywords: Clinical engineering -Verification and validation of diagnostic & therapeutic systems / technologies, Defibrillators (implantable or external), Implantable devices for cardiac monitoring
Abstract: Implantable cardioverter defibrillators (ICDs) are developed to provide timely therapies when adverse patient conditions are detected. Device therapies need to be adjusted for individual patients and evolving patient conditions, which can be achieved by adjusting device parameter settings. However, there are no validated clinical guidelines for parameter personalization, especially for patients with complex and rare conditions. In this paper, we propose a reinforcement learning framework for online parameter personalization of ICDs. Heart states can be inferred from ECG signals from ECG patches, which can be used to create a digital twin of the patient. Reinforcement learning then use the digital twin as environment to explore parameter settings with less misdiagnosis. Experiments were performed on three virtual patients with specific and evolving heart conditions, and the result shows that our proposed approach can identify ICD parameter settings that can achieve better performance compared to default parameter settings.
|
|
09:15-09:30, Paper ThAT8.4 | |
Predicting Isolated Nocturnal Hypertension Using Dawn and Dusk Home Blood Pressure Monitoring |
|
Davidson, Shaun | University of Oxford |
Roman, Cristian | University of Oxford |
Tarassenko, Lionel | University of Oxford |
Keywords: Wearable or portable devices for vital signal monitoring, Physiological monitoring & diagnistic devices - Blood pressure, Clinical engineering - Health technology / system management and assessment
Abstract: Hypertension is a major global cause of morbidity and mortality. Home Blood Pressure Monitoring (HBPM) has the potential to help diagnose patients experiencing isolated nocturnal hypertension who may otherwise be missed. This paper investigates potential diagnostic thresholds for diagnosing isolated nocturnal hypertension using dawn and dusk HBPM measurements in the BP-Eth ambulatory blood pressure monitoring (ABPM) database. Depending on whether European or American diagnostic guidelines for hypertension were used, incidence of isolated nocturnal hypertension in the BP-Eth database was 17.1% or 16.8%, respectively. Using averaged dawn and dusk HBPM measurements to diagnose isolated nocturnal hypertension yielded an AUROC of 0.79 (European guidelines) or 0.84 (American guidelines). The SBP and DBP diagnostic thresholds required to detect 80% of cases of isolated nocturnal hypertension were found to be 125.4 mmHg and 75.7 mmHg, respectively (European guidelines) or 117.6 mmHg and 74.3 mmHg, respectively (American guidelines). These thresholds corresponded to a sensitivity of 80% and specificity of 63% (European guidelines) or sensitivity of 83% and specificity of 65% (American guidelines). These results demonstrate the potential for HBPM to function as an intermediate step in screening patients, determining which patients require more intensive ABPM monitoring for detection of isolated nocturnal hypertension.
|
|
09:30-09:45, Paper ThAT8.5 | |
Computational Analysis of Balloon Catheter Behaviour at Variable Inflation Levels |
|
Yao, Junke | University College London |
Bosi, Giorgia Maria | University College London |
Burriesci, Burriesci | Italian National Workers Compensation Authority (INAIL) |
Wurdemann, Helge Arne | University College London |
Keywords: Models and simulations of therapeutic devices and systems, Cardiovascular assessment and diagnostic technologies
Abstract: Aortic valvuloplasty is a minimally invasive procedure for the dilatation of stenotic aortic valves. Rapid ventricular pacing is an established technique for balloon stabilization during this procedure. However, low cardiac output due to the pacing is one of the inherent risks, which is also associated with several potential complications. This paper proposes a numerical modelling approach to understand the effect of different inflation levels of a valvuloplasty balloon catheter on the positional instability caused by a pulsating blood flow. An unstretched balloon catheter model was crimped into a tri-folded configuration and then inflated to several levels. Ten different inflation levels were then tested, and a Fluid-Structure Interaction model was built to solve interactions between the balloon and the blood flow modelled in an idealised aortic arch. Our computational results show that the maximum displacement of the balloon catheter increases with the inflation level, with a small step at around 50% inflation and a sharp increase after reaching 85% inflation. This work represents a substantial progress towards the use of simulations to solve the interactions between a balloon catheter and pulsating blood flow.
|
|
09:45-10:00, Paper ThAT8.6 | |
Towards Micropump and Microneedle-Based Drug Delivery Using Micro Transdermal Interface Platforms (MicroTIPs) |
|
Tjulkins, Fjodors | Tyndall National Institute, University College Cork |
Sebastian, Ryan | Tyndall National Institute |
Guillerm, Theo | Tyndall National Institute |
Clover, A. James P. | University College Cork |
Hu, Yuan | Tyndall National Institute, University College Cork |
Lyness, Alexander | West Pharmaceutical Services |
O'Mahony, Conor | Tyndall National Institute, University College Cork |
Keywords: Transdermal drug delivery, Infusion pumps, Robotic-aided therapies - Wireless therapeutic systems
Abstract: Micro Transdermal Interface Platforms (MicroTIPs) will combine minimally invasive microneedle arrays with highly miniaturized sensors, actuators, control electronics, wireless communications and artificial intelligence. These patch-like devices will be capable of autonomous physiological monitoring and transdermal drug delivery, resulting in increased patient adherence and devolved healthcare. In this paper, we experimentally demonstrate the feasibility of controlled transdermal drug delivery using a combination of 500 um tall silicon microneedles, a commercial micropump, pressure and flow sensors, and bespoke electronics. Using ex-vivo human skin samples and a customized application/retraction system, leak-free delivery of volumes ranging from 0.7-1.1 mL has been achieved in under one hour.
|
|
ThAT9 |
Gala |
Theme 02. Image Reconstruction and Enhancement |
Oral Session |
Chair: Lu, Hengfa | The University of Texas at Austin |
|
08:30-08:45, Paper ThAT9.1 | |
Active Sampling for Accelerated MRI with Low-Rank Tensors |
|
He, Zichang | University of California, Santa Barbara |
Zhao, Bo | University of Texas at Austin |
Zhang, Zheng | University of California, Santa Barbara |
Keywords: Image reconstruction and enhancement - Compressed sensing / Sampling, Image reconstruction and enhancement - Machine learning / Deep learning approaches, Machine learning / Deep learning approaches
Abstract: Magnetic resonance imaging (MRI) is a powerful imaging modality that revolutionizes medicine and biology. The imaging speed of high-dimensional MRI is often limited, which constrains its practical utility. Recently, low-rank tensor models have been exploited to enable fast MR imaging with sparse sampling. Most existing methods use some pre-defined sampling design, and active sensing has not been explored for low-rank tensor imaging. In this paper, we introduce an active low-rank tensor model for fast MR imaging. We propose an active sampling method based on a Query-by-Committee model, making use of the benefits of low-rank tensor structure.Numerical experiments on a 3-D MRI data set with Cartesian sampling designs demonstrate the effectiveness of the proposed method.
|
|
08:45-09:00, Paper ThAT9.2 | |
Improved Balanced Steady-State Free Precession Based MR Fingerprinting with Deep Autoencoders |
|
Lu, Hengfa | The University of Texas at Austin |
Ye, Huihui | Zhejiang University |
Zhao, Bo | University of Texas at Austin |
Keywords: Image reconstruction and enhancement - Compressed sensing / Sampling, Iterative image reconstruction, Image reconstruction and enhancement - Machine learning / Deep learning approaches
Abstract: Magnetic Resonance (MR) Fingerprinting is an emerging transient-state imaging paradigm, which enables the quantization of multiple MR tissue parameters in a single experiment. Balanced steady-state free precession (bSSFP)-based MR Fingerprinting has excellent signal-to-noise characteristics and also allows for acquiring both tissue parameter maps and field inhomogeneity maps. However, field inhomogeneity often results in complex magnetization evolutions in bSSFP-based MR Fingerprinting, which creates significant challenges in image reconstruction. In this paper, we introduce a new method to address the image reconstruction problem. The proposed method incorporates a low-dimensional nonlinear manifold learned from an ensemble of magnetization evolutions using a deep autoencoder. It provides much better representation power than a low-dimensional linear subspace in capturing complex magnetization evolutions. We formulate the image reconstruction problem with this nonlinear model and solve the resulting optimization problem using an algorithm based on variable splitting and the alternating direction method of multipliers. We evaluate the performance of the proposed method using numerical experiments and demonstrate that it significantly outperforms the state-of-art method using a linear subspace model.
|
|
09:00-09:15, Paper ThAT9.3 | |
Perceptual cGAN for MRI Super-Resolution |
|
Almahfouz Nasser, Sahar | Indian Institute of Technology Bombay |
Shamsi, Saqib | Whirlpool Corporation |
Mahesh, Bundele, Valay | IIT Bombay |
Garg, Bhavesh | Indian Institute of Technology Bombay |
Sethi, Amit | Indian Institute of Technology Bombay |
Keywords: Image reconstruction and enhancement - Machine learning / Deep learning approaches, Image reconstruction and enhancement - Image synthesis, Image retrieval
Abstract: Capturing high-resolution magnetic resonance(MR) images is a time consuming process, which makes it unsuitable for medical emergencies and pediatric patients. Low-resolution MR imaging, by contrast, is faster than its high-resolution counterpart, but it compromises on fine details necessary for a more precise diagnosis. Super-resolution (SR), when applied to low-resolution MR images, can help increase their utility by synthetically generating high-resolution images with little additional time. In this paper, we present a SR technique for MR images that is based on generative adversarial networks(GANs), which have proven to be quite useful in generating sharp-looking details in SR. We introduce a conditional GAN with perceptual loss, which is conditioned upon the input low-resolution image, which improves the performance for isotropic and anisotropic MRI super-resolution.
|
|
09:15-09:30, Paper ThAT9.4 | |
Future Image Prediction of Gait Plantar Pressure Using Spatio-Temporal Transformer |
|
Mona, Ahmadian | Tarbiat Modares University |
Shirian, Amir | University of Warwick |
Rahmani-Boldaji, Sadegh | Sheikh Bahaei University |
Keywords: Image reconstruction and enhancement - Machine learning / Deep learning approaches, Image reconstruction and enhancement - Image synthesis, Image feature extraction
Abstract: Gait is one of the most frequently used forms of human movement during daily activities. The majority of works focus on exploring the dynamic factors during gait. Different from previous works, we adapt an image prediction task for anticipating the next frame in process of gait. In this work, we present a novel framework for human gait plantar pressure prediction using Spatio-temporal Transformer. We train the model to predict the next plantar pressure image in an image series while also learning frame feature encoders that predict the features of subsequent frames in the sequence. We proposed two new components in our loss function for considering temporality as well as smaller values in the image. Our method has the advantage over existing models in that it preserves the sequential sequence of observed images while also preserving long-range dependency, which are both important for the prediction. Our model achieves superior results over several competitive baselines on the CAD WALK database. Clinical relevance— This work can be used in robotic exoskeleton devices which are intelligent systems designed to improve gait performance and quality of life for the wearer that are being used to assist the recovery of walking ability for patients with disorders.
|
|
09:30-09:45, Paper ThAT9.5 | |
Cross-Correlation Full Waveform Inversion for Sound Speed Reconstruction in Ultrasound Computed Tomography |
|
Zhao, Yue | Harbin Institute of Technology |
Zhang, Nuomin | Harbin Institute of Technology |
Lu, Xin | De Montfort University |
Yuan, Yu | Harbin Institute of Technology |
Shen, Yi | Harbin Institute of Technology |
Keywords: Image reconstruction and enhancement - Tomographic reconstruction, Ultrasound imaging - Breast
Abstract: Ultrasound computed tomography (USCT) is considered to have great potential for breast cancer screening. Compared with the ray based methods, the reconstructed image using full waveform inversion (FWI) methods have higher spatial resolution. However, the results of FWI is difficult to converge to the real value when cycle skipping occurs. In this paper, a cross-correlation full waveform inversion (CC-FWI) is proposed for USCT image reconstruction. In the first stage, the ajoint source is adjusted as the residual of predicted signal and time-shifted measured signal to avoid cycle skipping. In the remaining stage, the FWI with source encoding is employed to accelerate convergence. The simulations are conducted to demonstrate the validity of the proposed algorithm. The root mean squared error (RMSE) of the proposed algorithm is much smaller than that of conventional FWI. The results suggest that CC-FWI is effective in avoiding cycle skipping. Clinical relevance— New imaging modalities of high resolution, safety to examines for early-stage breast cancer imaging are urgently needed for researching and development. Ultrasound computed tomography (USCT) is supposed to meet the above requirements and it can be potentially deployed in breast scanning.
|
|
ThAT10 |
Forth |
Theme 02. Digital Pathology |
Oral Session |
Chair: Sikaroudi, Milad | Kimia Lab, University of Waterloo |
Co-Chair: Garcia Martin, Natalia | University of Oxford |
|
08:30-08:45, Paper ThAT10.1 | |
A Comparison of Video-Based Methods for Neonatal Body Motion Detection |
|
Peng, Zheng | Eindhoven University of Technology |
van de Sande, Dennis | Eindhoven University of Technology |
Lorato, Ilde | Eindhoven University of Technology |
Long, Xi | Eindhoven University of Technology and Philips Research |
Liang, Rong-Hao | Eindhoven University of Technology |
Andriessen, Peter | Maxima Medical Center |
Cottaar, Ward | Eindhoven University of Technology |
Stuijk, Sander | TU Eindhoven |
van Pul, Carola | Maxima Medical Center |
Keywords: Image analysis and classification - Digital Pathology, Image classification, Image feature extraction
Abstract: Preterm infants in a neonatal intensive care unit (NICU) are continuously monitored for their vital signs, such as heart rate and oxygen saturation. Body motion patterns are documented intermittently by clinical observations. Changing motion patterns in preterm infants are associated with maturation and clinical events such as late-onset sepsis and seizures. However, continuous motion monitoring in the NICU setting is not yet performed. Video-based motion monitoring is a promising method due to its non-contact nature and therefore unobtrusiveness. This study aims to determine the feasibility of simple video-based methods for infant body motion detection. We investigated and compared four methods to detect the motion in videos of infants, using two datasets acquired with different types of cameras. The thermal dataset contains 32 hours of annotated videos from 13 infants in open beds. The RGB dataset contains 9 hours of annotated videos from 5 infants in incubators. The compared methods include background substruction (BS), sparse optical flow (SOF), dense optical flow (DOF), and oriented FAST and rotated BRIEF (ORB). The detection performance and computation time were evaluated by the area under receiver operating curves (AUC) and run time. We conducted experiments to detect motion and gross motion respectively. In the thermal dataset, the best performance of both experiments is achieved by BS with mean (standard deviation) AUCs of 0.86 (0.03) and 0.93 (0.03). In the RGB dataset, SOF outperforms the other methods in both experiments with AUCs of 0.82 (0.10) and 0.91 (0.05). All methods are efficient to be integrated into a camera system when using low-resolution thermal cameras.
|
|
08:45-09:00, Paper ThAT10.2 | |
Development of an Image-Based Methodology for the Evaluation of Histopathological Features in Human Meningioma |
|
Sierra, Ana | Universitat Politècnica De València |
San-Miguel, Teresa | Universitat De València |
Monleon, Daniel | Hospital Clinico Universitario De Valencia |
Moratal, David | Universitat Politècnica De València |
Keywords: Image analysis and classification - Digital Pathology, Image feature extraction, Optical imaging
Abstract: Meningioma is the most common intracranial tumor in adulthood. With a clear female predominance and a recurrence rate that reaches 20%, it is, despite being considered a benign tumor, a pathology that greatly compromises post-diagnosis quality of life. Its prone to recur or progress to a higher degree is difficult to predict in the absence of obvious histological criteria. This project aims to develop an automatic methodology to aid in the diagnosis of meningiomas that is objective and easily reproducible. The methodology is based on histopathological image analysis using artificial intelligence and machine learning algorithms. It includes a semi-automatic process of identification and cleaning of the scanned samples, an automatic detection of the nuclei of each image and, finally, the parameterization of the samples. The obtained data together with the clinical information will be analyzed using statistical methods in order to provide a methodology to support clinical diagnosis and decision-making in patient management. The result is the development of an effective methodology that generates a set of data associated with morphological parameters with different trends according to the pathological groups studied. A tool has been developed that allows an effective semiautomatic analysis of the images to evaluate these parameters in an objective and reproducible way, helping in clinical decision-making and facilitating to undertake projects with large sample series.
|
|
09:00-09:15, Paper ThAT10.3 | |
Hospital-Agnostic Image Representation Learning in Digital Pathology |
|
Sikaroudi, Milad | Kimia Lab, University of Waterloo |
Rahnamayan, Shahryar | University of Ontario Institute of Technology (UOIT) |
Tizhoosh, Hamid Reza | University of Waterloo |
Keywords: Image analysis and classification - Digital Pathology, Image analysis and classification - Machine learning / Deep learning approaches, Image feature extraction
Abstract: Whole Slide Images (WSIs) in digital pathology are used to diagnose cancer subtypes. The difference in procedures to acquire WSIs at various trial sites gives rise to variability in the histopathology images, thus making consistent diagnosis challenging. These differences may stem from variability in image acquisition through multi-vendor scanners, variable acquisition parameters, and differences in staining procedure; as well, patient demographics may bias the glass slide batches before image acquisition. These variabilities are assumed to cause a domain shift in the images of different hospitals. It is crucial to overcome this domain shift because an ideal machine-learning model must be able to work on the diverse sources of images, independent of the acquisition center. A domain generalization technique is leveraged in this study to improve the generalization capability of a Deep Neural Network (DNN), to an unseen histopathology image set (i.e., from an unseen hospital/trial site) in the presence of domain shift. According to experimental results, the conventional supervised-learning regime generalizes poorly to data collected from different hospitals. However, the proposed hospital-agnostic learning can improve the generalization considering the low-dimensional latent space representation visualization, and classification accuracy results.
|
|
09:15-09:30, Paper ThAT10.4 | |
Rethinking ImageNet Pretraining for Computational Histopathology |
|
Ray, Indranil | IIT Kharagpur |
Raipuria, Geetank | Lead Scientist, AIRAMATRIX PVT. LTD |
Singhal, Nitin | AIRA Matrix |
Keywords: Image analysis and classification - Digital Pathology, Image analysis and classification - Machine learning / Deep learning approaches, Image classification
Abstract: Transfer learning from ImageNet pretrained weights is widely used when training Deep Learning models on a Histopathology dataset. However, the visual features of the two domains are different. Rather than ImageNet pretrained weights, pre-training on a Histopathology dataset may provide better initialization. To prove this hypothesis, we train two commonly used Deep Learning model architectures - ResNet and DenseNet on a complex Histopathology classification dataset, and compare transfer learning performance with ImageNet pretrained weights. Based on the fine-tuning on three histopathology datasets including two different stains (H&E and IHC), we show that the domain specific pretrained weights are better suited for transfer learning. This is reflected by higher performance, lower training time as well as better feature reuse.
|
|
09:30-09:45, Paper ThAT10.5 | |
A Graph Based Neural Network Approach to Immune Profiling of Multiplexed Tissue Samples |
|
Garcia Martin, Natalia | University of Oxford |
Malacrino, Stefano | University of Oxford |
Wojciechowska, Marta | University of Oxford |
Campo, Leticia | University of Oxford |
Jones, Helen | Oxford University Hospitals |
Wedge, David | University of Manchester |
Holmes, Chris | University of Oxford |
Sirinukunwattana, Korsuk | The University of Oxford |
Sailem, Heba | University of Oxford |
Verrill, Clare | Nuffield Department of Surgical Sciences and Oxford NIHR Biomedi |
Rittscher, Jens | University of Oxford |
|
|
09:45-10:00, Paper ThAT10.6 | |
Attention-Based Multiple Instance Learning with Self-Supervision to Predict Microsatellite Instability in Colorectal Cancer from Histology Whole-Slide Images |
|
Leiby, Jacob | University of Pennsylvania |
Hao, Jie | University of Pennsylvania |
Kang, Gyeong Hoon | Seoul National University Hospital |
Park, Ji Won | Seoul National University Hospital |
Kim, Dokyoon | University of Pennsylvania |
Keywords: Image analysis and classification - Digital Pathology, Image analysis and classification - Machine learning / Deep learning approaches
Abstract: Microsatellite instability (MSI) is a clinically important characteristic of colorectal cancer. Standard diagnosis of MSI is performed via genetic analyses, however these tests are not always included in routine care. Histopathology whole-slide images (WSIs) are the gold-standard for colorectal cancer diagnosis and are routinely collected. This study develops a model to predict MSI directly from WSIs. Making use of both weakly- and self-supervised deep learning techniques, the proposed model shows improved performance over conventional deep learning models. Additionally, the proposed framework allows for visual interpretation of model decisions. These results are validated in internal and external testing datasets.
|
|
ThAT11 |
Lomond |
Theme 06. Stimulation of Neural Tissue |
Oral Session |
Chair: Guiraud, David | INRIA |
Co-Chair: Fridman, Gene | Johns Hopkins University |
|
08:30-08:45, Paper ThAT11.1 | |
Differential Co-Expression Analysis of RNA-Seq Data Reveals Novel Potential Biomarkers of Device-Tissue Interaction |
|
Moore, Michael | Michigan State University |
Thompson, Cort | Michigan State University |
Reimers, Mark | Michigan State University |
Purcell, Erin | Michigan State University |
Keywords: Neural interfaces - Tissue-electrode interface, Neural interfaces - Biomaterials, Neural interfaces - Bioelectric sensors
Abstract: The biological response to electrodes implanted in the brain has been a long-standing barrier to achieving a stable tissue device-interface. Understanding the mechanisms underlying this response could explain phenomena including recording instability and loss, shifting stimulation thresholds, off-target effects of neuromodulation, and stimulation-induced depression of neural excitability. Our prior work detected differential expression in hundreds of genes following device implantation. Here, we extend upon that work by providing new analyses using differential co-expression analysis, which identifies changes in the correlation structure between groups of genes detected at the interface in comparison to control tissues. We used an “eigengene” approach to identify hub genes associated with each module. Our work adds to a growing body of literature which applies new techniques in molecular biology and computational analysis to long-standing issues surrounding electrode integration with the brain.
|
|
08:45-09:00, Paper ThAT11.2 | |
Selectivity of Upper Limb Posterior Root Muscle Reflexes Via Cervicothoracic Spinal Cord Stimulation |
|
Fleming, Neil | Trinity College Dublin |
Taylor, Clare | Trinity College Dublin, the University of Dublin |
Etzelmueller, Mark | Trinity College Dublin |
Gill, Conor | Trinity College Dublin |
O'Keeffe, Clodagh | Trinity College Dublin |
Mahony, Nicholas | Trinity College Dublin |
Reilly, Richard | Trinity College Dublin |
Keywords: Neural stimulation, Neuromuscular systems - EMG models, Neuromuscular systems - Central mechanisms
Abstract: Recent studies have reported that transcutaneous spinal stimulation (tSCS) may facilitate improved upper limb motor function in those with incomplete tetraplesia. However, little is known about how tSCS engages upper limb motor pools. This study aimed to explore the extent to which discrete upper limb motor pools can be selectively engaged via altering stimulus location and intensity. 14 participants with intact nervous systems completed two test visits, during which posterior root-muscle reflexes (PRMR) were evoked via a 3x3 cathode matrix applied over the cervicothoracic spine. An incremental recruitment curve at C7 vertebral level was initially performed to attain minimal threshold intensity (MTI) in each muscle. Paired pulses (1ms square monophasic with inter-pulse interval of 50ms) were subsequently delivered at a frequency of 0.25Hz at two intensities (MTI and MTI+20%) across all nine locations. in a random order. Evoked response to the 1st (PRMR1) and 2nd (PRMR2) stimuli were recorded from four upper limb muscles. A significant effect of spinal level was observed in all muscles for PRMR1 with greater responses recorded more caudally. Unexpectedly, contralateral cathode placement significantly increased PRMR1 in Biceps Brachii (P=0.012), Flexor Carpi Radialis (P=0.035) and Abductor Pollicis Brevis (P=0.001). Post-activation depression (PAD) was also significantly increased with contralateral cathode placement in Biceps Brachii (P=0.001), Triceps Brachii (P=0.012) and Flexor Carpi Radialis (P=0.0001). These results suggest that some level of unilateral motor pool selectivity may be attained via altering stimulus intensity and location during cervicothoracic tSCS.
|
|
09:00-09:15, Paper ThAT11.3 | |
Demonstration of an Optimized Large-Scale Optogenetic Cortical Interface for Non-Human Primates* |
|
Griggs, Devon | University of Washington |
Bloch, Julien | University of Washington, Seattle |
Fisher, Shawn | University of Washington |
Ojemann, William | University of Pennsylvania |
Coubrough, Kali | University of Washington |
Khateeb, Karam | University of Washington |
Chu, Marcus | University of Washington |
Yazdan-Shahmorad, Azadeh | University of Washington |
Keywords: Neural interfaces - Implantable systems, Neural stimulation, Neural interfaces - Microelectrode technology
Abstract: Abstract— Optogenetics is a powerful neuroscientific tool which allows neurons to be modulated by optical stimulation. Despite widespread optogenetic experimentation in small animal models, optogenetics in non-human primates (NHPs) remains a niche field, particularly at the large scales necessary for multi-regional neural research. We previously published a large-scale, chronic optogenetic cortical interface for NHPs which was successful but came with a number of limitations. In this work, we present an optimized interface which improves upon the stability and scale of our previous interface while using more easily replicable methods to increase our system’s availability to the scientific community. Specifically, we (1) demonstrate the long-term (~3 months) optical access to the brain achievable using a commercially-available transparent artificial dura with embedded electrodes, (2) showcase large-scale optogenetic expression achievable with simplified (magnetic resonance-free) surgical techniques, and (3) effectively modulated the expressing areas at large scales (~1 cm2) by light emitting diode (LED) arrays assembled in-house.
|
|
09:15-09:30, Paper ThAT11.4 | |
Neuroprotective Effects of Electrical Stimulation Following Ischemic Stroke in Non-Human Primates |
|
Zhou, Jasmine | University of Washington |
Khateeb, Karam | University of Washington |
Gala, Aryaman | University of Washington |
Rahimi, Mona | University of Washington |
Griggs, Devon | University of Washington |
Ip, Zachary | University of Washington |
Yazdan-Shahmorad, Azadeh | University of Washington |
Keywords: Neurological disorders - Stroke, Neural stimulation, Neural signal processing
Abstract: Brain stimulation has emerged as a novel therapy for ischemic stroke, a major cause of brain injury that often results in lifelong disability. Although past works in rodents have demonstrated protective effects of stimulation following stroke, few of these results have been replicated in humans due to the anatomical differences between rodent and human brains and a limited understanding of stimulation-induced network changes. Therefore, we combined electrophysiology and histology to study the neuroprotective mechanisms of electrical stimulation following cortical ischemic stroke in non-human primates. To produce controlled focal lesions, we used the photothrombotic method to induce targeted vasculature damage in the sensorimotor cortices of two macaques while collecting electrocorticography (ECoG) signals bilaterally. In another two monkeys, we followed the same lesioning procedures and applied repeated electrical stimulation via an ECoG electrode adjacent to the lesion. We studied the protective effects of stimulation on neural dynamics using ECoG signal power and coherence. In addition, we performed histological analysis to evaluate the differences in lesion volume. In comparison to controls, the ECoG signals showed decreased gamma power across the sensorimotor cortex in stimulated animals. Meanwhile, Nissl staining revealed smaller lesion volumes for the stimulated group, suggesting that electrical stimulation may exert neuroprotection by suppressing post-ischemic neural activity. With the similarity between NHP and human brains, this study paves the path for developing effective stimulation-based therapy for acute stroke in clinical studies.
|
|
09:30-09:45, Paper ThAT11.5 | |
Investigation of Neural Electrode Fabrication Process on Polycarbonate Substrate |
|
Lee, Joowon | Seoul National University |
Jeong, Hyunbeen | Seoul National University |
Kim, Ji sung | Seoul National University |
Seo, Jong Mo | Seoul National University, School of Engineering |
Keywords: Neural stimulation, Neural interfaces - Implantable systems
Abstract: Polycarbonate is a polymer that has been widely used including medical application due to its useful properties. It has high temperature resistance, biocompatibility, transparency and low water absorption rate, which are needful characteristics for packaging material of implantable neural prosthetic devices. In this study, we investigated fabrication of neural electrode with polycarbonate film using standard photolithography process and heated hydraulic press for thermal lamination. First, oxygen plasma surface treatment was performed to increase the adhesion between metal and polycarbonate film. Then thin layer of titanium and gold layer were deposited. Metal layer is patterned through standard photolithography techniques. After completing the metal patterning, thermal lamination was performed with site opened polycarbonate film.
|
|
09:45-10:00, Paper ThAT11.6 | |
Difference in Network Effects of Pulsatile and Galvanic Stimulation |
|
Adkisson, Paul | Johns Hopkins University School of Medicine |
Fridman, Gene | Johns Hopkins University |
Steinhardt, Cynthia | Johns Hopkins University |
Keywords: Neural interfaces - Implantable systems, Neural stimulation, Brain physiology and modeling - Neural dynamics and computation
Abstract: Biphasic pulsatile stimulation is the present standard for neural prosthetic use, and it is used to understand connectivity and functionality of the brain in brain mapping studies. While pulses have been shown to drive behavioral changes, such as biasing decision making, they have deficits. For example, cochlear implants restore hearing but lack the ability to restore pitch perception. Recent work shows that pulses produce artificial synchrony in networks of neurons and non-linear changes in firing rate with pulse amplitude. Studies also show galvanic stimulation, delivery of current for extended periods of time, produces more naturalistic behavioral responses than pulses. In this paper, we use a winner-take-all decision-making network model to investigate differences between pulsatile and galvanic stimulation at the single neuron and network level while accurately modeling the effects of pulses on neurons for the first time. Results show pulses bias spike timing and make neurons more resistive to natural network inputs than galvanic stimulation at an equivalent current amplitude.
|
|
ThAT12 |
M1 |
Theme 06. ECoG & LFP & Single Neuron AP Processing |
Oral Session |
Chair: Chiappalone, Michela | Istituto Italiano Di Tecnologia |
Co-Chair: Ranta, Radu | CRAN UMR 7039, Université De Lorraine/ CNRS |
|
08:30-08:45, Paper ThAT12.1 | |
Towards Naturalistic Speech Decoding from Intracranial Brain Data |
|
Berezutskaya, Julia | Donders Institute for Brain, Cognition and Behaviour, Radboud Un |
Ambrogioni, Luca | Donders Institute for Brain, Cognition and Behaviour |
Ramsey, Nick | University Medical Center Utrecht |
van Gerven, Marcel | Radboud University Nijmegen |
Keywords: Brain-computer/machine interface, Neural signals - Machine learning & Classification, Human performance - Speech
Abstract: Speech decoding from brain activity can enable development of brain-computer interfaces (BCIs) to restore naturalistic communication in paralyzed patients. Previous work has focused on development of decoding models from isolated speech data with a clean background and multiple repetitions of the material. In this study, we describe a novel approach to speech decoding that relies on a generative adversarial neural network (GAN) to reconstruct speech from brain data recorded during a naturalistic speech listening task (watching a movie). We compared the GAN-based approach, where reconstruction was done from the compressed latent representation of sound decoded from the brain, with several baseline models that reconstructed sound spectrogram directly. We show that the novel approach provides more accurate reconstructions compared to the baselines. These results underscore the potential of GAN models for speech decoding in naturalistic noisy environments and further advancing of BCIs for naturalistic communication.
|
|
08:45-09:00, Paper ThAT12.2 | |
An Immersive Virtual Reality Platform Integrating Human ECOG & sEEG: Implementation & Noise Analysis |
|
Paschall, Courtnie | University of Washington Seattle |
Rao, Rajesh PN | University of Washington |
Hauptmann, Jason | Seattle Children's Hospital |
Ojemann, Jeffrey G | University of Washington |
Herron, Jeffrey | University of Washington |
Keywords: Neural signal processing, Brain-computer/machine interface, Neural interfaces - Implantable systems
Abstract: Virtual reality (VR) offers a robust platform for human behavioral neuroscience, granting unprecedented experimental control over every aspect of an immersive and interactive visual environment. VR experiments have already integrated non-invasive neural recording modalities such as EEG and functional MRI to explore the neural correlates of human behavior and cognition. Integration with implanted electrodes would enable significant increase in spatial and temporal resolution of recorded neural signals and the option of direct brain stimulation for neurofeedback. In this paper, we discuss the first such implementation of a VR platform with implanted electrocorticography (ECoG) and stereo-electroencephalography (sEEG) electrodes in human, in-patient subjects. Noise analyses were performed to evaluate the effect of the VR headset on neural data collected in two VR-naïve subjects, one child and one adult, including both ECOG and sEEG electrodes. Results demonstrate an increase in line noise power (57-63Hz) while wearing the VR headset that is mitigated effectively by common average referencing (CAR), and no significant change in the noise floor bandpower (125-240Hz). To our knowledge, this study represents first demonstrations of VR immersion during invasive neural recording with in-patient human subjects.
|
|
09:00-09:15, Paper ThAT12.3 | |
Large-Scale Multimodal Neural Recordings on a High-Density Neurochip: Olfactory Bulb and Hippocampal Networks |
|
Emery, Brett Addison | German Center for Neurodegenerative Diseases (DZNE) |
Hu, Xin | German Center for Neurodegenerative Diseases (DZNE) |
Maugeri, Lorenzo | German Center for Neurodegenerative Diseases (DZNE) |
Khanzada, Shahrukh | German Center for Neurodegenerative Diseases (DZNE) |
Klütsch, Diana | German Center for Neurodegenerative Diseases (DZNE) |
Altuntac, Erdem | German Center for Neurodegenerative Diseases (DZNE) |
Amin, Hayder | German Center for Neurodegenerative Diseases (DZNE) |
Keywords: Neural interfaces - Microelectrode technology, Neural interfaces - Tissue-electrode interface, Brain physiology and modeling - Neural circuits
Abstract: A striking example of the brain’s complexity and continued plasticity is the addition of new neuronal components to a circuit in a process called neurogenesis. Two brain regions exhibit profound circuit remodeling through this process – the olfactory bulb and hippocampus. However, how local network changes in both regions influence global circuit rewiring and dynamic network features remain largely unexplored due to the lack of spatiotemporal resolution technology and large-scale electrophysiological activity recordings. Here, we demonstrate large-scale recordings using a high-density neurochip to reveal multimodal circuit-wide electrophysiological properties and layer-specific functional connectivity in the olfactory bulb and hippocampal networks. Our findings illustrate simultaneous recordings from the entire network, which allows us to quantify synchronous electrophysiological parameter differences and layer-specific waveform markers. Examining pairwise cross-covariance between active electrode pairs reveals individual neuronal ensemble contributions to synchronous activation between layers and hub microcircuits, demonstrating network-wide rewiring. Our study suggests a novel tool to address the computational implications of large-scale activity patterns in functional multimodal neurogenic circuits.
|
|
09:15-09:30, Paper ThAT12.4 | |
Robot Assisted Neurosurgery for High-Accuracy, Minimally-Invasive Deep Brain Electrophysiology in Monkeys |
|
Ho, Jonathan | University of Pittsburgh |
Liang, Lucy | University of Pittsburgh |
Grigsby, Erinn | University of Pittsburgh |
Balaguer, Josep-Maria | University of Pittsburgh |
Karapetyan, Vahagan | University of Pittsburgh |
Schaeffer, David | University of Pittsburgh |
Silva, Afonso | NINDS, NIH |
Hitchens, T. Kevin | Carnegie Mellon University |
Capogrosso, Marco | University of Pittsburgh |
Gerszten, Peter | University of Pittsburgh |
Gonzalez-Martinez, Jorge | Cleveland Clinic |
Pirondini, Elvira | University of Pittsburgh |
Keywords: Neural stimulation - Deep brain, Motor learning, neural control, and neuromuscular systems, Brain physiology and modeling - Sensory-motor
Abstract: Traditional methods to access subcortical structures involve the use of anatomical atlases and high precision stereotaxic frames but suffer from significant variations in implantation accuracy. Here, we leveraged the use of the ROSA One(R) Robot Assistance Platform in non-human primates to study electrophysiological interactions of the corticospinal tract with spinal cord circuits. We were able to target and stimulate the corticospinal tract within the internal capsule with high accuracy and efficiency while recording spinal local field potentials and multi-unit spikes. Our method can be extended to any subcortical structure and allows implantation of multiple deep brain stimulation probes at the same time.
|
|
09:30-09:45, Paper ThAT12.5 | |
On the Localization of Oscillatory Sources from (S)EEG Recordings |
|
Hernandez-Castanon, Viviana del Rocio | University of Lorraine, CRAN |
Le Cam, Steven | Université De Lorraine |
Ranta, Radu | CRAN UMR 7039, Université De Lorraine/ CNRS |
Keywords: Brain functional imaging - Source localization, Brain functional imaging - EEG
Abstract: Electrophysiological brain source localization consists in estimating the source positions and activities responsible for the (S)EEG measurements. The localization procedure is usually carried out in the time domain, however in specific situations the activities of interest can be located at well defined frequencies, e.g. in response to a rhythmic stimulation. This paper addresses the problem of sparse localization of multiple sources oscillating at the same frequency. In particular the non-unicity of the solution is emphasized, as alternative source maps involving equivalent or less number of sources can be found, challenging source localization methods based on sparsity. These limitations are illustrated under a realistic SEEG simulation framework, and the usefulness to perform localization for this modality is strengthen out.
|
|
09:45-10:00, Paper ThAT12.6 | |
Reward-Dependent Graded Suppression of Sensorimotor Beta-Band Local Field Potentials During an Arm Reaching Task in NHP |
|
Yadav, Taruna | University of Houston |
Magana Tellez, Oman | University of Houston |
Francis, Joseph Thachil | University of Houston |
Keywords: Brain-computer/machine interface, Brain physiology and modeling - Sensory-motor, Neuromuscular systems - EMG processing and applications
Abstract: A better understanding of reward signaling in the sensorimotor cortices can aid in developing Reinforcement Learning-based Brain-Computer Interfaces (RLBCI) for restoration of movement functions with fewer implants. Brain-computer interfaces (BCIs) using local field potentials (LFPs) have recently achieved performance comparable to spike-BCIs [1]. With superior stability over time, LFPs may be the preferred signal for BCIs. We show that sensorimotor LFPs can provide reward level information (R1 – R3) like spikes[2]. We used a cued reward-level reaching task in which reward information was temporally dissociated from movement information. This allowed the study of reward- and movement-related modulations in LFPs. We recorded simultaneously from contralateral primary -somatosensory (S1), -motor (M1), and the dorsal premotor (PMd) cortices in a female Macaca Mulatta. We found that all three cortices’ average beta band (14-30 Hz) amplitude showed robust modulation with reward levels during the cue presentation period. Such modulation was consistently observed after controlling for cue color, differences in behavioral variables, and electromyogram (EMG) activity. Statistical amplitude analysis showed that reward level could be extracted from the simple LFP feature of beta band amplitude, even before a reaching target appeared, and no specific reach plan could be developed.
|
|
ThBT2 |
Alsh-2 |
Theme 07. Physiological and Biological Sensing 3 |
Oral Session |
Chair: Godfrey, Alan | Northumbria University |
Co-Chair: Cheng, Leo K | The University of Auckland |
|
10:30-10:45, Paper ThBT2.1 | |
Characterization of Dry-Contact EEG Electrodes and an Empirical Comparison of Ag/AgCl and IrO2 Electrodes |
|
Kappel, Simon Lind | Aarhus University |
Kidmose, Preben | Aarhus University, Denmark |
Keywords: Bio-electric sensors - Sensing methods, Physiological monitoring - Instrumentation, Bio-electric sensors - Sensor systems
Abstract: Dry-contact electrodes are increasingly being used for EEG recordings in both research studies and consumer products. They are more user-friendly and better suited for long-term recordings. However, dry-contact electrodes also bring challenges with respect to the stability and impedance of the electrode-skin interface. We propose a methodology to characterize and compare dry-contact electrodes. The characterization is based on measuring the electrode-skin impedance spectrum, fit a parametric model of the electrode-skin interface to the measured spectrum, and calculate the resulting thermal noise spectrum. Thereby it is possible to relate the noise of an EEG recording to the theoretical noise contribution from the electrode-skin interface. To demonstrate the methodology, we performed an empirical study comparing two types of dry-contact electrodes in an ear-EEG setup. The electrodes were IrO 2, previously used for ear-EEG, and a new design based on Ag/AgCl. Here, we related the noise floor of an auditory steady-state response (ASSR) to the thermal noise spectrum of the electrode-skin interface. The study showed similar impedance and EEG recording quality for the two electrode types, and the thermal noise of the electrode-skin interface was below the noise floor of the EEG recordings for both electrode types.
|
|
10:45-11:00, Paper ThBT2.2 | |
Evaluation of a Wearable System for Fetal ECG Monitoring Using Cooperative Sensors |
|
Braun, Fabian | CSEM SA |
Bonnier, Guillaume | CSEM SA |
Rapin, Michael | Swiss Center for Electronics and Microtechnology, CSEM |
Yilmaz, Gurkan | CSEM SA |
Proust, Yara-Maria | CSEM SA |
Schneider, Sophie | Inselspital |
Radan, Anda-Petronela | Inselspital |
Strahm, Karin Maya | Inselspital |
Surbek, Daniel | Inselspital |
Lemay, Mathieu | CSEM |
Delgado-Gonzalo, Ricard | CSEM |
Keywords: Bio-electric sensors - Sensor systems, Physiological monitoring - Instrumentation, Health monitoring applications
Abstract: Fetal electrocardiography (fECG) has gotten widespread interest in the last years as technology for fetal monitoring. Compared to cardiotocography (CTG), the current state of the art, it can be designed in smaller formfactor and is thus suited for long-term and unsupervised monitoring. In the present study we evaluated a wearable system which is based on CSEM’s cooperative sensors, a versatile technology that allows for the measurement of multiple biosignals and an easy integration into a garment or patch. The system was tested on 25 patients with singleton pregnancies and an age of gestation ≥ 37 weeks. To reject unreliable fetal heart rate (fHR) estimations, the signal processing algorithm provides a signal quality index. In 12 out of 21 patients available for analysis, a good performance of fHR estimations was obtained with a mean absolute error < 5 bpm and an acceptance rate >70%. However, the remaining 9 patients showed low acceptance rates and high errors. Besides investigating the source of these high errors, future work includes the investigating improved signal processing algorithms, different body positions and the use of dry electrodes.
|
|
11:00-11:15, Paper ThBT2.3 | |
Self Applied Ear-EEG for Sleep Monitoring at Home |
|
Mikkelsen, Kaare | University of Aarhus |
Tabar, Yousef Rezaei | Middle East Technical University |
Toft, Hans Olaf | Widex A/S |
Hemmsen, Martin Christian | T&W Engineering |
Rank, Mike Lind | Widex A/S |
Kidmose, Preben | Aarhus University, Denmark |
Keywords: Wearable sensor systems - User centered design and applications, Physiological monitoring - Novel methods
Abstract: High quality sleep monitoring is done using EEG electrodes placed on the skin. This has traditionally required assistance by an expert when the equipment needed to mounted. However, this creates a limitation in how cheap and easy it can be to record sleep in the subject's own home. Here we present a data set of 120 home recordings of sleep, in which subjects use self-applied ear-EEG monitoring equipment. We compare this data set to a previously recorded data set with both ear-EEG and polysomnography, which was applied by an expert. Clinical relevance: On all tested metrics, self applied sleep recordings behaved the same as expert applied. This indicates that ear-EEG can reliably be used as a home sleep monitor, even when subjects apply the equipment themselves.
|
|
11:15-11:30, Paper ThBT2.4 | |
A Wireless System for EEG Acquisition and Processing in an Earbud Form Factor with 600 Hours Battery Lifetime |
|
Guermandi, Marco | University of Bologna |
Cossettini, Andrea | ETH Zurich |
Benatti, Simone | University of Bologna |
Benini, Luca | University of Bologna |
Keywords: Wearable low power, wireless sensing methods, Bio-electric sensors - Sensor systems, IoT sensors for health monitoring
Abstract: In recent years, in-ear electroencephalography(EEG) was demonstrated to record signals of similar quality compared to standard scalp-based EEG, and clinical applications of objective hearing threshold estimations have been reported. Existing devices, however, still lack important features. In fact, most of the available solutions are based on wet electrodes, require to be connected to external acquisition platforms, or do not offer on-board processing capabilities. Here we overcome all these limitations, presenting an ear- EEG system based on dry electrodes that includes all the acquisition, processing, and connectivity electronics directly in the ear bud. The earpiece is equipped with an ultra-low power analog front-end for analog-to-digital conversion, a low-power MEMS microphone, a low-power inertial measurement unit,and an ARM Cortex-M4 based microcontroller enabling on- board processing and Bluetooth Low Energy connectivity. The system can stream raw EEG data or perform data processing directly in-ear. We test the device by analysing its capability to detect brain response to external auditory stimuli, achieving 4 and 1.3 mW power consumption for data streaming or on board processing, respectively. The latter allows for 600 hours operation on a PR44 zinc-air battery. To the best of our knowledge, this is the first wireless and fully self-contained ear-EEG system performing on-board processing, all embedded in a single earbud.
|
|
11:30-11:45, Paper ThBT2.5 | |
Spatial Dependency of the PPG Morphology at Right Carotid Common Artery |
|
Bonnet, Stéphane | CEA Léti MINATEC |
LUBIN, Mathilde | CEA Léti MINATEC |
Doron, Maeva | Univ. Grenoble Alpes, CEA, LETI |
BLANQUER, Guillaume | CEA |
PERRIOLLAT, MATHIEU | CEA |
PRADA MEJIA, Robinson | Univ. Grenoble Alpes, CEA, LETI, F-38000 Grenoble |
Blandin, Pierre | Univ. Grenoble Alpes, CEA, LETI |
Gerbelot, Rémi | CEA, LETI, MINATEC Campus |
Keywords: Physiological monitoring - Instrumentation, Optical and photonic sensors and systems, Physiological monitoring - Modeling and analysis
Abstract: PhotoPlethysmoGraphy (PPG) is ubiquitously employed in wearable devices for health monitoring. Photodiode signal inversion is observed in rare occasions, most of the time when the sensor is pressed against the skin. We report in this article such observations made at the right common carotid artery site. Indeed we have systematically observed a photodiode signal inversion when the PPG sensor is placed where the pulse is the best felt at the carotid. In addition to be inverted, the pulse is steeper during the systolic phase. Such inversion has implications in terms of pulse arrival time (PAT) measurements In our experiments, this causes a difference of 20 ms in the carotid PAT when measured at the absolute maximum slope. The mechanical and optical properties of tissues must be better accounted to explain the PPG signal morphology. Clinical Relevance— Understanding the role of mechanical tissue properties seems relevant in order to obtain more reproducible results in PPG signal analysis.
|
|
11:45-12:00, Paper ThBT2.6 | |
Comparison of Stress Detection through ECG and PPG Signals Using a Random Forest-Based Algorithm |
|
Benchekroun, Mouna | Université De Technologie De Compiègne |
Chevallier, Baptiste | UTC Centre Innovation BMBI UMR 7338 |
Beaouiss, hamza | Université De Technologie De Compiègne |
Istrate, Dan | UTC |
Zalc, Vincent | UTC |
Khalil, Mohamad | Lebanese University, Doctoral School for Sciences Andtechnology, |
Lenne, Dominique | UTC - Heudiasyc |
Keywords: Wearable wireless sensors, motes and systems, Physiological monitoring - Modeling and analysis, Health monitoring applications
Abstract: Stress is has been classified as the health epidemic of the 21st century with an increasingly active research interest within the fields of psychology, neuroscience, medicine, and more recently affective computing. At present, stress is identified through cortisol levels in saliva but there is no unanimously accepted standard for continuous stress evaluation. With recent development in wearable sensors, many scientist are interested in stress identification through physiological signals such as the Heart rate variability (HRV). In this paper, we present a novel supervised machine learning-based algorithm to detect stress from HRV derived from both electrocardiograms (ECG) and photoplethysmograms (PPG). HRV features from ECG and PPG signals of 46 healthy subjects were analysed and used to separately train and test a Random Forest algorithm. In both datasets, stress was accurately identified with more than 80% F1-score and 90% AUC. Results show that PPG is a good surrogate to ECG for HRV analysis and stress detection. The proposed algorithm has the potential to assist researchers and clinicians in the automated continuous analysis of stress.
|
|
ThBT3 |
Boisdale-1 |
Theme 01. Machine Learning and Deep Learning for Electrophysiological Data
Analysis |
Oral Session |
Chair: Abasolo, Daniel | University of Surrey |
Co-Chair: Dauwels, Justin | NTU |
|
10:30-10:45, Paper ThBT3.1 | |
Exploiting Multiple EEG Data Domains with Adversarial Learning |
|
Bethge, David | Dr. Ing. H.c. F. Porsche AG, LMU Munich |
Hallgarten, Philipp | Porsche, University of Tübingen |
Ozdenizci, Ozan | Graz University of Technology |
Mikut, Ralf | Karlsruhe Institute of Technology |
Albrecht, Schmidt | LMU Munich |
Grosse-Puppendahl, Tobias | Dr. Ing. H.c. F. Porsche AG |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Data mining and big data methods - Inter-subject variability and personalized approaches, Physiological systems modeling - Multivariate signal processing
Abstract: Electroencephalography (EEG) is shown to be a valuable data source for evaluating subjects' mental states. However, the interpretation of multi-modal EEG signals is challenging, as they suffer from poor signal-to-noise-ratio, are highly subject-dependent, and are bound to the equipment and experimental setup used, (i.e. domain). This leads to machine learning models often suffer from poor generalization ability, where they perform significantly worse on real-world data than on the exploited training data. Recent research heavily focuses on cross-subject and cross-session transfer learning frameworks to reduce domain calibration efforts for EEG signals. We argue that multi-source learning via learning domain-invariant representations from multiple data-sources is a viable alternative, as the available data from different EEG data-source domains (e.g., subjects, sessions, experimental setups) grow massively. We propose an adversarial inference approach to learn data-source invariant representations in this context, enabling multi-source learning for EEG-based brain-computer interfaces. We unify EEG recordings from different source domains (i.e., emotion recognition datasets SEED, SEED-IV, DEAP, DREAMER), and demonstrate the feasibility of our invariant representation learning approach in suppressing data-source-relevant information leakage by 35% while still achieving stable EEG-based emotion classification performance.
|
|
10:45-11:00, Paper ThBT3.2 | |
AutoTransfer: Subject Transfer Learning with Censored Representations on Biosignals Data |
|
Smedemark-Margulies, Niklas | Northeastern University |
Wang, Ye | Mitsubishi Electric Research Laboratories (MERL) |
Koike-Akino, Toshiaki | Mitsubishi Electric Research Laboratories (MERL) |
Erdogmus, Deniz | Northeastern University |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Signal pattern classification
Abstract: We provide a regularization framework for subject transfer learning in which we train an encoder and classifier to minimize classification loss, subject to a penalty measuring independence between the latent representation and the subject label. We introduce three notions of independence and corresponding penalty terms using mutual information or divergence as a proxy for independence. For each penalty term, we provide several concrete estimation algorithms, using analytic methods as well as neural critic functions. We provide a hands-off strategy for applying this diverse family of regularization algorithms to a new dataset, which we call ``AutoTransfer". We evaluate the performance of these individual regularization strategies and our AutoTransfer method on EEG, EMG, and ECoG datasets, showing that these approaches can improve subject transfer learning for challenging real-world datasets.
|
|
11:00-11:15, Paper ThBT3.3 | |
Spiking Neural Networks Diagnosis of ADHD Subtypes through EEG Signals Evaluation |
|
Pedrollo, Guilherme | UFRGS |
Franco, Alexandre Rosa | Pontifícia Universidade Católica Do Rio Grande Do Sul |
Bagesteiro, Leia B | San Francisco State University |
Balbinot, Alexandre | Federal University of Rio Grande Do Sul (UFRGS) |
Keywords: Data mining and big data methods - Machine learning and deep learning methods, Data mining and big data methods - Pattern recognition, Signal pattern classification
Abstract: Attention-deficit hyperactivity disorder (ADHD) affects at least 5% of the world population and can disturb normal development causing serious issues in adulthood. Therefore, it is important to develop tools to help detecting ADHD so that treatment can start as soon as possible. Plus, the differentiation of ADHD in its subtypes is important to define the recommended treatment. Here we present original research to investigate the hypothesis of using a Spiking Neural Networks (SNN) EEG signals classifier for automated diagnostic of ADHD subtypes. This research used data from 243 patients and healthy volunteers acquired as part of the Healthy Brain Network. These resting state EEG signals were collected from 5-minutes scan with a 128 channel 500 Hz system. For benchmarking, we present a comparison of the SNN performance with a support vector machine, a k-nearest neighborhood, a random forest algorithm and a multi-layer perceptron. We present experiments for both the diagnostics of ADHD and for detecting which ADHD subtype the patient has. SNN presented a 72.00% accuracy for detecting ADHD surpassing all the other techniques by 9.1% and 68% in detecting if the subject is a member of the Combined ADHD, Inattentive ADHD or control groups (18% better than the second-best technique).
|
|
11:15-11:30, Paper ThBT3.4 | |
A Saliency Based Feature Fusion Model for EEG Emotion Estimation |
|
Delvigne, Victor | ISIA Lab, Faculty of Engineering, University of Mons/IMT Nord Eu |
Facchini, Antoine | IMT Nord Europe, CRIStAL UMR CNRS 9189 |
Wannous, Hazem | IMT Nord Europe |
Dutoit, Thierry | Faculté Polytechnique De Mons |
Ris, Laurence | Neuroscience Lab, Faculty of Medecine and Pharmacy, University O |
Jean-Philippe, Vandeborre | IMT Nord Europe, CRIStAL UMR CNRS 9189 |
Keywords: Data mining and big data methods - Machine learning and deep learning methods, Data mining and big data methods - Biosignal classification, Time-frequency and time-scale analysis - Time-frequency analysis
Abstract: Among the different modalities to assess emotion, electroencephalogram (EEG), representing the electrical brain activity, achieved motivating results over the last decade. Emotion estimation from EEG could help in the diagnosis or rehabilitation of certain diseases. In this paper, we propose a dual model considering two different representations of EEG feature maps: 1) a sequential based representation of EEG band power, 2) an image-based representation of the feature vectors. We also propose an innovative method to combine the information based on a saliency analysis of the image-based model to promote joint learning of both model parts. The model has been evaluated on four publicly available datasets: SEED-IV, SEED, DEAP and MPED. The achieved results outperform results from state-of-the-art approaches for three of the proposed datasets with a lower standard deviation that reflects higher stability. For sake of reproducibility, the codes and models proposed in this paper are available at https://github.com/VDelv/Emotion-EEG.
|
|
11:30-11:45, Paper ThBT3.5 | |
A Novel Deep Learning Approach Using AlexNet for the Classification of Electroencephalograms in Alzheimer’s Disease and Mild Cognitive Impairment |
|
Drage, Rachel | Centre for Biomedical Engineering, School of Mechanical Engineer |
Escudero, Javier | University of Edinburgh |
Parra, Mario | University of Strathclyde |
Scally, Brian | Institute of Psychological Sciences, University of Leeds |
Anghinah, Renato | Reference Center of Behavioral Distur Bances and Dementia, Scho |
de Araújo, Amanda Vitória Lacerda | Traumatic Brain Injury Cognitive Rehabilitation Out-Patient Cent |
Basile, Luis F | Division of Neurosurgery, University of São Paulo, São Paulo |
Abasolo, Daniel | University of Surrey |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Nonlinear dynamic analysis - Biomedical signals
Abstract: Alzheimer’s Disease (AD) is the most common form of dementia. Mild Cognitive Impairment (MCI) is the term given to the stage describing prodromal AD and represents a ‘risk factor’ in early-stage AD diagnosis from normal cognitive decline due to ageing. The electroencephalogram (EEG) has been studied extensively for AD characterization, but reliable early-stage diagnosis continues to present a challenge. The aim of this study was to introduce a novel way of classifying between AD patients, MCI subjects, and age-matched healthy control (HC) subjects using EEG-derived feature images and deep learning techniques. The EEG recordings of 141 age-matched subjects (52 AD, 37 MCI, 52 HC) were converted into 2D greyscale images representing the Pearson correlation coefficients and the distance Lempel-Ziv Complexity (dLZC) between the 21 EEG channels. Each feature type was computed from EEG epochs of 1s, 2s, 5s and 10s segmented from the original recording. The CNN architecture AlexNet was modified and employed for this three-way classification task and a 70/30 split was used for training and validation with each of the different epoch lengths and EEG-derived images. Whilst a maximum classification accuracy of 73.49% was obtained using dLZC-derived images from 10s epochs as input to the model, the classification accuracy reached 98.13% using the images obtained from Pearson correlation coefficients and 5s epochs.
|
|
11:45-12:00, Paper ThBT3.6 | |
Diagnosis of Alzheimer's Disease and Mild Cognitive Impairment Using EEG and Recurrent Neural Networks |
|
Gkenios, Georgios | International Hellenic University |
Latsiou, Konstantina | International Hellenic University |
Diamantaras, Konstantinos | International Hellenic University |
Chouvarda, Ioanna | Aristotle University |
Tsolaki, Magda | Aristotle University of Thessaloniki |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Signal pattern classification
Abstract: Alzheimer's disease (AD) is the main cause of dementia and Mild cognitive impairment (MCI) is a prodromal stage of AD whose early detection is considered crucial as it can contribute in slowing the progression of AD. In our study we attempted to classify a subject into AD, MCI, or Healthy Control (HC) groups with the use of electroencephalogram (EEG) data. Due to the time-series nature of EEG we experimented with the powerful recurrent neural network (RNN) classifiers and more specifically with models including basic or bidirectional Long Short-Term Memory (LSTM) modules. The EEG signals from 17 channels were preprocessed using a 0.1-32 Hz band-pass filter and then segmented into 2-second epochs during which, the subject had closed eyes. Finally, on each segment Fast Fourier Transform (FFT) was applied. To evaluate our models we studied four different classification problems: problem 1: separating subject into three classes (HC, MCI, AD) and problems 2-4: pairwise classifications AD vs. MCI, AD vs. HC and MCI vs. HC. For each problem we employed two different cross-validation approaches (a) by segment and (b) by patient. In the first one, segments from a subject EEG may exist in both training and validations set, while in the second one, all the EEG segments of a subject can only exist in either the training or the validation set. In the AD-MCI-HC classification we achieved an accuracy of 99% by segment cross-validation, which was an improvement to earlier studies that utilized recurrent neural network models. In the pairwise classification problems we achieved over 90% accuracy by segment and over 80% by subject.
|
|
ThBT4 |
Boisdale-2 |
Theme 01. Signal Processing and Classification of Muscle and Motion Signals |
Oral Session |
Chair: Porta, Alberto | Universita' Degli Studi Di Milano |
|
10:30-10:45, Paper ThBT4.1 | |
Sequential Learning on sEMGs in Short and Long-Term Situations Via Self-Training Semi-Supervised Support Vector Machine |
|
Okawa, Yuto | Rikkyo University |
Kanoga, Suguru | National Institute of Advanced Industrial Science and Technology |
Hoshino, Takayuki | Keio University |
Nitta, Tohru | Rikkyo University |
Keywords: Data mining and big data methods - Inter-subject variability and personalized approaches, Data mining and big data methods - Pattern recognition, Signal pattern classification
Abstract: The purpose of this study it to assess the effect of sequential learning of self-training support vector machine (ST-S3VM) on short- and long-term surface electromyogram (sEMG) datasets. A machine learning-based supervised classifier is enabling stable, complex, and high-performance motion control. Unlabeled sEMG measurements are easy by the development of wearable sensing technology. Thus, semi-supervised learning methods are attracted attention to utilize unlabeled sEMG data for supervised classifier with a small amount of labeled data. To evaluate robustness of ST-S3VM in realistic conditions, two public datasets which respectively contain a short- and long-term dataset were used. We compared the performance of ST-S3VM with four-kinds of SVM classifiers. In both short- and long-term situations, ST combined classifiers (ST-SVM and ST-S3VM) showed higher performances than the methods without ST (SVM and S3VM). In some cases, ST-S3VM had the best performance, but in other cases, ST-SVM had better performance than ST-S3VM. In order to make better use of unlabeled data, we will develop ST-S3VM to reduce the impact of harmful unlabeled data.
|
|
10:45-11:00, Paper ThBT4.2 | |
An Exploration of the Optimal Feature-Classifier Combinations for Transradial Prosthesis Control |
|
Douglas, Fraser | University of British Columbia |
Gover, Harry | University of Strathclyde |
Docherty, Cheryl | University of Strathclyde |
Shields, Gordon | University of Strathclyde |
Leventi, Konstantina | University of Strathclyde |
Di Caterina, Gaetano | University of Strathclyde |
Keywords: Signal pattern classification
Abstract: Within state-of-the-art gesture-based upper-limb myoelectric prosthesis control, gesture recognition commonly relies on the classification of features extracted from electromyographic (EMG) data gathered from the amputee’s residual forearm musculature. Despite best efforts in broadly maximizing gesture recognition accuracy, there does not yet exist a feature-classifier combination accepted as best-practice. In turn, this work hypothesizes that no single feature-classifier combination can consistently maximize accuracy across subjects, positing instead that control schemes should be personalized to the individual. To investigate this hypothesis, the study employed the 40-subject, 49-gesture Ninapro Database 2 (DB2) to compare the performance of 7 different historic, more recent, and state-of-the-art feature sets when classified by 5 machine learning algorithms commonly seen within EMG-based pattern recognition literature. The results demonstrate the ability of Linear Discriminant Analysis (LDA) to marginally exceed other more computationally intensive classifiers in terms of mean accuracy, while the feature set which maximized the highest proportion of individuals’ accuracies was shown to vary with both classifier choice and gesture count.
|
|
11:00-11:15, Paper ThBT4.3 | |
Improved Classification Accuracy of Hand Movements Using Softmax Classifier and Kalman Filter |
|
Al-Maliki, Abdullah | University of Arkansas-Little Rock |
Iqbal, Kamran | University of Arkansas at Little Rock |
|
|
11:15-11:30, Paper ThBT4.4 | |
Dyskinesia Estimation of Imbalanced Data Using a Deep-Learning Model |
|
Hssayeni, Murtadha | Florida Atlantic University |
Jimenez-Shahed, Joohi | Icahn School of Medicine at Mount Sinai, New York City, NY |
Ghoraani, Behnaz | Florida Atlantic University |
Keywords: Data mining and big data methods - Machine learning and deep learning methods, Neural networks and support vector machines in biosignal processing and classification, Signal pattern classification
Abstract: The collection of Parkinson's Disease (PD) time-series data usually results in imbalanced and incomplete datasets due to the geometric distribution of PD complications' severity scores. Consequently, when training deep convolutional models on these datasets, the models suffer from overfitting and lack generalizability to unseen data. In this paper, we investigated a new framework of Conditional Generative Adversarial Networks (cGANs) as a solution to improve the extrapolation and generalizability of the regression models in such datasets. We used a real-world PD dataset to estimate Dyskinesia severity in patients with PD. The developed cGAN demonstrated significantly better generalizability to unseen data samples than a traditional Convolutional Neural Network with an improvement of 34%. This solution can be applied in similar imbalanced time-series data, especially in the healthcare domain, where balanced and uniformly distributed data samples are not readily available.
|
|
11:30-11:45, Paper ThBT4.5 | |
Human Activity Recognition in Parkinson's Disease Using Deep Models Trained on Healthy Population Motion Data |
|
Davidashvilly, Shelly | Florida Atlantic University |
Hssayeni, Murtadha | Florida Atlantic University |
Chi, Christopher | Florida Atlantic University |
Jimenez-Shahed, Joohi | Icahn School of Medicine at Mount Sinai, New York City, NY |
Ghoraani, Behnaz | Florida Atlantic University |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Signal pattern classification, Data mining and big data methods - Machine learning and deep learning methods
Abstract: Physical activity recognition in patients with Parkinson’s Disease (PwPD) is challenging due to the lack of large-enough and good quality motion data for PwPD. A common approach to this obstacle involves the use of models trained on better quality data from healthy patients. Models can struggle to generalize across these domains due to motor complications affecting the movement patterns in PwPD and differences in sensor axes orientations between data. In this paper, we investigated the generalizability of a deep convolutional neural network (CNN) model trained on a young, healthy population to PD, and the role of data augmentation on alleviating sensor position variability. We used two publicly available healthy datasets - PAMAP2 and MHEALTH. Both datasets had sensor placements on the chest, wrist, and ankle with 9 and 10 subjects, respectively. A private PD dataset was utilized as well. The proposed CNN model was trained on PAMAP2 in k-fold cross-validation based on the number of subjects, with and without data augmentation, and tested directly on MHEALTH and PD data. Without data augmentation, the trained model resulted in 48.16% accuracy on MHEALTH and 0% on the PD data when directly applied with no model adaptation techniques. With data augmentation, the accuracies improved to 87.43% and 44.78%, respectively, indicating that the method compensated for the potential sensor placement variations between data.
|
|
11:45-12:00, Paper ThBT4.6 | |
Dynamical Synergies in Multidigit Hand Prehension |
|
Pei, Dingyi | University of Maryland Baltimore County |
Sathishkumar Olikkal, Parthan | University of Maryland Baltimore County |
Adali, Tulay | University of Maryland Baltimore County |
Vinjamuri, Ramana | University of Maryland Baltimore County |
Keywords: Principal component analysis
Abstract: Hand prehension requires a highly coordinated control of contact forces. The high dimensional sensorimotor system of the human hand although operates at ease, poses several challenges when replicated for prosthetic control. This study investigates how the dynamical synergies, coordinated spatial patterns of contact forces, contribute to the contact forces in a grasp, and whether the dynamical synergies could potentially serve as candidates for feedforward and feedback mechanisms. Ten right-handed subjects were recruited to grasp and hold mass-varied objects. The contact forces during this multidigit prehension were recorded using an instrumented grip glove. The dynamical synergies were derived using principal component analysis (PCA). The contact force patterns during the grasps were reconstructed using the first few synergies. The significance of the dynamical synergies and the current challenges and possible applications of the dynamical synergies were discussed along with the integration of the dynamical synergies into prosthetics and exoskeletons that can possibly enable near-natural control.
|
|
ThBT5 |
Carron -1 |
Theme 10. Imaging Informatics |
Oral Session |
Co-Chair: Xue, Zhiyun | National Library of Medicine |
|
10:30-10:45, Paper ThBT5.1 | |
A Coarse-To-Fine Pathology Patch Selection for Improving Gene Mutation Prediction in Acute Myeloid Leukemia |
|
Chiu, Chun-Chia | National Tsing Hua University, Hsinchu, Taiwan |
Li, Jeng-Lin | National Tsing Hua University |
Wang, Yu-Fen | Tai-Cheng Stem Cell Therapy Center, National Taiwan University |
Ko, Bor-Sheng | Department of Internal Medicine, National Taiwan University Hosp |
Lee, Chi-Chun | National Tsing Hua University |
Keywords: General and theoretical informatics - Machine learning, General and theoretical informatics - Predictive analytics, Imaging Informatics - Image analysis, processing and classification
Abstract: Identifying gene mutation is essential to prognosis and therapeutic decisions for acute myeloid leukemia (AML) but the current gene analysis is inefficient and non-scalable. Pathological images are readily accessible and can be effectively modeled using deep learning. This work aims at predicting gene mutation directly by modeling bone marrow smear images. Traditionally, bone marrow smear slides are cropped into patches with manual segmentation for patch-level modeling. Slide-level modeling, such as multi-instance learning, could aggregate patches for holistic modeling, though suffer from excessive redundancy. In this study, we propose a discriminative multi-instance approach to select useful patches in a coarse-to-fine process. Specifically, we preprocess a slide into patches by using a trained pre-selector network. Then, we rule out low quality patches in the coarse selection with known prior knowledge, and refine the model using gene-discriminative patches in the fine selection. We evaluate the framework for CEBPA, FLT3, and NPM1 gene mutation prediction and obtain 71.67%, 56.26%, and 56.34% F1-score. Further analysis show the effect of different selection criteria on prediction gene mutations using pathological images.
|
|
10:45-11:00, Paper ThBT5.2 | |
Deep Learning Classification with ResNet50 Using DCGAN for Data Augmentation of Imbalanced Breast Cancer Dataset (withdrawn from program) |
|
Islam, A.K.M. Kamrul | Georgia State University |
|
11:00-11:15, Paper ThBT5.3 | |
A Deep Multi-Label Segmentation Network for Eosinophilic Esophagitis Whole Slide Biopsy Diagnostics |
|
Daniel, Nati | Department of Physiology, Biophysics and System Biology, Faculty |
Larey, Ariel | INTEL |
Aknin, Eliel | Technion - Israel Institute of Technology |
Osswald, Garrett A. | Division of Allergy and Immunology, Cincinnati Children's Hospit |
Caldwell, Julie M. | Division of Allergy and Immunology, Cincinnati Children's Hospit |
Rochman, Mark | Division of Allergy and Immunology, Cincinnati Children's Hospit |
Collins, Margaret H. | Department of Pathology, Cincinnati Children's Hospital Medical |
Yang, Guang-Yu | Department of Pathology, Ann & Robert H. Lurie Children's Hospit |
Arva, Nicoleta C. | Department of Pathology, Ann & Robert H. Lurie Children's Hospit |
Capocelli, Kelley E. | Department of Pathology, Children’s Hospital Colorado |
Rothenberg, Marc E. | Division of Allergy and Immunology, Cincinnati Children's Hospit |
Savir, Yonatan | Technion |
Keywords: Imaging Informatics - Computational pathology, Imaging Informatics - Biomedical imaging marker extraction, Imaging Informatics - Image analysis, processing and classification
Abstract: Eosinophilic esophagitis (EoE) is an allergic inflammatory condition of the esophagus associated with elevated numbers of eosinophils. Disease diagnosis and monitoring require determining the concentration of eosinophils in esophageal biopsies, a time-consuming, tedious and somewhat subjective task currently performed by pathologists. Here, we developed a machine learning pipeline to identify, quantitate and diagnose EoE patients' at the whole slide image level. We propose a platform that combines multi-label segmentation deep network decision support system with dynamics convolution that is able to process whole biopsy slide. Our network is able to segment both intact and not-intact eosinophils with a mean intersection over union (mIoU) of 0.93. This segmentation enables the local quantification of intact eosinophils with a mean absolute error of 0.611 eosinophils. We examined a cohort of 1066 whole slide images from 400 patients derived from multiple institutions. Using this set, our model achieved a global accuracy of 94.75%, sensitivity of 94.13%, and specificity of 95.25% in reporting EoE disease activity. Our work provides state-of-the-art performances on the largest EoE cohort to date, and successfully addresses two of the main challenges in EoE diagnostics and digital pathology, the need to detect several types of small features simultaneously, and the ability to analyze whole slides efficiently. Our results pave the way for an automated diagnosis of EoE and can be utilized for other conditions with similar challenges.
|
|
11:15-11:30, Paper ThBT5.4 | |
Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening |
|
Xue, Zhiyun | National Library of Medicine |
Yu, Kelly | National Cancer Institute |
Pearlman, Paul | National Cancer Institute |
Pal, Anabik | Indian Statistical Institute |
Chen, Tseng- Cheng | National Taiwan University Hospital, Taipei |
Hua, Chun-Hung | China Medical University Hospital, Taichung |
Kang, Chung Jan | Chang Gung Memorial Hospital, Linkou |
Chien, Chih-Yen | Chang Gung Memorial Hospital, Kaohsiung |
Tsai, Ming-Hsui | China Medical University Hospital, Taichung |
Wang, Cheng-Ping | National Taiwan University Hospital, Taipei |
Chaturvedi, Anil | National Cancer Institute |
Antani, Sameer | National Library of Medicine |
Keywords: Imaging Informatics - Image analysis, processing and classification, Health Informatics - Computer-aided decision making, Imaging Informatics - Biomedical imaging marker extraction
Abstract: Intelligent computer-aided algorithms analyzing photographs of various mouth regions can help in reducing the high subjectivity in human assessment of oral lesions. Very often, in the images, a ruler is placed near a suspected lesion to indicate its location and as a physical size reference. In this paper, we compared two deep-learning networks: ResNeSt and ViT, to automatically identify ruler images. Even though the ImageNet 1K dataset contains a “ruler” class label, the pre-trained models showed low sensitivity. After fine-tuning with our data, the two networks achieved high performance on our test set as well as a hold-out test set from a different provider. Heatmaps generated using three saliency methods: GradCam and XRAI for ResNeSt model, and Attention Rollout for ViT model, demonstrate the effectiveness of our technique.
|
|
11:30-11:45, Paper ThBT5.5 | |
Stacked Ensemble Network to Assess the Structural Variations in Retina: A Bio-Marker for Early Disease Diagnosis |
|
Khan, Muhammad Zubair | University of Missouri-Kansas City |
Lee, Yugyung | University of Missouri Kansas City |
Keywords: Imaging Informatics - Image registration, segmentation, and compression, Bioinformatics - Bioinformatics for health monitoring, Health Informatics - Informatics for chronic disease management
Abstract: The retina is a unique tissue that extends the human brain in transmitting the incoming light into neural spikes. Researchers collaborating with domain experts proposed numerous deep networks to extract vessels from the retina; however, these techniques have the least response for micro-vessels. The proposed method has developed a stacked ensemble network approach with deep neural architectures for precise vessel extraction. Our method has used bi-directional LSTM for filling gaps in dis-joint vessels and applied W-Net for boundary refinement and emphasizing local regions to achieve better results for micro-vessels extraction. The platform has combined the strength of various networks to improve the automated screening process and has shown promising results on benchmark datasets.
|
|
11:45-12:00, Paper ThBT5.6 | |
Decrypting the Information Captured by MRI-Radiomic Features in Predicting the Response to Neoadjuvant Chemotherapy in Breast Cancer |
|
Saint Martin, Marie-Judith | Institut Curie/Université Paris-Saclay |
Frouin, Frederique | Inserm - Institut Curie |
Malhaire, Caroline | Institut Curie |
ORLHAC, FANNY | Institut Curie, Inserm |
Keywords: Imaging Informatics - Radiomics, General and theoretical informatics - Machine learning
Abstract: MRI-based radiomic models have shown promises in predicting the response to neoadjuvant chemotherapy in breast cancer. However, it is difficult to determine which information from the images contributes the most to the prediction: the distribution of gray-levels, the tumour heterogeneity, the shape of the lesions or the intensities of peritumoural regions. The purpose of this study is to dissociate the different sources of information to improve prediction results. Based on pre-treatment MR images from 103 patients, four types of 3D Volumes Of Interest were defined and arranged in multiple combinations. Combining features extracted from different regions proved to increase prediction performances.
|
|
ThBT6 |
Carron-2 |
Theme 10. Sensor Informatics - eHealth and MHealth |
Oral Session |
Chair: Charlton, Peter | University of Cambridge |
Co-Chair: Semiz, Beren | Koc University |
|
10:30-10:45, Paper ThBT6.1 | |
A New Motor and Cognitive Dual-Task Approach Based on Foot Tapping for the Identification of Mild Cognitive Impairment |
|
Mancioppi, Gianmaria | Scuola Superiore Sant'Anna |
Fiorini, Laura | University of Florence |
Rovini, Erika | University of Florence |
Zeghari, Radia | University of Cote D'Azur |
Gros, Auriane | Université Nice Sophia Antipolis |
Manera, Valeria | Université Nice Sophia Antipolis |
Robert, Philippe | Universitè Nice Sophia Antipolis |
Cavallo, Filippo | University of Florence |
Keywords: Health Informatics - Decision support methods and systems, General and theoretical informatics - Statistical data analysis
Abstract: This study investigates the adoption of innovative Motor and Cognitive Dual-Task (MCDT) based on the combination of increasing motor and cognitive tasks to discern between subjects with Mild Cognitive Impairment (MCI) and Cognitively Normal Adults (CNA). We aim to adopt new MCDT protocols and to compare their performance against the gold standard (a walking based MCDT, called GAIT). 27 older adults have been assessed through a customized wearable system during 4 MCDTs. We developed as many pooled indices (PIs), based on MCDTs perfomance, demographic data, and clinical scores. We use these parameters as regressors in 4 different logistic regression models. The regression models that encompassed features from innovative MCDT overcame the gold standard classification performance. In particular, models based on the heel tapping and the alternate heel-toe tapping reach the best outputs, namely +8% of accuracy if compared to the gold standard (a walking task). The use of logistic regression models based on MCDT PI have been effective in discerning between CNA textit{vs} MCI. Our results suggest that the gold standard MCDT may represents a too demanding exercise to highlight differences between CNA and MCI. It seems that MCDT based on an intermediate level of motor difficulty could represent the sweet spot for the identification of MCI against CNA.
|
|
10:45-11:00, Paper ThBT6.2 | |
Stress Detection from Surface Electromyography Using Convolutional Neural Networks |
|
Robles, Diego | Universidad De Valparaíso, Valparaíso |
Benchekroun, Mouna | Université De Technologie De Compiègne |
Zalc, Vincent | UTC |
Istrate, Dan | UTC |
Taramasco, Carla | Universidad De Valparaíso, Valparaíso |
Keywords: Health Informatics - eHealth, Health Informatics - Disease profiling and personalized treatment, General and theoretical informatics - Deep learning and big data to knowledge
Abstract: The study of stress and its implications has been the focus of interest in various fields of science. Many automated/semi-automated stress detection systems based on physiological markers have been gaining enormous popularity and importance in recent years. Such non voluntary physiological features exhibit unique characteristics in terms of reliability, accuracy. Combined with machine learning techniques, they offer a great field of study of stress identification and modelling. In this study, we explore the use of Convolutional Neural Networks (CNN) for stress detection through surface electromyography signals (sEMG) of the trapezius muscle. One of the main advantages of this model is the use of the sEMG signal without computed features contrary to classical machine learning algorithms. The proposed model achieved good results with 73% f1-score for a multi-class classification and 82% in a bi-class classification.
|
|
11:00-11:15, Paper ThBT6.3 | |
Prioritising Electrocardiograms for Manual Review to Improve the Efficiency of Atrial Fibrillation Screening |
|
Adeniji, Mary | University of Cambridge |
Brimicombe, J | University of Cambridge |
Cowie, Martin | Royal Brompton Hospital (Guy’s and St Thomas’ NHS Foundation Tru |
Dymond, Andrew | University of Cambridge |
Clair Linden, Hannah | Zenicor Medical Systems AB |
Lip, Gregory | University of Liverpool |
Mant, Jonathan | University of Cambridge |
Pandiaraja, Madhumitha | University of Cambridge |
Williams, Kate | University of Cambridge |
Charlton, Peter | University of Cambridge |
Keywords: Health Informatics - eHealth, Public Health Informatics - Public health management solutions, Health Informatics - Computer-aided decision making
Abstract: Screening for atrial fibrillation (AF) could reduce the incidence of stroke by identifying undiagnosed AF and prompting anticoagulation. However, screening may involve recording many electrocardiograms (ECGs) from each participant, several of which require manual review which is costly and time-consuming. The aim of this study was to investigate whether the number of ECG reviews could be reduced by using a model to prioritise ECGs for review, whilst still accurately diagnosing AF. A multiple logistic regression model was created to estimate the likelihood of an ECG exhibiting AF based on the mean RR-interval and variability in RR-intervals. It was trained on 1,428 manually labelled ECGs from 144 AF screening programme participants, and evaluated using 11,443 ECGs from 1,521 participants. When using the model to order ECGs for review, the number of reviews for AF participants was reduced by 74% since no further reviews are required after an AF ECG is identified; however, it did not impact the number of reviews in non-AF participants (the vast majority of participants), so the overall number of reviews was reduced by 3% with no missed AF diagnoses. When using the model to also exclude ECGs from review, the overall number of reviews was reduced by 28% with no missed AF diagnoses, and by 53% with only 4% of AF diagnoses missed. In conclusion, the workload can be reduced by using a model to prioritise ECGs for review. Ordering ECGs alone only provides only a moderate reduction in workload. The additional use of a threshold to exclude ECGs from review provides a much greater reduction in workload at the expense of some missed AF diagnoses.
|
|
11:15-11:30, Paper ThBT6.4 | |
Remote Photoplethysmography and Heart Rate Estimation by Dynamic Region of Interest Tracking |
|
Wei, Wenchuan | Samsung Research America |
Vatanparvar, Korosh | Samsung Research America |
Zhu, Li | Samsung Research America |
Kuang, Jilong | Samsung Research America |
Gao, Alex | Samsung Research America |
Keywords: Health Informatics - Patient tracking, Imaging Informatics - Image analysis, processing and classification, General and theoretical informatics - Algorithms
Abstract: Remote photoplethysmography (PPG) estimates vital signs by measuring changes in the reflected light from the human skin. Compared to traditional PPG techniques, remote PPG enables contactless measurement at a reduced cost. In this paper, we propose a novel method to extract remote PPG signals and heart rate from videos. We propose an algorithm to dynamically track regions of interest (ROIs) and combine the signals from all ROIs based on signal qualities. To maintain a stable frame rate and accuracy, we propose a dynamic down- sampling approach, which makes our system robust to the different video resolutions and user-camera distances. We also propose the strategy of adaptive measurement time to estimate HR, which can achieve comparable accuracy in HR estimation while reducing the average measurement time. To test the accuracy of the proposed system, we have collected data from 30 subjects with facial masks. Experimental results show that the proposed system can achieve 3.0bpm mean absolute error in HR estimation.
|
|
11:30-11:45, Paper ThBT6.5 | |
Improving Respiratory Timing Estimation Using Quality Indexing and Electrocardiogram-Derived Respiration |
|
Gazi, Asim | Georgia Institute of Technology |
Jung, Hewon | Georgia Institute of Technology |
Kimball, Jacob | Georgia Institute of Technology |
Inan, Omer | Georgia Institute of Technology |
Keywords: Sensor Informatics - Multi-sensor data fusion, General and theoretical informatics - Data quality control, Sensor Informatics - Physiological monitoring
Abstract: Numerous applications require accurate estimation of respiratory timings. Respiratory effort (RSP) measurement is a popular approach to accomplish this, especially when the tightness of the sensing belt around the chest can be ensured. In less controlled settings, however, belt looseness and artifacts from movement of the belt on the chest can corrupt the signal. This paper demonstrates that respiration quality indexing and outlier removal can help mitigate these issues, improving estimates of respiration rate (RR), inspiration time (Ti), and expiration time (Te). In a sample of 15 healthy human participants undergoing a protocol of five controlled breathing exercises in four postures each, electrocardiogram (ECG) and RSP signals were collected. RSP signals were processed to extract breath-by-breath estimates of RR, Ti, and Te. These estimates were compared against ground truth spirometry-based estimates using Bland-Altman analysis. We find that incorporating quality indexing and outlier removal prior to feature extraction improves the 95% limits of agreement by 10-40%. We also find that by using ECG-derived respiration (EDR) during periods of RSP artifact, the data removal necessary for accurate respiratory timing estimation is significantly reduced (P < 0.05 for all postures). These findings encourage the use of quality assessment and EDR to enhance the robustness of RR, Ti, and Te estimation from RSP signals. Clinical Relevance— Detecting stimulus-induced or pathological changes in respiratory function can enhance our understanding and monitoring of respiratory health. Quality assessment and the use of EDR help accomplish this by enabling more accurate measurement of respiratory timings.
|
|
11:45-12:00, Paper ThBT6.6 | |
More to Less (M2L): Enhanced Health Recognition in the Wild with Reduced Modality of Wearable Sensors |
|
Yang, Huiyuan | Rice University |
Yu, Han | Rice University |
Sridhar, Kusha | Rice University |
Vaessen, Thomas | Katholieke Universiteit Leuven |
Myin-Germeys, Inez | KU Leuven |
Sano, Akane | Rice University |
Keywords: Sensor Informatics - Multi-sensor data fusion, Bioinformatics - Bioinformatics for health monitoring, Sensor Informatics - Sensor-based mHealth applications
Abstract: Abstract— Accurately recognizing health-related conditions from wearable data is crucial for improved healthcare outcomes. To improve the recognition accuracy, various approaches have focused on how to effectively fuse information from multiple sensors. Fusing multiple sensors is a common scenario in many applications, but may not always be feasible in real-world scenarios. For example, although combining bio- signals from multiple sensors (i.e., a chest pad sensor and a wrist wearable sensor) has been proved effective for improved performance, wearing multiple devices might be impractical in the free-living context. To solve the challenges, we propose an effective more to less (M2L) learning framework to improve testing performance with reduced sensors through leveraging the complementary information of multiple modalities during training. More specifically, different sensors may carry different but complementary information, and our model is designed to enforce collaborations among different modalities, where positive knowledge transfer is encouraged and negative knowledge transfer is suppressed, so that better representation is learned for individual modalities. Our experimental results show that our framework achieves comparable performance when compared with the full modalities. Our code and results will be available at https://github.com/comp-well-org/More2Less.git.
|
|
ThBT8 |
Dochart-2 |
Theme 05. Respiratory Signal Processing |
Oral Session |
Chair: Romero, Daniel | Institute for Bioengineering of Catalonia |
Co-Chair: Leonhardt, Steffen | RWTH Aachen University |
|
10:30-10:45, Paper ThBT8.1 | |
The Effect of Walking on the Estimation of Breathing Pattern Parameters Using Wearable Bioimpedance |
|
Blanco-Almazán, Dolores | Institute for Bioengineering of Catalonia |
Groenendaal, Willemijn | Imec Netherlands |
Catthoor, Francky | IMEC |
Jané, Raimon | Institut De Bioenginyeria De Catalunya (IBEC) |
Keywords: Cardiovascular, respiratory, and sleep devices - Wearables
Abstract: Wearable bioimpedance is a technique proposed to estimate breathing parameters such as respiratory rate (RR). However, its potential application lies in clinical investigation of daily-life activities like walking. This study evaluated the effect of the walking interference on the estimation of breathing parameters. 50 chronic obstructive pulmonary disease patients performed static and active measurements during thoracic bioimpedance acquisition. The static measurements included respiratory airflow for reference. The active measurements were used to estimate the walking interference from bioimpedance, and the obtained signals were added to static measurements for comparison with the reference. Afterward, we applied four different preprocessing methods to remove this walking interference and the resulting signals were used to detect the respiratory cycles and estimate breathing parameters (inspiratory time, expiratory time, duty cycle, and RR). The methods performed differently in terms of accuracy and mean average percentage error (MAPE), showing the need for specific preprocessing for active measurements. Furthermore, the MAPE values in the RR estimation were close to 3 % indicating that breathing parameters can be accurately estimated during walking. Accordingly, the present study reinforces the applicability of wearable bioimpedance for respiratory monitoring.
|
|
10:45-11:00, Paper ThBT8.2 | |
A Computational Cardiopulmonary Physiology Simulator Accurately Predicts Individual Patient Responses to Changes in Mechanical Ventilator Settings |
|
Mistry, Sonal | University of Warwick |
Brook, Bindi | University of Nottingham |
Saffaran, Sina | The University of Warwick |
Chikhani, Marc | University of Nottingham |
Hannon, David | National University of Ireland, Galway |
Laffey, John | National University of Ireland, Galway |
Scott, Timothy | Academic Department of Military Anaesthesia and Critical Care, R |
Camporota, Luigi | Department of Critical Care Medicine, Guy's and St Thomas' NHS F |
Hardman, Jonathan G. | University of Nottingham |
Bates, Declan Gerard | University of Warwick |
Keywords: Pulmonary and critical care - Bioengineering applications in Intensive care, Pulmonary and critical care - Pulmonary disease, Cardiovascular and respiratory system modeling - Gas exchange models
Abstract: We present new results validating the capability of a high-fidelity computational simulator to accurately predict the responses of individual patients with acute respiratory distress syndrome to changes in mechanical ventilator settings. 26 pairs of data-points comprising arterial blood gasses collected before and after changes in inspiratory pressure, PEEP, FiO2, and I:E ratio from six mechanically ventilated patients were used for this study. Parallelized global optimization algorithms running on a high-performance computing cluster were used to match the simulator to each initial data point. Mean absolute percentage errors between the simulator predicted values of PaO2 and PaCO2 and the patient data after changing ventilator parameters were 10.3% and 12.6%, respectively. Decreasing the complexity of the simulator by reducing the number of independent alveolar compartments reduced the accuracy of its predictions.
|
|
11:00-11:15, Paper ThBT8.3 | |
Why Reduced Inspiratory Pressure Could Determine Success of Non-Invasive Ventilation in Acute Hypoxic Respiratory Failure |
|
Weaver, Liam | University of Warwick |
Saffaran, Sina | The University of Warwick |
Chikhani, Marc | University of Nottingham |
Laffey, John | National University of Ireland, Galway |
Scott, Timothy | Academic Department of Military Anaesthesia and Critical Care, R |
Camporota, Luigi | Department of Critical Care Medicine, Guy's and St Thomas' NHS F |
Hardman, Jonathan G. | University of Nottingham |
Bates, Declan Gerard | University of Warwick |
Keywords: Pulmonary and critical care - Ventilatory Assist Devices, Pulmonary and critical care - Bioengineering applications in Intensive care, Respiratory transport, mechanics and control - Periodic breathing
Abstract: The magnitude of inspiratory effort relief within the first 2 hours of non-invasive ventilation for hypoxic respiratory failure was shown in a recent exploratory clinical study to be an early and accurate predictor of outcome at 24 hours. We simulated the application of non-invasive ventilation to three patients whose physiological and clinical characteristics match the data in that study. Reductions in inspiratory effort corresponding to reductions of esophageal pressure swing greater than 10 cmH2O more than halved the values of total lung stress, driving pressure, power and transpulmonary pressure swing. In the absence of significant reductions in inspiratory pressure, multiple indicators of lung injury increased after application of non-invasive ventilation.
|
|
11:15-11:30, Paper ThBT8.4 | |
Development of a Pleural Pressure Catheter Via Continuous Fiberoptic Esophageal Pressure Measurements |
|
Lundstrom, Julie A. | Rush River Research Corp |
Khemani, Robinder | University of Southern California, Children’s Hospital Los Angel |
Hotz, Justin | Department of Anesthesiology and Critical Care Medicine, Childre |
Newth, Christopher John Lester | Children's Hospital Los Angeles, University of Southern Californ |
Achanta, Satyanarayana | Duke University School of Medicine |
Gentile, Michael | Duke University |
Hedin, Daniel | Advanced Medical Electronics |
Keywords: Pulmonary and critical care - Pulmonary function testing & instrumentation, Cardiovascular, respiratory, and sleep devices - Sensors, Cardiovascular, respiratory, and sleep devices - Monitors
Abstract: There is growing research showing the importance of measuring esophageal pressure as a surrogate for pleural pressure for patients on mechanical ventilators. The most common measurement method uses a balloon catheter whose accuracy can vary based on patient anatomy, balloon position, balloon inflation, and the presence of other tubes in the esophagus. The authors present the development and initial testing results of a new combination catheter, utilizing fiberoptic pressure sensing to provide more accurate esophageal pressure measurements, and allows for the incorporation of a feeding tube and temperature sensor.
|
|
11:30-11:45, Paper ThBT8.5 | |
Detecting Obstructive Apnea Episodes Using Dynamic Bayesian Networks and ECG-Based Time-Series |
|
Romero, Daniel | Institute for Bioengineering of Catalonia |
Jané, Raimon | Institut De Bioenginyeria De Catalunya (IBEC) |
Keywords: Cardiovascular and respiratory signal processing - Cardiovascular signal processing
Abstract: In this study, we proposed an automatic detector for obstructive apnea episodes using only ECG-based time-series from a single-ECG channel. Several obstructive apnea episodes were provoked for different separated sequences of 15 minutes in anesthetized Sprague-Dawley rats. In this recurrent obstructive sleep apnea (OSA) model, each episode lasted 15 s, while the number of total events per sequence was randomly selected. The beat-to-beat interval (RR) and the R-wave amplitude (Ra) time-series were extracted and pre-processed for each sequence and used to train Dynamic Bayesian Networks (DBN) with different lags. An optimal trade-off between the lag (L) and RMSE values was considered to select the best model to be used when detecting apnea episodes. The selected models were then used to estimate the occurrence probability of apnea episodes, p(At), by using a filtering approach. Finally, the time series of the estimated probabilities were post-processed using non-overlapped 15-s epochs, to determine whether they are classified as apneic or non-apneic segments. Results showed that those lagged models with orders greater than 5, presented suitable RMSE values and become more sensitive as the order increased. A detection threshold of 0.2 seems to provide the best apnea detection performance overall, with Acc=0.81, Se=0.83, and Sp=0.79, using two ECG parameters and L = 10. Clinical relevance— Dynamic Bayesian Networks represent a powerful tool to develop personalized models for apnea detection and diagnosis in OSA patients.
|
|
11:45-12:00, Paper ThBT8.6 | |
Standalone Electrical Impedance Tomography Predicts Spirometry Indicators and Enables Regional Lung Assessment |
|
Zouari, Fedi | Gense Technologies Limited |
Oon, Wei Yi | The University of Hong Kong |
Modak, Dipyaman | Gense Technologies Ltd |
Kwok, Wang Chun | Queen Mary Hospital, Hong Kong |
Cao, Peng | The University of Hong Kong |
Lee, Wei-Ning | The University of Hong Kong |
Tam, Terence Chi Chun | The University of Hong Kong (HKU) |
Wong, Eddie C. | Gense Technologies Ltd |
Chan, Russell | NYU School of Medicine |
Keywords: Pulmonary and critical care - Pulmonary function testing & instrumentation, Cardiovascular and respiratory signal processing - Time-frequency, time-scale analysis of respiratory variability
Abstract: Electrical impedance tomography (EIT) is a bio-medical imaging modality that has several clinical applications namely for human lungs. Yet, its relationship with gold standard lung diagnostic tools including spirometry is not available. In this study, simultaneous EIT and spirometry measurements were collected for 14 healthy subjects who performed forced breathing paradigms of different efforts simulating a wide range of spirometry indicators. It is demonstrated that EIT can predict standard spirometry indicators over a wide dynamic range, with a potential sensitivity and specificity of 98% and 100%, respectively, in detecting obstructive patterns. It is also shown that EIT can provide a regional mapping of the spirometry indicator which are shown to be consistent with their corresponding global indicators. Overall, EIT can predict spirometry indicators and can assess regional lung health through parametric mapping.
|
|
ThBT9 |
Gala |
Theme 11. Biomedical Engineering Education |
Oral Session |
Chair: van Oostrom, Johannes | University of Florida |
Co-Chair: Hradetzky, David | University of Applied Sciences and Arts Northwestern Switzerland |
|
10:30-10:45, Paper ThBT9.1 | |
Implementation of Health Technology Assessment and Management Course in Undergraduate Program in Biomedical Engineering ITB |
|
Setiawan, Agung Wahyu | School of Electrical Engineering and Informatics, Institut Tekno |
Wicaksono, Albertus A. | PT. Sari Mitra Medika |
Keywords: Teaching design, Novel approaches to BME education, Career development in BME
Abstract: The Undergraduate Program in Biomedical Engineering ITB, Indonesia, introduce the Health Technology Assessment and Management as an elective course in 2021. This course is implemented to support the World Health Assembly that urges the member states to establish national strategies in health technology assessment and management, particularly medical devices. Furthermore, it is designed to give biomedical engineering students a broader insight into their career opportunities. Therefore, this course is delivered by the practitioner and guided by the main lecturer. The course syllabus is developed from the WHO Medical Devices Technical Series and European Network for Health Technology Assessment. It tries to implement HTA Core Model for Rapid Relative Effectiveness Assessments. A questionnaire is used to measure the students' perception of the course implementation. Moreover, it is used to obtain the students' comments and feedback. The course that is delivered by the practitioner not only gives the course content but also the context. After attending the course, students have a broader insight into the career opportunities as biomedical engineers in Indonesia.
|
|
10:45-11:00, Paper ThBT9.2 | |
Development and Testing of a Prototype of a Dental Extraction Trainer with Real-Time Feedback on Forces, Torques, and Angular Velocity |
|
Beuling, Maaike Geertruida | Amsterdam University Medical Center |
van Riet, Tom Cornelis Theodorus | Academic Medical Center, University of Amsterdam |
van Frankenhuyzen, Jan | Technical University Delft |
van Antwerpen, Reinier | Technical University Delft |
de Blocq van Scheltinga, Bas | Delft University of Technology |
Dourleijn, Arnout Harm Hendrik | Delft University of Technology |
Ireiz, Dzan | Delft University of Technology |
Streefkerk, Sander | Delft University of Technology |
van Zanten, Jonathan C. | Delft University of Technology |
de Lange, Jan | Academic Medical Center, University of Amsterdam |
Kober, Jens | Delft University of Technology |
Dodou, Dimitra | Delft University of Technology |
Keywords: Teaching design, Instruction and learning, Novel approaches to BME education
Abstract: The need for a training modality for tooth extraction procedures is increasing, as dental students do not feel properly trained. In this study, a prototype of a training setup is designed, in which extraction procedures can be performed on jaw models and cadaveric jaws. The prototype was designed in a way that it can give real-time feedback on the applied forces in all three dimensions (buccal/lingual, mesial/distal, and apical/coronal), torques, and angular velocity. To evaluate the prototype, a series of experimental extractions on epoxy models, conserved jaws, and fresh frozen jaws were performed. Extraction duration (s), angular velocity (degrees/s), average force (N), average torque (Nm), linear impulse (Ns), and angular impulse (Nms) were shown in real-time to the user and used to evaluate the prototype. In total, 342 (92.9%) successful extractions were performed using the prototype (n= 113 epoxy factory-made, n=187 epoxy re-used, n=17 conserved, n=25 fresh frozen). No significant differences were found between the conserved and the fresh frozen jaws. The fresh frozen extraction duration, linear impulse, and angular impulse differed significantly from the corresponding values obtained for the epoxy models. Extractions were successfully performed, and the applied forces, torques, and angular velocity were recorded and shown as real-time feedback using the prototype of the dental extraction trainer. The feedback of the prototype is considered reliable.
|
|
11:00-11:15, Paper ThBT9.3 | |
Experience with a Continuous Education Program for Clinical, Regulatory, and Quality Affairs in Northwestern Switzerland |
|
Hradetzky, David | University of Applied Sciences and Arts Northwestern Switzerland |
Etter, Philippe | Medidee Services SA |
Lucano, Elena | University of Rome "Sapienza", |
Keywords: Career development in BME, Novel approaches to BME education, Instruction and learning
Abstract: The European Medical Device and In-Vitro Diagnostic Medical Device industry faces currently a highly challenging situation, as applied regulations changed throughout the last year significantly. To cope with this situation a novel continuous education program for employees from these sectors, aiming to provide knowledge and hands-on experience in clinical, regulatory, and quality affairs. Since 2020 two classes were successfully completed at the University of Applied Sciences and Arts Northwestern Switzerland. Within this paper the concept and content are described, the participants population highlighted, and the benefit for the participant and their employer elaborated.
|
|
11:15-11:30, Paper ThBT9.4 | |
A General Education Course in Medical Devices Innovation at Zhejiang University |
|
Chen, Wanlin | Zhejiang University |
Zheng, Jing | Zhejiang University |
Qi, Wei | Zhejiang Univwersity |
Wu, Yuxuan | University of Glasgow |
Chen, Hang | Zhejiang University |
Keywords: Biomedical engineering curricula, Teaching design, BME undergraduate research
Abstract: Innovation and development in medical devices are of great significance for overcoming the problems such as the increasing costs of healthcare and the widening societal inequity in medical technologies. This paper presents the design and outcomes of a general education course in medical devices innovation offered for an eight-week quarter each year since Spring 2018 at Zhejiang University. The course consists of two modules, lectures and team project, both of which are well designed based on the entire innovation process spanning needs finding, concept generation, prototyping, and strategy development. A professional teaching team with eight experts from various disciplines and institutes has been established as well. Since its inception, 296 students from 34 majors have participated and 71 original projects have been proposed. The results of self-assessment questionnaires showed that the course had equipped students with broader fundamentals and specialized knowledge, and stronger skills in innovation and teamwork, which provide a solid foundation for students' future innovation practice.
|
|
11:30-11:45, Paper ThBT9.5 | |
The PLH - Purpose Launchpad Health - Meta-Methodology to Explore Problems and Evaluate Solutions for Biomedical Engineering Impact Creation |
|
Friebe, Michael | Otto-Von-Guericke-University |
Fritzsche, Holger | Otto-Von-Guericke-University |
Morbach, Oliver | ProQIT |
Heryan, Katarzyna | AGH University of Science and Technology |
Keywords: Novel approaches to BME education, BME and global health, Instruction and learning
Abstract: Abstract— Healthcare Innovation ideas originating from biomedical engineering departments are rarely based on a deep understanding of a problem, but are often based on coming up with an engineering solution that does not meet an Unmet Clinical Need, is too complicated, bulky, costly, and does not consider global developments. For an impactful innovation design it is essential however to properly understand the clinical issues, forward project the effect of exponential technologies and other global developments. Health and healthcare are in need of disruptive ideas for preventive, predictive, personalised solutions that engage the individuals to pave the way towards real healthcare. We have adapted a novel meta-methodology for dedicated use with health related applications and have used it validating start-up ideas and also during a semester long lecture/seminar classroom setup with amazing results. Clinical Relevance— This novel health dedicated meta-methodology is dependent on interdisciplinary team and innovation work and heavily relies on a good understanding of the current clinical processes and needs as well as on a future projection of global health delivery developments. The clinical perspective is essential and meaning- and impactful innovation can only be developed validating desirability feasibility, and viability, which needs clinical-, engineering/technical-, as well as economic expertise.
|
|
ThBT10 |
Forth |
Theme 12. Personalized Healthcare |
Oral Session |
Chair: Menolotto, Matteo | Tyndall National Institute |
Co-Chair: Dutta, Anirban | University at Buffalo SUNY |
|
10:30-10:45, Paper ThBT10.1 | |
ATTENTIV: Instrumented Peripheral Catheter for the Detection of Catheter Dislodgement in IV Infiltration |
|
Bo, Jessica Y. | ETH Zurich |
Ta, Kevin | ETH Zurich |
Nishida, Rio | University of British Columbia |
Yeh, Gordon | University of British Columbia |
Tsang, Vivian W. L. | University of British Columbia |
Bolton, Megan | University of British Columbia |
Ranger, Manon | University of British Columbia |
Walus, Konrad | University of British Columbia |
Keywords: Point of care - Detection and monitoring, Medical technology - Entrepreneurship and commercialization, Medical technology - Innovation
Abstract: Intravenous (IV) infiltration is a common problem associated with IV infusion therapy in clinical practice. A multitude of factors can cause the leakage of IV fluids into the surrounding tissues, resulting in symptoms ranging from temporary swelling to permanent tissue damage. Severe infiltration outcomes can be avoided or minimized if the patient’s care provider is alerted of the infiltration at its earliest onset. However, there is a lack of real-time, continuous infiltration monitoring solutions, especially those suited for clinical use for critically ill patients. Our design of the sensor-integrated ATTENTIV catheter allows direct detection of catheter dislodgement, a root cause of IV infiltration. We verify two detection methods: blood-tissue differentiation with a support vector machine and signal peak identification with a thresholding algorithm. We present promising preliminary testing results on biological and phantom models that utilize bioimpedance as the sensing modality.
|
|
10:45-11:00, Paper ThBT10.2 | |
An MR-Conditional Needle Driver for Robot-Assisted Spinal Injections: Design Modifications and Evaluations |
|
Wang, Yanzhou | Johns Hopkins University |
Liu, Guanyun | Johns Hopkins University |
Li, Gang | Children's National Medical Center |
Cleary, Kevin | Children's National Medical Center |
Iordachita, Iulian | Johns Hopkins University |
Keywords: Medical technology - Product development process, Medical technology - Design and development, Medical technology - Innovation
Abstract: This paper introduces design modifications to our MR-Conditional, 2-degree-of-freedom (DOF), remotely- actuated needle driver for MRI-guided spinal injections. The new needle driver should better meet cleaning and sterilization guidelines needed for regulatory approval, preserve the sterile field during intraoperative needle attachment, and offer better ergonomics and intuitiveness when handling the device. Dynamic and static force and torque required to properly install the needle driver onto our 4-DOF robot base are analyzed, which provide insight into the risks of intraoperative tool attachment in the setting of robot-assisted spinal injections under MRI guidance.
|
|
11:00-11:15, Paper ThBT10.3 | |
A Toggling Resistant In-Pedicle Expandable Anchor: A Preliminary Study |
|
de Kater, Esther | TU Delft |
Weststeijn, Cornel | TU Delft |
Sakes, Aimée | Delft University of Technology |
Breedveld, Paul | Delft University of Technology |
Keywords: Medical technology - Innovation, Medical technology - Design and development
Abstract: Loosening of pedicle screws after spinal fusion surgery can prevent the desired fusion between vertebrae and may be reason for revision surgery. Especially in osteoporotic bone, toggling of pedicle screws is a common problem which compromises the fixation strength of these screws and can lead to loosening or axial pull-out of the screw. In this study we explore the use of an in-pedicle expandable anchor that shapes to the pedicle to increase the toggling resistance of the anchor by increasing the contact area between the anchor and the dense cortical bone of the pedicle. A scaled up, two dimensional prototype was designed. The prototype consists of a bolt and ten stainless steel wedges that expand by tensioning the bolt. During the expansion, the wedges are required to compress the cancellous bone. Based on the first preliminary experiment, it was found that the expansion of the wedges resulted in successful compression of 5 PCF cancellous bone phantom (Sawbones). This preliminary study shows that an expandable in-pedicle anchor could be a feasible option to increase the toggling resistance of spinal bone anchors, especially in osteoporotic bone. Clinical Relevance— Toggling of pedicle screws is a major cause of screw loosening. In this preliminary study, the use of an in-pedicle expandable anchor to increase the toggling resistance of spinal bone anchors is explored.
|
|
11:15-11:30, Paper ThBT10.4 | |
Investigating Innovation Ecosystems for Wearable Medical Devices |
|
Matic, Dunja | University of Toronto |
Foley, Rider | University of Virginia |
Asare, Philip | University of Toronto |
Keywords: Medical technology - Innovation, Medical technology - Product development process, Point of care - Home-based applications
Abstract: Wearable medical technologies (wearables) are a type of digital health technology that have the potential to transform the delivery of healthcare by offering a personalized, predictive, and preventative form of patient care. Unfortunately, the adoption of these technologies remains low, indicating an issue with the innovation ecosystem. Existing literature on innovation ecosystems fails to address wearables and the trade-offs between profitability and health outcomes, hindering discussion on how to promote the widespread adoption of wearables. This paper reviews and synthesizes literature from the business community and healthcare technology community on innovation ecosystems to contribute towards developing a more robust model of the innovation ecosystem for developing wearables. Future work aims to enrich this conceptualization with interviews of key actors in the innovation ecosystem.
|
|
11:30-11:45, Paper ThBT10.5 | |
Functional Near-Infrared Spectroscopy of Prefrontal Cortex During Memory Encoding and Recall in Elderly with Type 2 Diabetes Mellitus |
|
Zhao, Fei | University at Buffalo SUNY |
Tomita, Machiko | University at Buffalo SUNY |
Dutta, Anirban | University at Buffalo SUNY |
Keywords: Empowering individual healthcare decisions through technology, Preventive medicine, Medical technology - Clinical testing/clinical trials
Abstract: Low-frequency Fahræus–Lindqvist-driven oscillations in the small vessels are crucial because oscillations in small vessels support nutrient supply. Understanding of this is critical in type 2 diabetes mellitus (T2DM) to develop therapeutic measures in order to prevent Alzheimer's Disease Related Dementias. Indeed, vascular factors are known to contribute to cerebrovascular disease as well as mild cognitive impairment and dementia, which are predicted to affect 152 million people by 2050 (Alzheimer's Disease International London, UK, 2019). In this clinical study, we performed functional near-infrared spectroscopy (fNIRS) of the forehead to investigate the effect of the Mini-Cog with three-item recall test on the prefrontal cortex (PFC) activation and the relative oscillatory power in the 0.01–0.02-Hz (Fahræus–Lindqvist effect) and 0.021–0.052 Hz (smooth muscle autonomic innervation) frequency bands in elderly (60 years and older) T2DM and age-matched controls. We found a significant (p<0.01) difference in the PFC activation between elderly subjects with T2DM and age-matched elderly controls. Moreover, power spectral density (PSD) analysis revealed a significantly lower relative power in 0.021–0.052 Hz (smooth muscle autonomic innervation) frequency band in elderly subjects with T2DM during the Mini-Cog three-item recall test. Furthermore, a drop in the oscillatory power in the 0.01–0.02 Hz frequency band during Mini-Cog three-item recall test was found more pronounced in the elderly subjects with T2DM. Therefore, our study highlighted portable brain imaging to capture cerebrovascular reactivity to cognitive load that may provide a biomarker of cerebrovascular dysfunction in T2DM.
|
|
ThBT12 |
M1 |
Theme 06. Machine Learning - Deep Learning |
Oral Session |
Chair: Dragomir, Andrei | National University of Singapore |
Co-Chair: Almani, Muhammad Noman | University of Florida |
|
10:30-10:45, Paper ThBT12.1 | |
Kernel Temporal Differences for EEG-Based Reinforcement Learning Brain Machine Interfaces |
|
Thapa, Bhoj Raj | University of Kentucky |
Restrepo Tangarife, Daniel | Universidad Tecnológica De Pereira |
Bae, Jihye | University of Kentucky |
Keywords: Brain-computer/machine interface, Neural signals - Machine learning & Classification, Neural signals - Nonlinear analysis
Abstract: Kernel temporal differences (KTD) (𝛌) algorithm integrated in Q-learning (Q-KTD) has shown its applicability and feasibility for reinforcement learning brain machine interfaces (RLBMIs). RLBMI with its unique learning strategy based on trial-error allows continuous learning and adaptation in BMIs. Q-KTD has shown good performance in both open and closed-loop experiments for finding a proper mapping from neural intention to control commands of an external device. However, previous studies have been limited to intracortical BMIs where monkey’s firing rates from primary motor cortex were used as inputs to the neural decoder. This study provides the first attempt to investigate Q-KTD algorithm’s applicability in EEG-based RLBMIs. Two different publicly available EEG data sets are considered, we refer to them as Data set A and Data set B. EEG motor imagery tasks are integrated in a single step center-out reaching task, and we observe the open-loop RLBMI experiments reach 100% average success rates after sufficient learning experience. Data set A converges after approximately 20 epochs for raw features and Data set B shows convergence after approximately 40 epochs for both raw and Fourier transform features. Although there still exist challenges to overcome in EEG-based RLBMI using Q-KTD, including increasing the learning speed, and optimization of a continuously growing number of kernel units, the results encourage further investigation of Q-KTD in closed-loop RLBMIs using EEG.
|
|
10:45-11:00, Paper ThBT12.2 | |
Discrimination of Subjective Cognitive Decline from Healthy Control Based on Glucose-Oxygen Metabolism Network Coupling Features and Machine Learning |
|
Ding, Changchang | Shanghai University |
Wang, Luyao | Shanghai University |
Han, Ying | XuanWu Hospital of Capital Medical University |
jiang, jiehui | Shanghai University |
Keywords: Neurological disorders, Brain functional imaging
Abstract: Background: Our previous studies have proved that preclinical Alzheimer's disease (AD) which including subjective cognitive decline (SCD) stage, can be distinguished from normal control (NC) by glucose-oxygen metabolism coupling at the voxel level, but whether the coupling at the network level worked has not been studied. Therefore, this study aimed to explore the coupling relationship between brain glucose metabolic connectivity network and oxygen functional connectivity network, and whether its feasibility as a biomarker to discriminate SCD from healthy control (HC). Methods: Resting-state functional magnetic resonance imaging (rs-fMRI) and glucose positron emission tomography (PET) based on hybrid PET/MRI scans were used to investigate metabolism-oxygen metabolism coupling in 56 SCD individuals and 54 HCs. Network coupling features were selected by logistic regression-recursive feature elimination (LR-RFE), and then a linear support vector machine (SVM) was used to distinguish SCD and HC by using 5-fold cross-validation. Results: The classification average accuracy of network coupling had reached 76.36% with a standard deviation of 9.85% (with a sensitivity of 77.82% ± 15.13% and a specificity of 75.30% ± 15.15%). After receiver operating characteristic (ROC) analysis, the average area under curve (AUC) of network coupling was 0.788 (95% confidence interval [CI] = [0.653-0.983]). Conclusion: This study provided a new perspective for exploring network coupling. The proposed classification method highlighted the potential clinical application by combing glucose-oxygen metabolism coupling and machine learning in identifying SCD.
|
|
11:00-11:15, Paper ThBT12.3 | |
Multilayer Network Framework Reveals Cross-Frequency Coupling Hubs in Cortical Olfactory Perception |
|
Jiang, Mengting | National University of Singapore |
Dimitriadis, Stavros | CARDIFF UNIVERSITY |
Seet, Manuel | NUS |
Hamano, Junji | Procter and Gamble |
Saba, Mariana | Procter and Gamble |
Thakor, Nitish | National University of Singapore |
Dragomir, Andrei | National University of Singapore |
Keywords: Brain functional imaging - EEG, Neural signal processing, Brain-computer/machine interface
Abstract: Olfactory perception is shaped by dynamic interactions among networks of widely distributed brain regions involved in several neurocognitive processes. However, the neural mechanisms that enable effective coordination and integrative processing across these brain region, which have different functions and operating characteristics, are not yet fully understood. In this study we use electroencephalography (EEG) signals and a multilayer network formalism to model cross-frequency coupling across the brain and identify brain regions that operate as connecting hubs, thus facilitating integrative function. To this goal we investigate α − γ coupling and θ − γ coupling during exposure to olfactory stimuli of different pleasantness levels. We found that a wider distributed network of hubs emerges in the higher pleasantness condition and that significant differences in the hubs connectivity are located in the middle frontal and central regions. Our results indicate the consistent functional role that γ band activity plays in information integration in olfactory perception.
|
|
11:15-11:30, Paper ThBT12.4 | |
A Cross-Modality Deep Learning Method for Measuring Decision Confidence from Eye Movement Signals |
|
Fei, Cheng | Shanghai Jiao Tong University |
Li, Rui | Shanghai Jiao Tong University, |
Zhao, Li-Ming | Shanghai Jiao Tong University |
Li, Ziyi | Shanghai Jiao Tong University |
Lu, Bao-Liang | Shanghai Jiao Tong University |
Keywords: Human performance - Modelling and prediction
Abstract: Electroencephalography (EEG) signals can effectively measure the level of human decision confidence. However, it is difficult to acquire EEG signals in practice due to the expensive cost and complex operation, while eye movement signals are much easier to acquire and process. To tackle this problem, we propose a Cross-modality deep learning method based on Deep Canoncial Correlation Analysis (CDCCA) to transform each modality separately and coordinate different modalities into a hyperspace by using specific canonical correlation analysis constraints. In our proposed method, only eye movement signals are used as inputs in the test phase and the knowledge from EEG signals is learned in the training stage. Experimental results on two human decision confidence datasets demonstrate that our proposed method achieves advanced performance compared with the existing single-modal approaches trained and tested on eye movement signals and maintains a competitive accuracy in comparison with multimodal models.
|
|
11:30-11:45, Paper ThBT12.5 | |
Estimating Reward Function from Medial Prefrontal Cortex Cortical Activity Using Inverse Reinforcement Learning |
|
Tan, Jieyuan | Hong Kong University of Science and Technology |
Shen, Xiang | Hong Kong University of Science and Technology |
Zhang, Xiang | The Hong Kong University of Science and Technology |
SONG, Zhiwei | The Hong Kong University of Science and Technology |
Wang, Yiwen | Hong Kong University of Science and Techology |
Keywords: Brain-computer/machine interface, Neural signal processing
Abstract: Reinforcement learning (RL)-based brain-machine interfaces (BMIs) learn the mapping from neural signals to subjects’ intention using a reward signal. External rewards (water or food) or internal rewards extracted from neural activity are leveraged to update the parameters of decoders in the existing RL-based BMI framework. However, for complex tasks, the design of external reward could be difficult, which may not fully reflect the subject’s own evaluation internally. It is important to obtain an internal reward model from neural activity to access subject’s internal evaluation when the subject is performing the task through trial and error. In this paper, we propose to use an inverse reinforcement learning (IRL) method to estimate the internal reward function interpreted from the brain to assist the update of the decoders. Specifically, the inverse Q-learning (IQL) algorithm is applied to extract internal reward information from real data collected from medial prefrontal cortex (mPFC) when a rat was learning a two-lever-press discrimination task. Such an internal reward information is validated by checking whether it can guide the training of the RL decoder to complete movement task. Compared with the RL decoder trained with the external reward, our approach achieves a similar decoding performance. This preliminary result validates the effectiveness of using IRL to obtain the internal reward model. It reveals the potential of estimating internal reward model to improve the design of autonomous learning BMIs.
|
|
11:45-12:00, Paper ThBT12.6 | |
Recurrent Neural Networks Controlling Musculoskeletal Models Predict Motor Cortex Activity During Novel Limb Movements |
|
Almani, Muhammad Noman | University of Florida |
Saxena, Shreya | University of Florida |
Keywords: Motor learning, neural control, and neuromuscular systems, Neuromuscular systems - Computational modeling, Brain physiology and modeling - Neural dynamics and computation
Abstract: Goal-driven networks trained to perform a task analogous to that performed by biological neural populations are being increasingly utilized as insightful computational models of motor control. The resulting dynamics of the trained networks are then analyzed to uncover the neural strategies employed by the motor cortex to produce movements. However, these networks do not take into account the role of sensory feedback in producing movement, nor do they consider the complex biophysical underpinnings of the underlying musculoskeletal system. Moreover, these models can not be used in context of predictive neuromechanical simulations for hypothesis generation and prediction of neural strategies during novel movements. In this research, we adapt state-of-the-art deep reinforcement learning (DRL) algorithms to train a controller to drive a developed anatomically accurate monkey arm model to track experimentally recorded kinematics. We validate that the trained controller mimics biologically observed neural strategies to produce movement. The trained controller generalizes well to unobserved conditions as well as to perturbation analyses. The recorded firing rates of motor cortex neurons can be predicted from the controller activity with high accuracy even on unseen conditions. Finally, we validate that the trained controller outperforms existing goal-driven and representational models of motor cortex in single neuron decoding accuracy, thus showing the utility of the complex underpinnings of anatomically accurate models in shaping motor cortex neural activity during limb movements. The learned controller can be used for hypothesis generation and prediction of neural strategies during novel movements and unobserved conditions.
|
|
ThCT1 |
Alsh-1 |
Theme 12. Point-Of-Care Technologies for Perosnlized Healthcare |
Oral Session |
|
14:00-14:15, Paper ThCT1.1 | |
An mHealth App for the Non-Contact Measurement of Pulmonary Function Using the Smartphone’s Built-In Depth Sensor |
|
Mitsuya, Masaru | The University of Electro-Communications |
Kurosawa, Masaki | The University of Electro-Communications |
Kirimoto, Tetsuo | The University of Electro-Communications |
Matsui, Takemi | Tokyo Metropolitan University |
Sun, Guanghao | The University of Electro-Communications |
Keywords: Point of care - Respiratory monitoring, Point of care - Home-based applications, Point of care - Clinical use and acceptance
Abstract: The use of smartphones in clinical practice is referred to as mobile health (mHealth). This has attracted great interest in both academia and industry because of its potential to augment healthcare. In this study, we developed an mHealth app for the non-contact measurement of chest-wall movements using the iPhone ’s built-in depth sensor, thereby enabling a pulmonary self-monitoring function for personal use. The depth sensor provides depth values for each pixel and 2D mapping of the chest-wall movements. To extract respiratory signals from the right and left thoracic regions and abdomen, a 2D-depth image-segmentation method was implemented. The method was based on the anatomy and physiology of chest-wall movements, assuming differences in the anterior displacement in the thoracic and abdominal regions. It was observed that the differences were significant (p < 0.05) in the segmented regions of interest (ROIs) of the right and left thoracic region and abdomen. Respiratory signals extracted from each ROI were compared with the contact bio-impedance signals, which were highly correlated (r = 0.94).
|
|
14:15-14:30, Paper ThCT1.2 | |
Iterative Development of a Software to Facilitate Independent Home Use of BCI Technologies for Children with Quadriplegic Cerebral Palsy |
|
Floreani, Erica Danielle | University of Calgary |
Kelly, Dion | University of Calgary |
Rowley, Danette | Alberta Children's Hospital |
Irvine, Brian | University of Calgary |
Kinney-Lang, Eli | University of Calgary |
Kirton, Adam | University of Calgary |
Keywords: Point of care - Home-based applications, Medical technology - Design and development, Personalized medicine
Abstract: Brain-computer interfaces (BCIs) are emerging as a new solution for individuals with severe disability to interact with the world. However, BCI technologies have yet to reach end-users in their daily lives due to significant translational gaps. To address these gaps, we applied user-centered design principles to establish a home BCI program for children with quadriplegic cerebral palsy. This work describes the technical development of the software we designed to facilitate BCI use at home. Children and their families were involved at each design stage to evaluate and provide feedback. Since deployment, seven families have successfully used the system independently at home and continue to use BCI at home to further enable participation and independence for their children. Clinical relevance: The design and successful implementation of user-centered software for home use will both inform on the feasibility of BCI as a long-term access solution for children with neurological disabilities as well as decrease barriers of accessibility and availability of BCI technologies for end-users.
|
|
14:30-14:45, Paper ThCT1.3 | |
Privacy-Preserving In-Bed Pose and Posture Tracking on Edge |
|
Kamath, Cholpady Vikram | Northeastern University |
Liu, Shuangjun | Northeastern University |
Ostadabbas, Sarah | Northeastern University |
Keywords: Point of care - Detection and monitoring, Point of care - Home-based applications, Empowering individual healthcare decisions through technology
Abstract: In-bed behavior monitoring is commonly needed for bed-bound patient and has long been confined to wearable devices or expensive pressure mapping systems. Meanwhile, vision-based human pose and posture tracking while experiencing a lot of attention/success in the computer vision field has been hindered in terms of usability for in-bed cases, due to huge privacy concerns surrounding this topic. Moreover, the inference models for mainstream pose and posture estimation often require excessive computing resources, impeding their implementation on edge devices. In this paper, we introduce a privacy-preserving in-bed pose and posture tracking system running entirely on an edge device with added functionality to detect stable motion as well as setting user-specific alerts for given poses. We evaluated the estimation accuracy of our system on a series of retrospective infrared (LWIR) images as well as samples from a real-world test environment. Our test results reached over 93.6% estimation accuracy for in-bed poses and achieved over 95.9% accuracy in estimating three in-bed posture categories.
|
|
14:45-15:00, Paper ThCT1.4 | |
Evaluating the Empatica E4 Derived Heart Rate and Heart Rate Variability Measures in Older Men and Women |
|
Guruswamy Ravindran, Kiran Kumar | University of Surrey |
della Monica, Ciro | University of Surrey |
Atzori, Giuseppe | University of Surrey |
Lambert, Damion | University of Surrey |
Revell, Victoria | University of Surrey |
Dijk, Derk-Jan | University of Surrey |
Keywords: Point of care - Evaluation and validation, Point of care - Clinical use and acceptance, Point of care - Heart rate monitoring
Abstract: Wearable heart rate monitors offer a cost-effective way of non-invasive, long-term monitoring of cardiac health. Validation of wearable technologies in an older populations is essential for evaluating their effectiveness during deployment in healthcare settings. To this end, we evaluated the validity of heart rate measures from a wearable device, Empatica E4, and compared them to the electrocardiography (ECG). We collected E4 data simultaneously with ECG in thirty-five older men and women during an overnight sleep recording in the laboratory. We propose a robust approach to resolve the missing inter-beat interval (IBI) data and improve the quality of E4 derived measures. We also evaluated the concordance of heart rate (HR) and heart rate variability (HRV) measures with ECG. The results demonstrate that the automatic E4 heart rate measures capture long-term HRV whilst the short-term metrics are affected by missing IBIs. Our approach provides an effective way to resolve the missing IBI issue of E4 and extracts reliable heart rate measures that are concordant with ECG.
|
|
15:00-15:15, Paper ThCT1.5 | |
Smartphone-Based Point-Of-Care Urinalysis Assessment |
|
Kibria, Imran E | National University of Sciences and Technology |
Ali, Hussnain | University of Texas at Dallas |
Khan, Shoab | CASE-Center for Advanced Studies |
Keywords: Point of care - Diagnostics, Point of care - Detection and monitoring, Empowering individual healthcare decisions through technology
Abstract: A dipstick urinalysis test is performed by immersing a reagent strip in the urine specimen and then comparing the resulting reagent pad colors with a reference key. The color assessment of the reagent strip can be performed manually or by using a urine analyzer. However, the manual procedure is prone to subjective inaccuracies in varying ambient illumination and urine analyzer equipment is expensive. This paper presents a smartphone-based machine-learning approach to accurately determine the reagent pad colors for automated assessment. We start with a unique calibration chart and use multivariate linear regression to map the captured color values to their true equivalents. This accounts for the camera-induced distortions and ambient illumination factors. Subsequently, the color comparison is performed using the least Euclidean distance to match the calibrated color of each reagent pad with the reference key. The results from an experimental study, using five different smartphone cameras and three common illumination settings, indicate a high degree of accuracy in color assessment for synthetic dipsticks. The proposed smartphone-based method is an easy-to-perform, time-efficient, and cost-effective solution for an automated urinalysis and could be used as an alternative to manual reading or benchtop urine analyzers.
|
|
15:15-15:30, Paper ThCT1.6 | |
Bio-Conductivity Characteristics of Chronic Kidney Disease Stages Examined by Portable Frequency-Difference Electrical Impedance Tomography |
|
Yap, Desmond Y.H. | The University of Hong Kong |
Ma, Elsa K.Y. | Gense Technologies Ltd |
Oon, Wei Yi | The University of Hong Kong |
Lee, Wing Hang | Gense Technologies Ltd |
Li, Wai Ho | Gense Technologies Ltd |
Ho, Cheuk Man | Gense Technologies Ltd |
Gautama, Brianna | Gense Technologies Ltd |
Chan, Russell | NYU School of Medicine |
Wong, Eddie C. | Gense Technologies Ltd |
Keywords: Point of care - Home-based applications
Abstract: Chronic kidney disease (CKD) is an escalating global health concern, and non-invasive means for early CKD detection is eagerly awaited. Here, we explore the potential of using home-based frequency-difference electrical impedance tomography (fdEIT) to evaluate CKD based on bio-conductivity characteristics. We first verified the feasibility of using portable EIT capturing bio-conductivity in fresh pig kidneys ex vivo. We further performed bio-conductivity measurement in vivo paired with standard eGFR measurements on CKD patients by EIT and traditional blood test, respectively. Our results showed a significant correlation between renal bio-conductivity changes captured by fdEIT and standard eGFR scores. These results hold promise to be developed into a non-invasive and portable device for early CKD detection and longitudinal CKD treatment monitoring in clinical, community and home-based settings.
|
|
ThCT3 |
Boisdale-1 |
Theme 01. Signal Processing and Classification of Photoplethysmographic
Signals |
Oral Session |
Chair: Allen, John | Coventry University |
|
14:00-14:15, Paper ThCT3.1 | |
Signal Quality Assessment of Photoplethysmogram Signals Using Quantum Pattern Recognition Technique and Lightweight CNN Module |
|
Sarkar, Sayan | Wecare Medservice Llp |
Ghosh, Aayushman | Indian Institute of Engineering Science and Technology, Shibpur |
Chatterjee, Tamaghno | Indian Institute of Engineering Science and Technology, Shibpur |
Keywords: Data mining and big data methods - Biosignal classification, Data mining and big data methods - Pattern recognition, Data mining and big data methods - Machine learning and deep learning methods
Abstract: Photoplethysmography (PPG) signal comprises physiological information related to cardiorespiratory health. High-quality PPG signals are necessary to extract cardiores piratory information accurately. Motion artifacts can easily corrupt PPG signals due to human locomotion, leading to noise enriched, poor quality signals. Several rule-based and Machine-Learning (ML) - based approaches for PPG signal quality estimation are available, but those algorithms’ efficacy is questionable. So, the authors propose a lightweight CNN architecture for signal quality assessment by employing a novel Quantum Pattern Recognition (QPR) technique. The proposed algorithm is validated on manually annotated data obtained from the University of Queensland database. A total of 28366, 5s signal segments are preprocessed and transformed into image files of 20 × 500 pixels for input to the 2D CNN architecture. The developed model classifies the PPG signal as ’good’ and ’bad’ with an accuracy of 98.3% with 99.3% sensitivity, 94.5% specificity and 98.9% F1-score. The experimental analysis concludes that slim architecture and novel Spatio-temporal pattern recognition technique improve the system’s performance. The proposed approach is suitable for a resource-constrained wearable implementation.
|
|
14:15-14:30, Paper ThCT3.2 | |
PPG Signal Reconstruction Using Deep Convolutional Generative Adversarial Network |
|
Wang, Yuning | University of Turku |
Azimi, Iman | University of Turku |
Kazemi, Kianoosh | University of Turku |
Rahmani, Amir M. | Department of Computer Science, University of California Irvine, |
Liljeberg, Pasi | Department of Information Technology, University of Turku |
Keywords: Data mining and big data methods - Machine learning and deep learning methods, Neural networks and support vector machines in biosignal processing and classification
Abstract: Photoplethysmography (PPG) is a non-invasive technique used in wearable devices to collect various vital signs, including heart rate and heart rate variability. The signal is highly susceptible to motion artifacts, which is inevitable in health monitoring and may lead to inaccurate decision-making. Studies in the literature proposed time series analysis, signal decomposition, and machine learning methods to reconstruct PPG signals or reduce noise. However, they are limited to short-term noisy signals or to noise caused by certain physical activities. In this paper, we propose a deep convolutional generative adversarial network (GAN) method to reconstruct distorted PPG signals. Our method exploits the temporal information extracted from the corrupted signal and preceding data to perform PPG reconstruction. The model is trained and tested using data collected by smartwatches in a home-based health monitoring application. We evaluate the proposed GAN method in comparison to three state-of-the-art PPG reconstruction methods. The evaluation includes noisy PPG signals with different durations and SNR values. The proposed method outperforms the other methods by obtaining the least error rates. The results indicate that the proposed method is effective for improving PPG signal quality to produce reliable heart rate and heart rate variability.
|
|
14:30-14:45, Paper ThCT3.3 | |
CapNet: A Deep Learning-Based Framework for Estimation of Capnograph Signal from PPG |
|
Ahmed, Shahed | Bangladesh University of Engineering and Technology |
Islam, Md. Tariqul | Bangladesh University of Engineering and Technology |
Biswas, Soumav | Bangladesh University of Engineering & Technology |
Hayther Samrat, Rayhan | Bangladesh University of Engineering and Technology |
Islam, Md. Tafhimul | Bangladesh University of Engineering and Technology |
Subhana, Arik | Bangladesh University of Engineering and Technology |
Shahnaz, Celia | Bangladesh University of Engineering and Technology |
Keywords: Data mining and big data methods - Machine learning and deep learning methods, Neural networks and support vector machines in biosignal processing and classification
Abstract: Ambulatory respiration signal extraction system is required to maintain continuous surveillance of a patient with respiratory deficiency. The capnograph signal has received a lot of attention in recent years as a valuable indicator of respiratory conditions. However, the typical capnograph signal extraction method is quite expensive and also unpleasant to the patient due to the involvement of a nasal cannula. With the advent of wearable sensor technology, there has been significant research on the use of photoplethysmogram (PPG) signals as a less expensive alternative to extract respiratory information. In this paper, we propose CapNet, a novel deep learning-based framework which takes the regular PPG signal as input, and estimates the capnograph signal as output. Training, validation and testing of the proposed networks in CapNet is done using the IEEE TMBE Respiratory Rate Benchmark dataset by utilizing reference capnograph respiration signals. With a lower MSE and higher cross-correlation values, CapNet outperforms two traditional signal processing algorithms and another recently proposed deep neural network, RespNet. The proposed framework expectantly can be implementable and feasible for constant supervising of patients undergoing respiratory ailments.
|
|
14:45-15:00, Paper ThCT3.4 | |
Unsupervised Study of Plethysmography Signals through DTW Clustering |
|
Germain, Thibaut | Centre Borelli, ENS Paris-Saclay |
Truong, Charles | Centre Borelli, ENS Paris-Saclay |
Oudre, Laurent | Université Paris-Saclay, ENS Paris-Saclay |
Krejci, Eric | Centre Borelli, CNRS UMR9010 |
Keywords: Data mining and big data methods - Pattern recognition, Signal pattern classification, Nonlinear dynamic analysis - Biomedical signals
Abstract: The study of plethysmography time series is crucial to better understand the breathing behavior of mice, in particular the influence of neurotoxins on the respiratory system. Current approaches rely on a few respiratory descriptors computed on individual breathing cycles that fail to account for the variety of breathing habits and their evolution with time. In this paper we introduce a new procedure for the automatic analysis of plethysmography signals. Our method relies on a new and robust segmentation of respiratory cycles and a DTW-based clustering algorithm to extract the most typical respiratory cycles (called reference sequences). We can then create a symbolic representation of any new recording by matching respiratory cycles to their closest reference sequence. This new representation is a visual and quantitative tool to assess the breathing behavior of mice and its evolution with time. Our method is applied to plethysmography signals collected on mice with two different genotypes and exposed to a neurotoxin. Clinical relevance: This article proposes a novel approach for studying plethysmography data. Our algorithm is able to accurately extract meaningful respiratory cycles and associated ventilation patterns descriptors such as tidal volume and inhalation/exhalation duration. In addition, thanks to the associated symbolic representation of signals, the temporal evolution of respiration is easily quantified. This opens a new research path to study the often slowly evolving and subtle influence of neurotoxins on the respiratory system.
|
|
15:00-15:15, Paper ThCT3.5 | |
Classifying Nocturnal Blood Pressure Patterns Using Photoplethysmogram Features |
|
Finnegan, Eoin | University of Oxford |
Davidson, Shaun | University of Oxford |
Harford, Mirae | University of Oxford |
Jorge, Joao | University of Oxford |
Villarroel, Mauricio | University of Oxford |
Tarassenko, Lionel | University of Oxford |
Keywords: Signal pattern classification, Data mining and big data methods - Biosignal classification
Abstract: Circadian rhythms in blood pressure (BP) may in some cases be indicative of an increased risk of adverse cardiovascular events. However, current methods for assessing these rhythms can be disruptive to sleep, work, and daily activities. Features of the photoplethysmogram (PPG), which can be non-invasively and unobtrusively recorded, have been suggested as surrogate measures of BP. This work investigates the presence of a circadian rhythm in these features and evaluates their potential to classify nocturnal BP patterns. 742 patients who were discharged home from the ICU were selected from the MIMIC-III database. Our results show that a number of PPG features exhibit a clear and observable circadian rhythm. Of the 19 features evaluated, the circadian rhythms of 5 features outperformed heart rate (HR) in terms of correlation with the circadian rhythm of SBP (|r| > 0.81). We also present evidence that a metric combining the PPG features significantly improves BP phenotype classification accuracy.
|
|
15:15-15:30, Paper ThCT3.6 | |
Neural Network Based Algorithm for a Spectrogram Classification of Wrist-Type PPG Using High-Order Harmonics Processing |
|
Fedorin, Illia | Samsung R&D Institute Ukraine |
Pohribnyi, Vitalii | Samsung R&D Institute Ukraine |
Sverdlov, Denys | Samsung R&D Institute Kyiv, Ukraine |
Krasnoshchok, Illia | Samsung R&D Institute Ukraine |
Keywords: Time-frequency and time-scale analysis - Time-frequency analysis, Signal pattern classification, Neural networks and support vector machines in biosignal processing and classification
Abstract: The importance of accurate and continuous heart rate monitoring during workout cannot be overestimated. Supporting heart rate in the desired range, you strengthen the heart muscle and the overall fitness level. Therefore, the precise heart rate measurements are important at each stage: before workout, during exercises and after completion. One of the most important problems for precise heart rate measurement during high intensive exercises with the help of wearable devices is the movement artifacts. Even the smallest movement of the muscles, the turn of the wrist, the movement of the fingers or even the displacement of the fitness tracker per millimeter - all this very much distorts the useful signal. To solve the problem of motion artifacts, both digital signal processing approaches are used, as well as deep learning methods. In this paper, we offer a new method of processing the signal of wearable devices during workout, in particular to solve the motion artifacts problem, using deep neural networks. A distinctive feature of the model is the use of higher signal harmonics to determine the shape and type of signal. In particular, a method is proposed for classifying the signal spectrogram to noise, movement and useful component. During cross-validation on an available datasets, we compared the effectiveness of the proposed approach for spectrogram classification and received an improvement of averaged ROC AUC (area under the receiver operating characteristic curve) and F1 Score by 5% by using higher harmonics.
|
|
ThCT4 |
Boisdale-2 |
Theme 01. Signal Processing and Classification of Speech and Acoustic
Signals |
Oral Session |
|
14:00-14:15, Paper ThCT4.1 | |
Unaligned Multimodal Sequences for Depression Assessment from Speech |
|
Zhao, Ziping | Tianjin Normal University |
Wang, Keru | Tianjin Normal University |
Keywords: Neural networks and support vector machines in biosignal processing and classification
Abstract: Abstract — A growing area of mental health research pertains to how an individual's degree of depression might be automatically assessed through analyzing multimodal-based objective markers. However, when combined with machine learning, this research can be challenging due to the existence of unaligned multimodal sequences and the limited amount of annotated training data. In this paper, a novel cross-modal framework for automatic depression severity assessment is proposed. The low-level descriptions (LLDs) from multiple clues (such as text, audio and video) are extracted, after which multimodal fusion via cross-modal attention mechanism is utilized to facilitate the learning of more accurate feature representations. For the features extracted from each modality, the cross-modal attention mechanism is utilized to continuously update the input sequence of the target mode, until the score of the patient's health questionnaire (PHQ-8) can finally be obtained. Moreover, Self-Attention Generative Adversarial Networks (SAGAN) is employed to increase the amount of training data available for depression severity analysis. Experimental results on the depression sub-challenge dataset of the Audio/Visual Emotion Challenge (AVEC 2017 and AVEC 2019) demonstrate the effectiveness of our proposed method.
|
|
14:15-14:30, Paper ThCT4.2 | |
The Impact of Speaker Diarization on a DNN-Based Autism Severity Estimation |
|
Eni, Marina | Ben-Gurion University of the Negev |
Gorodetski, Alex | BGU |
Dinstein, Ilan | Ben Gurion University |
Zigel, Yaniv | Ben-Gurion University of the Negev |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Physiological systems modeling - Signal processing in physiological systems, Time-frequency and time-scale analysis - Time-frequency analysis
Abstract: This paper presents a speech-based system for autism severity estimation combined with automatic speaker diarization. Speaker diarization was performed by two different methods. The first used acoustic features, which included Mel-Frequency Cepstral Coefficients (MFCC) and pitch, and the second used x-vectors – embeddings extracted from Deep Neural Networks (DNN). The speaker diarization was trained using a Fully Connected Deep Neural Network (FCDNN) in both methods. We then trained a Convolutional Neural Network (CNN) to estimate the severity of autism based on 48 acoustic and prosodic features of speech. One hundred thirty-two young children were recorded in the Autism Diagnostic Observation Schedule (ADOS) examination room, using a distant microphone. Between the two diarization methods, the MFCC and Pitch achieved a better Diarization Error Rate (DER) of 26.91%. Using this diarization method, the severity estimation system achieved a correlation of 0.606 (Pearson) between the predicted and the actual autism severity scores (i.e., ADOS scores).
|
|
14:30-14:45, Paper ThCT4.3 | |
UFRC: A Unified Framework for Reliable COVID-19 Detection on Crowdsourced Cough Audio |
|
Chang, Jiangeng | National University of Singapore |
Ruan, Yucheng | National University of Singapore |
Cui, Shaoze | National University of Singapore |
John, Soong Tshon Yit | National University of Singapore |
Feng, Mengling | Massachusetts Institute of Technology |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Data mining and big data methods - Machine learning and deep learning methods, Data mining and big data methods - Biosignal classification
Abstract: We suggested a unified system with core components of data augmentation, ImageNet-pretrained ResNet-50, cost-sensitive loss, deep ensemble learning, and uncertainty estimation to quickly and consistently detect COVID-19 using acoustic evidence. To increase the model's capacity to identify a minority class, data augmentation and cost-sensitive loss are incorporated (infected samples). In the COVID-19 detection challenge, ImageNet-pretrained ResNet-50 has been found to be effective. The unified framework also integrates deep ensemble learning and uncertainty estimation to integrate predictions from various base classifiers for generalisation and reliability. We ran a series of tests using the DiCOVA2021 challenge dataset to assess the efficacy of our proposed method, and the results show that our method has an AUC-ROC of 85.43 percent, making it a promising method for COVID-19 detection. The unified framework also demonstrates that audio may be used to quickly diagnose different respiratory disorders.
|
|
14:45-15:00, Paper ThCT4.4 | |
A Cough-Based Deep Learning Framework for Detecting COVID-19 |
|
Hoang, Truong | FPT Software Ho Chi Minh Ltd |
PHAM, LAM | Austrian Institute of Technology |
Ngo, Dat | University of Essex |
Nguyen, Hoang D. | University of Glasgow |
Keywords: Signal pattern classification, Neural networks and support vector machines in biosignal processing and classification
Abstract: This paper presents a deep learning framework for detecting COVID-19 positive subjects from their cough sounds. In particular, the proposed approach comprises two main steps. In the first step, we generate a feature representing the cough sound by combining an embedding extracted from a pre-trained model and handcrafted features extracted from draw audio recording, referred to as the front-end feature extraction. Then, the combined features are fed into different back-end classification models for detecting COVID-19 positive subjects in the second step. Our experiments on the Track-2 dataset of the Second 2021 DiCOVA Challenge achieved the second top ranking with an AUC score of 81.21 and the top F1 score of 53.21 on a Blind Test set, improving the challenge baseline by 8.43% and 23.4% respectively and showing deployability, robustness and competitiveness with the state-of-the-art systems.
|
|
15:00-15:15, Paper ThCT4.5 | |
Automated Quality Assessment for Accelerometer-Based Heart Sounds Recorded with a Novel Subcutaneous Medical Implant |
|
Tatulli, Eric | Univ. Grenoble Alpes, CNRS, CHU Grenoble Alpes, Grenoble INP, TI |
Fontecave-Jallon, Julie | Univ. Grenoble Alpes, CNRS, CHU Grenoble Alpes, Grenoble INP |
Gumery, Pierre-Yves | Université Grenoble Alpes |
Keywords: Signal pattern classification, Data mining and big data methods - Pattern recognition, Physiological systems modeling - Signal processing in physiological systems
Abstract: In the context of monitoring patients with heart failure conditions, the automated assessment of heart sound quality is of major importance to insure the relevance of the medical analysis of the heart sound data. We propose in this study a technique of quality classification based on the selection of a small set of representative features. The first features are chosen to characterize whether the periodicity, complexity or statistical nature of the heart sound recordings. After segmentation process, the latter features are probing the detectability of the heart sounds in cardiac cycles. Our method is applied on a novel subcutaneous medical implant that combines ECG and accelerometric-based heart sound measurements. The actual prototype is in pre-clinical phase and has been implanted on 4 pigs, which anatomy and activity constitute a challenging environment for obtaining clean heart sounds. As reference quality labeling, we have performed a three-class manual annotation of each recording, qualified as ``good'', ``unsure'' and ``bad''. Our method allows to retrieve good quality heart sounds with a sensitivity and an accuracy of 82%+/-2% and 88%+/-6% respectively. Clinical relevance: By accurately recovering high quality heart sound sequences, our method will enable to monitor reliable physiological indicators of heart failure complications such as decompensation.
|
|
ThCT6 |
Carron-2 |
Theme 09. Brain Disorders I |
Oral Session |
|
14:00-14:15, Paper ThCT6.1 | |
CNN-LSTM Based Multimodal MRI and Clinical Data Fusion for Predicting Functional Outcome in Stroke Patients |
|
Hatami, Nima | INSA-Lyon |
Tae-Hee, Cho | INSA-Lyon |
Laura, Mechtouff | Hospices Civils De Lyon |
Eker, Omer | Hospices Civils De Lyon |
Rousseau, David | Laboratoire LARIS, Université D'Angers |
Frindel, Carole | Umr Cnrs 5220 - Inserm U630 |
Keywords: Computer modeling for treatment planning, Neuromuscular systems - Stroke therapy devices / technologies
Abstract: Clinical outcome prediction plays an important role in stroke patient management where the modified Rankin scale (mRS), a measure of global disability, is widely applied.From a machine learning point-of-view, one of the main challenges is dealing with heterogeneous data at patient admission, i.e. the image data which are multi-dimensional and the clinical data which are scalars. In this paper, a multimodal convolutional neural network - long short-term memory (CNN-LSTM) based ensemble model is proposed.For each MR image, a dedicated network module provides preliminary prediction of the mRS score. The final mRS score is obtained by merging the preliminary probabilities of each module dedicated to a specific type of MR image weighted by the clinical metadata, here age or the NIH Stroke Scale/Score. The experimental results demonstrate that the proposed model surpasses the baselines and offers an original way to automatically encode the spatio-temporal context of MR images in a deep learning architecture. The highest AUC(0.77) was achieved for the proposed model with NIHSS.
|
|
14:15-14:30, Paper ThCT6.2 | |
Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning: Preliminary Results |
|
Manjur, Sultan Mohammad | University of Connecticut |
Hossain, Md Billal | University of Connecticut |
CONSTABLE, PAUL | Caring Futures Institute College of Nursing and Health Sciences, |
Thompson, Dorothy A. | UCL Great Ormond Street Institute of Child Health, University Co |
Marmolejo-Ramos, Fernando | Center for Change and Complexity in Learning, University of Sout |
Lee, Irene O | Behavioral and Brain Sciences Unit, Population Policy and Practi |
Skuse, David H | Behavioral and Brain Sciences Unit, Population Policy and Practi |
Posada-Quintero, Hugo Fernando | University of Connecticut |
Keywords: Diagnostic devices - Physiological monitoring, Ambulatory Diagnostic devices - Point of care technologies
Abstract: Autism spectrum disorder (ASD) is a neurodevelopmental condition that impacts language, communication and social interactions. The current diagnostic process for ASD is based upon a detailed multidisciplinary assessment. Currently no clinical biomarker exists to help in the diagnosis and monitoring of this condition that has a prevalence of approximately 1%. The electroretinogram (ERG), is a clinical test that records the electrical response of the retina to light. The ERG is a promising way to study different neurodevelopmental and neurodegenerative disorders, including ASD. In this study, we have proposed a machine learning based method to detect ASD from control subjects using the ERG waveform. We collected ERG signals from 47 control (CO) and 96 ASD individuals. We analyzed ERG signals both in the time and the spectral domain to gain insight into the statistically significant discriminating features between CO and ASD individuals. We evaluated the machine learning (ML) models using a subject independent cross validation-based approach. Time-domain features were able to detect ASD with a maximum 65% accuracy. The classification accuracy of our best ML model using time-domain and spectral features was 86%, with 98% sensitivity. Our preliminary results indicate that spectral analysis of ERG provides helpful information for the classification of ASD.
|
|
14:30-14:45, Paper ThCT6.3 | |
A Comparison of an Implanted Accelerometer with a Wearable Accelerometer for Closed-Loop DBS |
|
Rojas-Torres, Erick | California State University, Los Angeles |
Schmidt, Stephen | Duke University |
Chowdhury, Afsana | Duke University |
Pajic, Miroslav | Duke University |
Turner, Dennis | Duke University |
Won, Deborah Soonmee | California State University, Los Angeles |
Keywords: Wireless technologies for interrogation of implantable therapeutic devices, Neuromuscular systems - Deep brain stimulation technologies
Abstract: Sensing technology, as well as cloud communication, is enabling the development of closed-loop deep brain stimulation for Parkinson’s disease. The accelerometer is a practical sensor that can provide information about the disease/health state of the patient as well as physical activity levels, all of which in the long-term can provide feedback information to an adaptive closed-loop control algorithm for more effective and personalized DBS therapy. In this paper, we present for the first time, acceleration streamed from Medtronic’s RC+S device in patients with Parkinson’s disease while at home, and compare it to acceleration acquired concurrently from the patient’s Apple Watch. We examined the correlation between the accelerometer signals at varying time scales. We also compared the spectral band power obtained from the two accelerometers. While there was an average correlation of 0.37 for subject 1 and 0.50 for subject 2 between the two acceleration signals on a time scale of 10 minutes, the correlation was lower for shorter time scales on the order of seconds. There was greater spectral power in the Parkinsonian tremor band of 4-7 Hz for the externally worn accelerometer than the internal accelerometer, but the internal accelerometer showed greater relative power distributed in the higher frequencies (7-30 Hz). Thus, based on this preliminary analysis, we expect that the internal accelerometer may be used to assess patient activity and state for closed-loop DBS but tremor detection may require more sophisticated signal processing. Furthermore, the internal accelerometer may contain information in higher frequency bands that reveal information about the patient state.
|
|
14:45-15:00, Paper ThCT6.4 | |
Energy Savings of Multi-Channel Neurostimulators with Non-Rectangular Current-Mode Stimuli Using Multiple Supply Rails |
|
Kolovou-Kouri, Konstantina | Delft University of Technology |
Rashidi, Amin | Delft University of Technology |
Varkevisser, Francesc | Delft University of Technology |
Serdijn, Wouter A. | Delft University of Technology |
Giagka, Vasiliki | Bioelectronics, TU Delft |
Keywords: Neuromodulation devices
Abstract: In neuromodulation applications, conventional current mode stimulation is often preferred over its voltage mode equivalent due to its good control of the injected charge. However, it comes at the cost of less energy-efficient output stages. To increase energy efficiency, recent studies have explored non-rectangular stimuli. The current work highlights the importance of an adaptive supply for an output stage with programmable non-rectangular stimuli and accordingly proposes a system-level architecture for multi-channel stimulators. In the proposed architecture, a multi-output DC/DC Converter (DDC) allows each channel to choose among the available supply levels (i.e., DDC outputs) independently and based on its instant voltage/current requirement. A system-level analysis is carried out in Matlab to calculate the possible energy savings of this solution, compared to the conventional approach with a fixed supply. The energy savings have been simulated for a variety of supply levels and waveform amplitudes, suggesting energy savings of up to 83% when employing 6 DDC outputs and the lowest current amplitude explored (250 µA), and as high as 26% for a full-scale amplitude (4 mA).
|
|
15:00-15:15, Paper ThCT6.5 | |
Design of Optimal Coils for Deep Transcranial Magnetic Stimulation |
|
Vilchez Membrilla, Jose Antonio | University of Cadiz |
Cobos Sánchez, Clemente | University of Cadiz |
Torres Montijano, Carmen | University of Granada |
Valerga Puerta, Ana Pilar | School of Engineering, University of Cadiz |
Fernández Pantoja, Mario | University of Granada |
Keywords: Neuromuscular systems - Deep brain stimulation technologies, Neuromuscular systems - Neural stimulation, Neuromuscular systems - Muscle stimulation
Abstract: Abstract — In this work, a stream function inverse boundary element method (IBEM) has been used for designing different deep transcranial magnetic stimulation (dTMS) coils to activate the prefrontal cortex and the temporal lobe have been set as the target regions. In addition, the performances of these coils have been described and the electric field induced by them has been obtained by using a computational forward technique. These results show that the stream function IBEM is an ideal approach to design optimal dTMS coils capable of producing deep stimulation in the target brain regions. Clinical relevance — The design problem proposed here can be used to produce efficient dTMS stimulators for neurological disorders, which can overcome some of the currently existing limitations of the most common devices employed in TMS.
|
|
ThCT7 |
Dochart-1 |
Theme 10. Sensor Informatics - Wearable and Multi-Modal Data |
Oral Session |
Chair: Sandham, William | Scotsig |
|
14:00-14:15, Paper ThCT7.1 | |
Modeling Subjective Fear Using Skin Conductance: A Preliminary Study in Virtual Reality |
|
Baldini, Andrea | University of Pisa |
Frumento, Sergio | University of Pisa |
menicucci, danilo | National Reaserch Council (CNR) |
Gemignani, Angelo | University of Pisa |
Scilingo, Enzo Pasquale | University of Pisa |
Greco, Alberto | University of Pisa |
Keywords: General and theoretical informatics - Statistical data analysis, Health Informatics - Virtual reality in medicine
Abstract: Reliably measuring fear perception could help evaluate the effectiveness of treatments for pathological conditions such as specific phobias or post-traumatic stress syndrome (e.g., exposure therapy). In this study, we developed a novel virtual reality (VR) scenario to induce fear and evaluate the related physiological response by the analysis of skin conductance (SC) signal. Eighteen subjects voluntarily experienced the fear VR scenario while their SC was recorded. After the experiment, each participant was asked to score the perceived subjective fear using a Likert scale from 1 to 10. We used the cvxEDA algorithm to process the collected SC signals and extract several features able to estimate the autonomic response to the fearful stimuli. Finally, the extracted features were linearly combined to model the subjective fear perception scores by means of LASSO linear regression. The sparsification imposed by the LASSO procedure to mitigate the overfitting risk identified an optimal linear model including only the standard deviation of the tonic SC component as a regressor (p = 0.007; R 2 = 0.3337). The significant contribution of this feature to the model suggests that subjects experiencing more intense subjective fear have a more variable and unstable sympathetic tone.
|
|
14:15-14:30, Paper ThCT7.2 | |
Design of a Wearable Flexible Meander-Line Antenna for Wireless Medical Body Area Networks |
|
Ali, Shahid | Petronas University, Malaysia |
Sovuthy, Cheab | Department of Electrical and Electronic Engineering, Universiti |
Noghanian, Sima | University of North Dakota |
Abbasi, Qammer H | James Watt School of Engineering, University of Glasgow |
Asenova, Tatjana | Sonova AG, Switzerland |
Derleth, Peter | Sonova AG |
Casson, Alexander James | The University of Manchester |
Arslan, Tughrul | University of Edinburgh |
Hussain, Amir | Edinburgh Napier University, UK |
Keywords: Health Informatics - Behavioral health informatics, Health Informatics - Healthcare communication networks, Health Informatics - Personal health systems
Abstract: A flexible meander-line monopole antenna (MMA) is presented for wireless medical body area networks. The antenna can be worn for on-and off-body healthcare applications. The overall dimension of the MMA is 37mm×50mm×2.37mm3. The MMA was manufactured and measured, and results matched with simulations. The MMA design shows a bandwidth of up to 1282.4 (450.5) MHz and provides gains of 3.03 (4.85) dBi in the lower and upper operating bands, respectively, showing omnidirectional radiation patterns in free space. While worn on the chest or arm, bandwidths as high as 688.9 (500.9) MHz and 1261.7 (524.2) MHz, and the gains of 3.80 (4.67) dBi and 3.00 (4.55) dBi were observed. The experimental measurements of the read range confirmed the results of the coverage range of up to 11 meters.
|
|
14:30-14:45, Paper ThCT7.3 | |
Multi-Modal Data Integration Platform Combining Clinical and Preclinical Models of Post Subarachnoid Hemorrhage Epilepsy |
|
Maharathi, Biswajit | University of Illinois at Chicago, Chicago |
Wong, Jensen | University of Illinois at Chicago |
Geraghty, Joseph R. | University of Illinois College of Medicine |
Serafini, Anna | University of Illinois at Chicago |
Davis, Jared | University of Illinois at Chicago |
Butler, Mitchell | University of Illinois at Chicago |
Kolar, Subhash | University of Illinois at Chicago |
pandey, Dilip | University of Illinois at Chicago |
Loeb, Jeffrey A. | University of Illinois at Chicago |
Keywords: Health Informatics - Clinical information systems, Health Informatics - Health data acquisition, transmission, management and visualization, Health Informatics - Health information systems
Abstract: Abstract—Subarachnoid hemorrhage (SAH) is a devastating neurological injury that can lead to many downstream complications including epilepsy. Predicting who will get epilepsy in order to find ways to prevent it as well as stratify patients for future interventions is a major challenge given the large number of variables not only related to the injury itself, but also to what happens after the injury. Extensive multimodal data are generated during the process of SAH patient care. In parallel, preclinical models are under development that attempt to imitate the variables observed in patients. Computational tools that consider all variables from both human data and animal models are lacking and demand an integrated, time-dependent platform where researchers can aggregate, store, visualize, analyze, and share the extensive integrated multimodal information. We developed a multi-tier web-based application that is secure, extensible, and adaptable to all available data modalities using flask micro-web framework, python, and PostgreSQL database. The system supports data visualization, data sharing and downloading for offline processing. The system is currently hosted inside the institutional private network and holds ~14 TB of data from 164 patients and 71 rodents. Clinical Relevance—Our platform supports clinical and preclinical data management. It allows users to comprehensively visualize patient data and perform visual analytics. These utilities can improve research and clinical practice for subarachnoid hemorrhage and other brain injuries.
|
|
14:45-15:00, Paper ThCT7.4 | |
Speech, Facial and Fine Motor Features for Conversation-Based Remote Assessment and Monitoring of Parkinson’s Disease |
|
Kothare, Hardik | Modality.AI, Inc |
Roesler, Oliver | Modality.AI, Inc |
Burke, William | Modality.AI, Inc |
Neumann, Michael | Modality.AI, Inc |
Liscombe, Jackson | Modality.AI, Inc |
Exner, Andrew | Purdue University |
Snyder, Sandy | Purdue University |
Cornish, Andrew | Modality.AI, Inc |
Habberstad, Doug | Modality.AI, Inc |
Pautler, David | Modality.AI, Inc |
Suendermann-Oeft, David | Modality.AI, Inc |
Huber, Jessica | Purdue University |
Ramanarayanan, Vikram | Modality.AI, Inc |
Keywords: Health Informatics - Telehealth, Sensor Informatics - Data inference, mining, and trend analysis, Health Informatics - Health data acquisition, transmission, management and visualization
Abstract: We present a cloud-based multimodal dialogue platform for the remote assessment and monitoring of speech, facial and fine motor function in Parkinson’s Disease (PD) at scale, along with a preliminary investigation of the efficacy of the various metrics automatically extracted by the platform. 22 healthy controls and 38 people with Parkinson's Disease (pPD) were instructed to complete four interactive sessions, spaced a week apart, on the platform. Each session involved a battery of tasks designed to elicit speech, facial movements and finger movements. We find that speech, facial kinematic and finger movement dexterity metrics show statistically significant differences between controls and pPD. We further investigate the sensitivity, specificity, reliability and generalisability of these metrics. Our results offer encouraging evidence for the utility of automatically-extracted audiovisual analytics in remote monitoring of PD and other movement disorders.
|
|
15:00-15:15, Paper ThCT7.5 | |
Preserving Data Privacy and Accuracy of Human Pose Estimation Software Based on CNNs for Remote Gait Analysis |
|
Martini, Enrico | University of Verona |
Boldo, Michele | University of Verona |
Aldegheri, Stefano | University of Verona |
Vale, Nicola | University of Verona |
Filippetti, Mirko | University of Verona |
Smania, Nicola | University of Verona |
Bertucco, Matteo | University of Verona |
Picelli, Alessandro | University of Verona |
Bombieri, Nicola | Univ. Verona |
Keywords: Health Informatics - Telemedicine, Health Informatics - internet of things in healthcare, Health Informatics - eHealth
Abstract: In the last years there have been significant improvements in the accuracy of real-time 3D skeletal data estimation software. These applications based on convolutional neural networks (CNNs) can play a key role in a variety of clinical scenarios, from gait analysis to medical diagnosis. One of the main challenges is to apply such intelligent video analytic at a distance, which requires the system to satisfy, beside accuracy, also data privacy. To satisfy privacy by default and by design, the software has to run on ”edge” computing devices, by which the sensitive information (i.e., the video stream) is elaborated close to the camera while only the process results can be stored or sent over the communication network. In this paper we address such a challenge by evaluating the accuracy of the state-of-the-art software for human pose estimation when run ”at the edge”. We show how the most accurate platforms for pose estimation based on complex and deep neural networks can become inaccurate due to subsampling of the input video frames when run on the resource constrained edge devices. In contrast, we show that, starting from less accurate and ”lighter” CNNs and enhancing the pose estimation software with filters and interpolation primitives, the platform achieves better real- time performance and higher accuracy with a deviation below the error tolerance of a marker-based motion capture system.
|
|
15:15-15:30, Paper ThCT7.6 | |
Emotional Models for the Estimation of Arousal and Pleasure in Older Adults During Balance Rehabilitation Training |
|
Tsiouris, Kostas | Biomedical Engineering Laboratory, School of Electrical and Comp |
Tsakanikas, Vasilis D. | University of Ioannina |
Gatsios, Dimitris | University of Ioannina |
Pavlou, Marousa | Centre for Human and Applied Physiological Sciences, King’s Coll |
Fotiadis, Dimitrios I. | University of Ioannina |
Keywords: Sensor Informatics - Behavioral informatics, Sensor Informatics - Physiological monitoring, Sensor Informatics - Wearable systems and sensors
Abstract: Emotional computing has been previously applied to assess physiological behavior in a wide variety of tasks and activities. This study extends for the first time the use of emotional computing in the field of balance rehabilitation training. A proof-of-concept study was conducted to assess arousal and pleasure response to a range of physical exercises from the OTAGO and HOLOBALANCE balance rehabilitation programs with varying levels of difficulty and physical demand. Eleven participants were enrolled and performed a set of exercises wearing an ECG sensor, reporting arousal and pleasure at the end of each session. A dataset of 264 unique sessions was collected and used to extract heart rate variability (HRV) features from the measured RR intervals and automatically assess user arousal and pleasure, evaluating different classification algorithms. The results suggested that assessment of both emotions is feasible, reaching an accuracy of 72% and 74% for arousal and pleasure estimation, respectively. Clinical Relevance— Arousal and pleasure are clinically useful indicators of patient’s experience and engagement while performing balance rehabilitation exercises with novel sensing technologies and monitoring platforms.
|
|
ThCT8 |
Dochart-2 |
Theme 09. Therapeutic and Interventional Data Science / Novel Technologies |
Oral Session |
Chair: Linte, Cristian A. | Rochester Institute of Technology |
Co-Chair: Saccomandi, Paola | Politecnico Di Milano |
|
14:00-14:15, Paper ThCT8.1 | |
Evaluation and Comparison of Target Registration Error in Active and Passive Optical Tracking Systems |
|
Grünbeck, Inger Annett | The Intervention Centre, Oslo University Hospital and Department |
Teatini, Andrea | University of Oslo - Department of Informatics, the Intervention |
Kumar, Rahul Prasanna | Oslo University Hospital |
Elle, Ole Jakob | The Intervention Centre, Oslo University Hospital and Department |
Wiig, Ola | Oslo University Hospital |
Keywords: Robotic-aided therapies - Image guided surgery systems/ technologies, Clinical engineering -Verification and validation of diagnostic & therapeutic systems / technologies, Robotic-aided therapies - Computer-assisted surgery systems
Abstract: Optical tracking systems combined with imaging modalities such as computed tomography and magnetic resonance imaging are important parts of image guided surgery systems. By determining the location and orientation of surgical tools relative to a patient's reference system, tracking systems assist surgeons during the planning and execution of image guided procedures. Therefore, knowledge of the tracking system-induced error is of great importance. To this end, this study compared one passive and two active optical tracking systems in terms of their Target Registration Error. Two experiments were performed to measure the systems' accuracy, testing the impact of factors such as the size of the measuring volume, length of surgical instruments and environmental conditions with orthopedic procedures in mind. According to the performed experiments, the active systems achieved significantly higher accuracy than the tested passive system, reporting an overall accuracy of 0.063 mm (SD = 0.025) and 0.259 mm (SD = 0.152), respectively.
|
|
14:15-14:30, Paper ThCT8.2 | |
Augmented Reality As a Tool to Guide Patient-Specific Templates Placement in Pelvic Resections |
|
Mendicino, Antonellamaria Rita | Università Di Pisa |
Condino, Sara | University of Pisa |
Carbone, Marina | University of Pisa |
Cutolo, Fabrizio | EndoCAS Center, University of Pisa |
Cattari, Nadia | University of Pisa |
Andreani, Lorenzo | University Hospital of Pisa |
Parchi, Paolo Domenico | University of Pisa |
Rodolfo, Capanna | University of Pisa |
Ferrari, Vincenzo | Universià Di Pisa |
Keywords: Robotic-aided therapies - Computer-assisted surgery systems, Robotic-aided therapies - Surgical robotic systems, Robotic-aided therapies - Planning and execution technologies in surgical robotics
Abstract: Patient-specific templates (PST) have become a useful tool for guiding osteotomy in complex surgical scenarios such as pelvic resections. The design of the surgical template results in sharper, less jagged resection margins than freehand cuts. However, their correct placement can become difficult in some anatomical regions and cannot be verified during surgery. Conventionally, pelvic resections are performed using Computer Assisted Surgery (CAS), and in recent years Augmented Reality (AR) has been proposed in the literature as an additional tool to support PST placement. This work presents an AR task to simplify and improve the accuracy of the positioning of the template by displaying virtual content. The focus of the work is the creation of the virtual guides displayed during the AR task. The system was validated on a patient-specific phantom designed to provide a realistic setup. Encouraging results have been achieved. The use of the AR simplifies the surgical task and optimizes the correct positioning of the cutting template: an average error of 2.19 mm has been obtained, lower than obtained with state-of-the-art solutions. In addition, supporting PST placement through AR guidance is less time-consuming than the standard procedure that solely relies on anatomical landmarks as reference.
|
|
14:30-14:45, Paper ThCT8.3 | |
Unscented Kalman Filtering for Real Time Thermometry During Laser Ablation Interventions |
|
Soltani sarvestani, Mohammadamin | Politecnico Di Milano |
Cotin, Stephane | Inria |
Saccomandi, Paola | Politecnico Di Milano |
Keywords: Therapeutic devices and systems - ablation systems and technologies, Computer modeling for treatment planning
Abstract: We present a data-assimilation Bayesian framework in the context of laser ablation for the treatment of cancer. For solving the nonlinear estimation of the tissue temperature evolving during the therapy, the Unscented Kalman Filter (UKF) predicts the next thermal status and controls the ablation process, based on sparse temperature information. The purpose of this paper is to study the outcome of the prediction model based on UKF and to assess the influence of different model settings on the framework performances. In particular, we analyze the effects of the time resolution of the filter and the number and the location of the observations.
|
|
14:45-15:00, Paper ThCT8.4 | |
Comparison of Mechanistic and Learning-Based Tip Force Estimation on Tendon-Driven Soft Robotic Catheters |
|
Yaftian, Pegah | Concordia University |
Mohammadi Bandari, Naghmeh | Mechanical Engineering Department, Concordia University |
Dargahi, Javad | Concordia University |
Hooshiar, Amir | Concordia University |
Keywords: Tactile displays and perception, Biologically inspired robotics and micro-biorobotics - Machine learning and control, Robot-aided surgery - Remote surgery systems / telesurgery
Abstract: Abstract—Researchers have adopted mechanistic and learning-based approaches for tip force estimation on soft robotic catheters. Typically, the literature attributes the mechanistic methods with more accuracy while indicating the learning-based methods outpace in computational time. In this study, a previously validated mechanistic tip force estimation method was compared with four learning-based methods, i.e., support vector- regression (SVR), random-forest (RF), AdaBoost (Ada), and deep neural network (DNN). The learning-based methods were trained on experimental data acquired from a robotic catheter, developed in-house. The accuracy of force estimation using the five methods were compared with the ground truth forces in a teleoperated catheter manipulation test. Moreover, the capability of the learning-based models in contact detection, i.e., detection of the onset of tip contact, were compared with the ground truth. The results showed that the mechanical model had a mean-absolute error (MAE) of 8.8 mN while the MAE of SVR, RF, Ada, and DNN were 5.6, 5.2, 5.3, and 5.1 mN, respectively. Moreover, the accuracy and precision of the mechanistic model for contact detection was 89.2% and 91.7%, respectively, while these were 97.0%, 97.7%, 97.6%, and 97% and 97.9%, 98.3%, 97.8%, and 98.8% for the SVR, RF, Ada, and DNN, respectively. The comparison showed that with hyperparameter optimization the learning-based models surpassed the mechanistic model in accuracy and precision, while both method approaches revealed acceptable performance for the proposed application.
|
|
15:00-15:15, Paper ThCT8.5 | |
NnUNet-Based Multi-Modality Breast MRI Segmentation and Tissue-Delineating Phantom for Robotic Tumor Surgery Planning |
|
Alqaoud, Motaz | Old Dominion University |
Plemmons, John | Eastern Virginia Medical School |
Feliberti, Eric | Eastern Virginia Medical School |
Dong, Siqin | Old Dominion University |
Kaipa, Krishnanand | Old Dominion University |
Fichtinger, Gabor | Queen's University |
Xiao, Yiming | Concordia University |
Audette, Michel | Old Dominion University |
Keywords: Machine learning / Deep learning approaches, Multimodal imaging, Magnetic resonance imaging - MR breast imaging
Abstract: Abstract— Segmentation of the thoracic region and breast tissues is crucial for analyzing and diagnosing the presence of breast masses. This paper introduces a medical image segmentation architecture that aggregates two neural networks based on the state-of-the-art nnU-Net. Additionally, this study proposes a polyvinyl alcohol cryogel (PVA-C) breast phantom, based on its automated segmentation approach, to enable planning and navigation experiments for robotic breast surgery. The dataset consists of multimodality breast MRI of T2W and STIR images obtained from 10 patients. A statistical analysis of segmentation tasks emphasizes the Dice Similarity Coefficient (DSC), segmentation accuracy, sensitivity, and specificity. We first use a single class labeling to segment the breast region and then exploit it as an input for three-class labeling to segment fatty, fibroglandular (FGT), and tumorous tissues. The first network has a 0.95 DCS, while the second network has a 0.95, 0.83, and 0.41 for fat, FGT, and tumor classes, respectively.
|
|
15:15-15:30, Paper ThCT8.6 | |
Analysis of Current Deep Learning Networks for Semantic Segmentation of Anatomical Structures in Laparoscopic Surgery |
|
Silva, Bruno | Life and Health Sciences Research Institute (ICVS), School of Me |
Oliveira, Bruno | 2Ai - Applied Artificial Intelligence Laboratory |
Morais, Pedro | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Buschle, L. R. | Karl Storz SE & Co. KG, Tuttlingen, Germany |
Correia-Pinto, Jorge | Life and Health Sciences Research Institute (ICVS), School of Me |
Lima, Estêvão | ICVS/3Bs |
Vilaça, João | 2Ai - Applied Artificial Intelligence Laboratory |
Keywords: Image segmentation, Machine learning / Deep learning approaches
Abstract: Semantic segmentation of anatomical structures in laparoscopic videos is a crucial task to enable the development of new computer-assisted systems that can assist surgeons during surgery. However, this is a difficult task due to artifacts and similar visual characteristics of anatomical structures on the laparoscopic videos. Recently, deep learning algorithms have been showed promising results on the segmentation of laparoscopic instruments. However, due to the lack of large public datasets for semantic segmentation of anatomical structures, there are only a few studies on this task. In this work, we evaluate the performance of five networks, namely U-Net, U-Net++, DynUNet, UNETR and DeepLabV3+, for segmentation of laparoscopic cholecystectomy images from the recently released CholecSeg8k dataset. To the best of our knowledge, this is the first benchmark performed on this dataset. Training was performed with dice loss. The networks were evaluated on segmentation of 8 anatomical structures and instruments, performance was quantified through the dice coefficient, intersection over union, recall, and precision. Apart from the U-Net, all networks obtained scores similar to each other, with the U-Net++ being the network with the best overall score with a mean Dice value of 0.62. Overall, the results show that there is still room for improvement in the segmentation of anatomical structures from laparoscopic videos.
|
|
ThCT9 |
Gala |
Theme 02. Other Imaging Applications |
Oral Session |
Chair: Theissen, Helen | University of Oxford |
Co-Chair: Toschi, Nicola | University of Rome |
|
14:00-14:15, Paper ThCT9.1 | |
Probing the Link between the APOE-ε4 Allele and Whole-Brain Gray Matter Using Deep Learning |
|
Abrol, Anees | Georgia State University, the Mind Research Network |
Hajjar, Ihab | Emory University School of Medicine |
Calhoun, Vince D | Tri-Institutional Center for Translational Research in Neuroimag |
Keywords: Magnetic resonance imaging - MR neuroimaging, Brain imaging and image analysis, Machine learning / Deep learning approaches
Abstract: The APOE-ε4 allele is a known genetic risk for Alzheimer’s disease (AD). Thus, it can be reasoned that the APOE-ε4 allele would also impact neurodegeneration-associated structural brain changes. Here we probe if the APOE-ε4 genotype directly modulates the human brain’s gray matter using a neural network trained on the whole-brain gray matter images from the cognitively normally aging (CN) and AD individuals. To investigate the linkage between the APOE-ε4 allele and whole-brain (voxel-wise) gray matter, we systematically profile our investigation in multiple classification tasks, including diagnostic classification and APOE-ε4 classification conjointly as well as independently. Results suggest that although the MRI data can reliably track and reflect neurodegenerative changes in the brain cross-sectionally, the APOE-ε4 status may not be distinguishable correspondingly. The nonexistence of a direct and convincing modulative effect of APOE-ε4 on the whole-brain gray matter indicates that the gray matter changes may be independent of the APOE-ε4 status, and instead characterize a non-APOE, comorbid mechanism in AD.
|
|
14:15-14:30, Paper ThCT9.2 | |
Mutual Information Neural Estimation for Unsupervised Multi-Modal Registration of Brain Images |
|
Snaauw, Gerard | University of Adelaide |
Sasdelli, Michele | The University of Adelaide |
Maicas Suso, Gabriel | The University of Adelaide |
Lau, Stephan | The University of Adelaide |
Verjans, Johan | Australian Institute for Machine Learning |
Jenkinson, Mark | University of Oxford |
Carneiro, Gustavo | University of Adelaide |
Keywords: Deformable registration, Multimodal image fusion, Machine learning / Deep learning approaches
Abstract: Many applications in image-guided surgery and therapy require fast and reliable non-linear, multi-modal image registration. Recently proposed unsupervised deep learning-based registration methods have demonstrated superior performance compared to iterative methods in just a fraction of the time. Most of the learning-based methods have focused on mono-modal image registration. The extension to multi-modal registration depends on the use of an appropriate similarity function, such as the mutual information (MI). We propose guiding the training of a deep learning-based registration method with MI estimation between an image-pair in an end-to-end trainable network. Our results show that a small, 2-layer network produces competitive results in both mono- and multi-modal registration, with sub-second run-times. Comparisons to both iterative and deep learning-based methods show that our MI-based method produces topologically and qualitatively superior results with an extremely low rate of non-diffeomorphic transformations. Real-time clinical application will benefit from a better visual matching of anatomical structures and less registration failures/outliers.
|
|
14:30-14:45, Paper ThCT9.3 | |
Deciphering Stomach Myoelectrical Slow Wave Conduction Patterns Via Confocal Imaging of Gastric Pacemaker Cells and Fractal Geometry |
|
Mah, Sue Ann | University of Auckland |
Avci, Recep | The University of Auckland |
Du, Peng | The University of Auckland |
Vanderwinden, Jean-Marie | Université Libre De Bruxelles |
Cheng, Leo K | The University of Auckland |
Keywords: Functional image analysis, Optical imaging - Confocal microscopy, Image analysis and classification - Machine learning / Deep learning approaches
Abstract: Interstitial Cells of Cajal (ICC) are specialized gastrointestinal (GI) pacemaker cells that generate and actively propagate slow waves of depolarization (SWs) of the muscularis propria. SWs regulate the motility of the GI tract necessary for digestion, absorption of nutrients, and elimination of waste. Within the gastric wall, there are three main inter-connected layers of ICC networks: longitudinal muscle ICC (ICC-LM), myenteric plexus ICC (ICC-MP) & circumferential muscle (ICC-CM). Fractal structural parameters such as Fractal Dimension (FD), Lacunarity and Succolarity, have many advantages over physically-based parameters when it comes to characterizing the complex architectures of ICC networks. The analysis of networks of ICC throughout the proximal and distal murine gastric antrum with the FD and Lacunarity metrics was previously performed. Although the application of Succolarity is relatively nascent compared to the FD and Lacunarity; nevertheless, numerous studies have demonstrated the capability of this fractal measure to extract information from images associated with flow by which neither the FD nor Lacunarity are capable of discerning. In this study, Succolarity analysis of ICC-MP and ICC-CM networks were performed with confocal images taken across the proximal and distal murine antrum. Our findings demonstrated the Succolarity of ICC-MP and ICC-CM varied with directions and antral regions. The Succolarity of ICC-MP did not vary considerably with direction, however, Succolarity was higher in the aboral direction with 0.2113 0.1589, and 0.0637 0.0822 in the proximal and distal antrum, respectively. The overall Succolarity of ICC-MP was significantly higher than that of ICC-CM in the proximal antrum (0.1580 ± 0.1325 vs 0.0008 ± 0.0007, p-value=0.0008) and in the distal antrum (0.0449 ± 0.0409 vs 0.0006 ± 0.0010, p-value=0.003).
|
|
14:45-15:00, Paper ThCT9.4 | |
Evaluation of Non-Invasive Thermal Imaging for Detection of Viability of Onchocerciasis Worms |
|
Dedhiya, Ronak | Niramai Health Analytics |
Kakileti, Siva Teja | Niramai Health Analytix Pvt. Ltd |
Deepu, Goutham | Niramai Health Analytics (Intern) |
Gopinath, Kanchana | Niramai Health Analytics |
Opoku, Nicholas | School of Public Health, University of Health an Allied Science |
King, Christopher | Center for Global Health & Diseases, Case Western Reserve Univer |
Manjunath, Geetha | Niramai Health Analytix |
Keywords: Infra-red imaging, Image feature extraction, Image analysis and classification - Machine learning / Deep learning approaches
Abstract: Onchocerciasis is causing blindness in over half a million people in the world today. Drug development for the disease is crippled as there is no way of measuring effectiveness of the drug without an invasive procedure. Drug efficacy measurement through assessment of viability of onchocerca worms requires the patients to undergo nodulectomy which is invasive, expensive, time-consuming, skill-dependent, infrastructure dependent and lengthy process. In this paper, we discuss the first-ever study that proposes use of machine learning over thermal imaging to non-invasively and accurately predict the viability of worms. The key contributions of the paper are (i) a unique thermal imaging protocol along with pre-processing steps such as alignment, registration and segmentation to extract interpretable features (ii) extraction of relevant semantic features (iii) development of accurate classifiers for detecting the existence of viable worms in a nodule. When tested on a prospective test data of 30 participants with 48 palpable nodules, we achieved an Area Under the Curve (AUC) of 0.85. Clinical Relevance— This is the first ever research effort of using thermal imaging in the assessment of viability of onchocerca worms and it resulted in a very high specificity>95% which makes it a promising modality to pursue further.
|
|
15:00-15:15, Paper ThCT9.5 | |
Multi-Scale Graphical Representation of Cell Environment |
|
Theissen, Helen | University of Oxford |
Chakraborty, Tapabrata | University of Oxford |
Malacrino, Stefano | University of Oxford |
Royston, Daniel | Oxford University Hospitals NHS Foundation Trust |
Rittscher, Jens | University of Oxford |
Keywords: Multiscale image analysis, Image analysis and classification - Digital Pathology, Machine learning / Deep learning approaches
Abstract: We present a multi-scale graphical network that can capture the relevant representations of individual cell morphology, topological structure of cell communities in a tissue image, as well as whole slide level attributes. This helps to effectively merge the disease relevant cell morphology to the overall topological context within the sample, within one unified deep framework. From the explainability point of view, instead of empirical design, the graphs are designed with biomedical considerations in mind in order to have translational validity. We also provide a clinically interpretable visualisation of the cells and their micro- and macro-environment by leveraging label noise reduction. We demonstrate the efficacy of our methodology on myeloproliferative neoplasms (MPN), a haematopoietic stem cell disorder as an exemplar test case. The proposed method achieves an encouraging performance in the robust separation of different MPN subtypes in this exciting new dataset as part of this work.
|
|
15:15-15:30, Paper ThCT9.6 | |
Deep Learning Methods for Lesion Detection on Mammography Images: A Comparative Analysis |
|
Ferrete Ribeiro, Raul | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Gomes-Fonseca, João | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Torres, Helena | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Oliveira, Bruno | 2Ai - Applied Artificial Intelligence Laboratory |
Vilhena, Estela | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Morais, Pedro | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Vilaça, João | 2Ai - Applied Artificial Intelligence Laboratory |
Keywords: X-ray radiography, Image segmentation, Machine learning / Deep learning approaches
Abstract: Automatic lesion segmentation in mammography images assists in the diagnosis of breast cancer, which is the most common type of cancer especially among women. The robust segmentation of mammography images has been considered a backbreaking task due to: i) the low contrast of the lesion boundaries; ii) the extremely variable lesions’ sizes and shapes; and iii) some extremely small lesions on the mammogram image. To overcome these drawbacks, Deep Learning methods have been implemented and have shown impressive results when applied to medical image segmentation. This work presents a benchmark for breast lesion segmentation in mammography images, where six state-of-the-art methods were evaluated on 1692 mammograms from a public dataset (CBIS-DDSM), and compared considering the following six metrics: i) Dice coefficient; ii) Jaccard index; iii) accuracy; iv) recall; v) specificity; and vi) precision. The base U-Net, UNETR, DynUNet, SegResNetVAE, RF-Net, MDA-Net architectures were trained with a combination of the cross-entropy and Dice loss functions. Although the networks presented Dice scores superior to 86%, two of them managed to distinguish themselves. In general, the results demonstrate the efficiency of the MDA-Net and DynUnet with Dice scores of 90.25% and 89.67%, and accuracy of 93.48% and 93.03%, respectively.
|
|
ThCT12 |
M1 |
Theme 06. Machine Learning - Deep Learning II |
Oral Session |
Chair: Han, Yiyuan | University of Essex |
Co-Chair: Hofmann, Ulrich G. | University of Freiburg |
|
14:00-14:15, Paper ThCT12.1 | |
Machine Learning Approaches to Classify Anatomical Regions in Rodent Brain from High Density Recordings |
|
Windbühler, Anna | Machine Learning Group, Department of Informatics, Universita |
Okkesim, Şükrü | Fatih Universty |
Christ, Olaf | Albert-Ludwigs-University |
Mottaghi, Soheil | University of Freiburg |
Rastogi, Shavika | International Centre for Neuromorphic Systems, the MARCS Institu |
Schmuker, Michael | University of Hertfordshire |
Baumann, Timo | OTH Regensburg |
Hofmann, Ulrich G. | University of Freiburg |
Keywords: Neural signals - Machine learning & Classification, Brain functional imaging - Mapping, Neural interfaces - Microelectrode technology
Abstract: Identifying different functional regions during a brain surgery is a challenging task usually performed by highly specialized neurophysiologists. Progress in this field may be used to improve in situ brain navigation and will serve as an important building block to minimize the number of animals in preclinical brain research required by properly positioning implants intraoperatively. The study at hand aims to correlate recorded high-density extracellular signals with the volume of origin by deep learning methods. Our work establishes connections between the position in the brain and recorded high-density neural signals. This was achieved by evaluating the performance of BLSTM, BGRU, QRNN and CNN neural network architectures on multisite electrophysiological data sets. All networks were able to successfully distinguish cortical and thalamic brain regions according to their respective neural signals. The GRU provides the best results with an accuracy of 88.6 % and demonstrates that this classification task might be solved in higher detail while minimizing complex preprocessing steps.
|
|
14:15-14:30, Paper ThCT12.2 | |
Information Sparseness in Cortical Microelectrode Channels While Decoding Movement Direction Using an Artificial Neural Network |
|
Premchand, Brian | A*STAR, I2R |
Toe, Kyaw Kyar | Institute for Infocomm Research, A*STAR |
Wang, Chuanchu | Institute for Infocomm Research |
Libedinsky, Camilo | A*STAR |
Ang, Kai Keng | Institute for Infocomm Research |
So, Rosa | Institute for Infocomm Research |
Keywords: Motor learning, neural control, and neuromuscular systems, Brain physiology and modeling - Neural dynamics and computation
Abstract: Implanted microelectrode arrays can directly pick up electrode signals from the primary motor cortex (M1) during movement, and brain-machine interfaces (BMIs) can decode these signals to predict the directions of contemporaneous movements. However, it is not well known how much each individual input is responsible for the overall performance of a BMI decoder. In this paper, we seek to quantify how much each channel contributes to an artificial neural network (ANN)-based decoder, by measuring how much the removal of each individual channel degrades the accuracy of the output. If information on movement direction was equally distributed among channels, then the removal of one would have a minimal effect on decoder accuracy. On the other hand, if that information was distributed sparsely, then the removal of specific information-rich channels would significantly lower decoder accuracy. We found that for most channels, their removal did not significantly affect decoder performance. However, for a subset of channels (16 out of 61), removing them significantly reduced the decoder accuracy. This suggests that information is not uniformly distributed among the recording channels. We propose examining these channels further to optimize BMIs more effectively, as well as understand how M1 functions at the neuronal level.
|
|
14:30-14:45, Paper ThCT12.3 | |
A Riemannian Deep Learning Representation to Describe Gait Parkinsonian Locomotor Patterns |
|
Olmos, Juan | Universidad Industrial De Santander |
Martinez, Fabio | Universidad Industrial De Santander |
Keywords: Neurological disorders, Neurological disorders - Diagnostic and evaluation techniques, Neurorehabilitation
Abstract: Parkinson is the second most common neurodegenerative disease, mainly related to progressive locomotor alterations caused by dopamine deficiency. The gait kinematic is a principal disease biomarker that associates patterns like the step length, flexed posture, and bradykinesia with disease progression. Nonetheless, these patterns are analyzed from invasive setups that only capture coarse dynamics at advanced disease stages. This work introduces a very compact and robust deep representation that effectively learns a Riemannian manifold to describe locomotor parkinsonian patterns. Contrary to traditional deep strategies, the presented framework fully explores data geometry from input mean covariance matrices representing video sequences. These symmetric positive definite (SPD) matrices lie in a Riemannian manifold. Then such matrices are projected to the SPD net, which learns a bank of SPD matrices from a non-linear training, that may be exploited in a hierarchical composition from a set of layers. In a final layer, a projection in a Euclidean space allows learning the discriminatory patterns of PD w.r.t control population. In a retrospective study with a total of 22 patients (11 Parkinson's and 11 controls), the proposed approach achieves a remarkable classification between Parkinson's and control video sequences, correctly labeling all Parkinson's patients, and outperforming typical 3D convolutional representations.
|
|
14:45-15:00, Paper ThCT12.4 | |
Classification of Tonic Pain Experience Based on Phase Connectivity in the Alpha Frequency Band of the Electroencephalogram Using Convolutional Neural Networks |
|
Han, Yiyuan | University of Essex |
Valentini, Elia | University of Essex |
Halder, Sebastian | University of Essex |
Keywords: Brain physiology and modeling, Neural signals - Machine learning & Classification, Brain functional imaging - EEG
Abstract: The complexity of brain activity involved in the generation of the experience of pain makes it hard to identify neural markers able to predict pain states. The within and between subjects variability of pain hinders the predictive potential of machine learning models trained across participants. This challenge can be tackled by implementing deep learning classifiers based on convolutional neural networks (CNNs). We targeted phase-based connectivity in the alpha band recorded with electroencephalography (EEG) during resting states and sensory conditions (eyes open [O] and closed [C] as resting states, and warm [W] and hot [H] water as sensory conditions). Connectivity features were extracted and re-organized as square matrices, because CNNs are effective in detecting the patterns from 2D data. To assess the classifier performance we implemented two complementary approaches: we 1) trained and tested the classifier with data from all participants, and 2) using a leave-one-out approach, that is excluding one participant at a time during training while using their data as a test set. The accuracy of binary classification between pain condition (H) and eyes open resting state (O) was 94.16% with the first approach, and 61.01% with the leave-one-out approach.
|
|
15:00-15:15, Paper ThCT12.5 | |
Label Alignment Improves EEG-Based Machine Learning-Based Classification of Traumatic Brain Injury |
|
Vishwanath, Manoj | University of California, Irvine |
Dutt, Nikil | UC Irvine |
Rahmani, Amir M. | Department of Computer Science, University of California Irvine, |
Lim, Miranda | VA Portland Health Care System, Oregon Health & Science Universi |
Cao, Hung | University of California, Irvine |
Keywords: Neural signals - Machine learning & Classification, Neurological disorders - Traumatic brain injury, Neural signal processing
Abstract: Machine learning and deep learning algorithms have paved the way for improved analysis of biomedical data which has led to a better understanding of various biological conditions. However, one major hindrance to leveraging the potential of machine learning models is the requirement of huge datasets. In the biomedical domain, this becomes extremely difficult due to uncertainties in collecting high-quality data as well as, in the case of human subjects' data, privacy. Further, when it comes to biomedical data, inter-subject variability has been a long-entrenched issue. The data obtained from different individuals will differ to a considerable extent that it becomes difficult to find population differences in small datasets. In this work, we investigate the use of label alignment techniques on an EEG-based Traumatic Brain Injury (TBI) classification task to overcome inter-subject variability, thereby increasing the classification accuracy. We show an increase in accuracy of around 6% in some cases as compared to our previous results. In the end, we also propose a methodology to incorporate TBI data from a different species (e.g., mice) after domain adaptation, which might further improve the performance by increasing the amount of training datasets available for the classification model.
|
|
15:15-15:30, Paper ThCT12.6 | |
A Deep Learning Framework Based on Dynamic Channel Selection for Early Classification of Left and Right Hand Motor Imagery Tasks |
|
Hong, Jiazhen | Rutgers, the State University |
Shamsi, Foroogh | Rutgers University |
Najafizadeh, Laleh | Rutgers University |
Keywords: Brain-computer/machine interface, Neural signals - Machine learning & Classification
Abstract: Ideal brain-computer interfaces (BCIs) need to be efficient and accurate, demanding for classifiers that can work across subjects while providing high classification accuracy results from recordings with short duration. To address this problem, we present a new deep learning framework for discriminating motor imagery (MI) tasks from electroencephalography (EEG) signals. The framework consists of a 1D convolutional neural network-long short-term memory (CNN-LSTM), combined with a dynamic channel selection approach based on Davies-Bouldin index (DBI). Using data from BCI competition IV-IIa data, the proposed framework reports an average classification accuracy of 70.17% and 76.18% when using only 800 ms and 1500 ms of the EEG data after the task onset, respectively. The proposed framework dynamically balances individual differences, achieves comparable or better performance compared to existing work, while using short duration of EEG.
|
|
ThEP |
Hall 5 |
E-Poster Session III - July 14, 2022 |
Poster Session |
|
15:45-17:30, Subsession ThEP-01, Hall 5 | |
Theme 01. Data Mining Methods for Biosignals Poster Session, 5 papers |
|
15:45-17:30, Subsession ThEP-02, Hall 5 | |
Theme 01. EEG/MEG Signal Processing Poster Session, 7 papers |
|
15:45-17:30, Subsession ThEP-03, Hall 5 | |
Theme 01. Signal Processing & Classification of Muscle and Motion Signals Poster Session, 12 papers |
|
15:45-17:30, Subsession ThEP-04, Hall 5 | |
Theme 01. Signal Processing and Classification for Wearable Systems Poster Session, 4 papers |
|
15:45-17:30, Subsession ThEP-05, Hall 5 | |
Theme 01. Time-Frequency and Time-Scale Analysis of Biosignals Poster Session, 13 papers |
|
15:45-17:30, Subsession ThEP-06, Hall 5 | |
Theme 02. Brain Imaging & Image Analysis Poster Session, 4 papers |
|
15:45-17:30, Subsession ThEP-07, Hall 5 | |
Theme 02. Image Segmentation - P2 Poster Session, 10 papers |
|
15:45-17:30, Subsession ThEP-08, Hall 5 | |
Theme 02. Machine Learning/Deep Learning Applications - P2 Poster Session, 10 papers |
|
15:45-17:30, Subsession ThEP-09, Hall 5 | |
Theme 02. Optical and CT Imaging and Applications Poster Session, 11 papers |
|
15:45-17:30, Subsession ThEP-10, Hall 5 | |
Theme 02. Ultrasound Imaging and Applications Poster Session, 9 papers |
|
15:45-17:30, Subsession ThEP-11, Hall 5 | |
Theme 03. Micro/Nano-Bioengineering; Cellular/Tissue Engineering & Biomaterials P1 Poster Session, 5 papers |
|
15:45-17:30, Subsession ThEP-12, Hall 5 | |
Theme 04. Tissue and Organ Modeling Poster Session, 9 papers |
|
15:45-17:30, Subsession ThEP-13, Hall 5 | |
Theme 05. Cardiovascular Modeling Poster Session, 9 papers |
|
15:45-17:30, Subsession ThEP-14, Hall 5 | |
Theme 05. Imaging for Cardiovascular Diseases Poster Session, 4 papers |
|
15:45-17:30, Subsession ThEP-15, Hall 5 | |
Theme 06. EEG for Neurorehabilitation Poster Session, 9 papers |
|
15:45-17:30, Subsession ThEP-16, Hall 5 | |
Theme 06. Machine Learning, Brain Signal Processing for Neurorehabilitation & Neural Engineering III Poster Session, 8 papers |
|
15:45-17:30, Subsession ThEP-17, Hall 5 | |
Theme 06. Neural Engineering for Peripheral Nerves, Spinal Cord & Muscles Studies Poster Session, 12 papers |
|
15:45-17:30, Subsession ThEP-18, Hall 5 | |
Theme 06. Virtual Reality & Physical Sensors for Neurorehabilitation Poster Session, 12 papers |
|
15:45-17:30, Subsession ThEP-19, Hall 5 | |
Theme 07. Human Movement Sensing P2 Poster Session, 10 papers |
|
15:45-17:30, Subsession ThEP-20, Hall 5 | |
Theme 07. Novel Sensing and Applications P1 Poster Session, 10 papers |
|
15:45-17:30, Subsession ThEP-21, Hall 5 | |
Theme 07. Wearable Sensing P1 Poster Session, 10 papers |
|
15:45-17:30, Subsession ThEP-22, Hall 5 | |
Theme 08. Biorobotics and Biomechanics P2 Poster Session, 9 papers |
|
15:45-17:30, Subsession ThEP-23, Hall 5 | |
Theme 09. Brain Disorders P1 Poster Session, 6 papers |
|
15:45-17:30, Subsession ThEP-24, Hall 5 | |
Theme 09. Robotics and Tracking Poster Session, 4 papers |
|
15:45-17:30, Subsession ThEP-25, Hall 5 | |
Theme 10. General and Theoretical Informatics P4 Poster Session, 10 papers |
|
15:45-17:30, Subsession ThEP-26, Hall 5 | |
Theme 10. Health Informatics P3 Poster Session, 8 papers |
|
15:45-17:30, Subsession ThEP-27, Hall 5 | |
Theme 01. Biomedical Signal Processing IV Poster Session, 9 papers |
|
15:45-17:30, Subsession ThEP-28, Hall 5 | |
Theme 02. Biomedical Imaging and Image Processing III Poster Session, 9 papers |
|
15:45-17:30, Subsession ThEP-29, Hall 5 | |
Theme 02. Biomedical Imaging and Image Processing VII Poster Session, 10 papers |
|
15:45-17:30, Subsession ThEP-30, Hall 5 | |
Theme 04. Computational Systems, Modeling and Simulation in Medicine, Multiscale Modeling & Synthetic Biology III Poster Session, 9 papers |
|
15:45-17:30, Subsession ThEP-31, Hall 5 | |
Theme 06. Neural and Rehabilitation Engineering III Poster Session, 11 papers |
|
15:45-17:30, Subsession ThEP-32, Hall 5 | |
Theme 06. Neural and Rehabilitation Engineering V Poster Session, 7 papers |
|
15:45-17:30, Subsession ThEP-33, Hall 5 | |
Theme 07. Biomedical Sensors and Wearable Systems II Poster Session, 5 papers |
|
15:45-17:30, Subsession ThEP-34, Hall 5 | |
Theme 07. Biomedical Sensors and Wearable Systems V Poster Session, 10 papers |
|
15:45-17:30, Subsession ThEP-35, Hall 5 | |
Theme 09. Therapeutic & Diagnostic Systems and Technologies II Poster Session, 8 papers |
|
15:45-17:30, Subsession ThEP-36, Hall 5 | |
Theme 10. Biomedical & Health Informatics III Poster Session, 8 papers |
|
15:45-17:30, Subsession ThEP-37, Hall 5 | |
Theme 11. Biomedical Engineering Education and Society Poster Session, 6 papers |
|
ThEP-01 |
Hall 5 |
Theme 01. Data Mining Methods for Biosignals |
Poster Session |
Chair: Tibble, Holly | University of Edinburgh |
|
15:45-17:30, Paper ThEP-01.1 | |
Estimating Medication Adherence from Electronic Health Records Using Rolling Averages of Single Refill-Based Estimates |
|
Tibble, Holly | University of Edinburgh |
Sheikh, Aziz | University of Edinburgh |
Tsanas, Athanasios | University of Edinburgh |
Keywords: Data mining and big data methods - Patient outcome and risk analysis, Data mining and big data methods - Inter-subject variability and personalized approaches
Abstract: Medication adherence is usually defined as the manner in which a patient takes their medication, in relation to the regimen agreed to with their healthcare provider. Electronic Health Records (EHRs) can be used to estimate adherence in a cost-effective and non-invasive manner across large-scale populations, although there is no universally agreed optimal approach to doing so. We sought to explore patterns of asthma ICS prescription refills in a large EHR dataset, and to evaluate the use of rolling-average based measures towards short-term adherence estimation. Over 1.6 million asthma controllers were prescribed for our cohort of 91,332 individuals, between January 2009 and March 2017. The Continuous Single interval measures of medication Availability (CSA) and Gaps (CSG) were calculated for individual prescriptions, as well as rolling-average adherence measures of the CSA over 3, 5, or 10 past prescription intervals. 16.7% of the study population had only a single prescription during their follow-up (a median duration of 7.1 years). 51% of prescriptions were refilled before (or on the day that) supply was exhausted, and for 19% of prescription refills, the amount of medication dispensed should have lasted at least twice as long as the duration before the next refill was filled. The rolling average measures had statistically strong associations (Spearman |R|>0.7) with the estimate for the subsequent prescription refill. Rolling averages of multiple individual refill-level adherence estimates provide a novel and simple way to crudely smoothen estimates from individual prescription refills, which are strongly influenced by common (and adherent) real-world behaviors, for more meaningful and effective trend detection.
|
|
15:45-17:30, Paper ThEP-01.2 | |
Predicting Dog Phenotypes from Genotypes |
|
Bartusiak, Emily | Purdue University |
Barrabes, Miriam | UPC |
Rymbekova, Aigerim | University of Bologna |
Gimbernat-Mayol, Julia | Imperial College London |
Lopez, Cayetana | UPC |
Barberis, Lorenzo | Stanford University |
Mas Montserrat, Daniel | Stanford University |
Giro-i-Nieto, Xavier | Universitat Politecnica De Catalunya |
Ioannidis, Alexander | Stanford University |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Data mining and big data methods - Machine learning and deep learning methods, Signal pattern classification - Genetic algorithms
Abstract: We analyze dog genotypes (i.e., positions of dog DNA sequences that often vary between different dogs) in order to predict the corresponding phenotypes (i.e., unique observed characteristics). More specifically, given chromosome data from a dog, we aim to predict the breed, height, and weight. We explore a variety of linear and non-linear classification and regression techniques to accomplish these three tasks. We also investigate the use of a neural network (both in linear and non-linear modes) for breed classification and compare the performance to traditional statistical methods. We show that linear methods generally outperform or match the performance of non-linear methods for breed classification. However, we show that the reverse is true for height and weight regression. Finally, we evaluate the results of all of these methods based on the number of input features used in the analysis. We conduct experiments using different fractions of the full genomic sequences, resulting in input sequences ranging from 20 SNPs to ~200k SNPs. In doing so, we explore the impact of using a very limited number of SNPs for prediction. Our experiments demonstrate that these phenotypes in dogs can be predicted with as few as 0.5% of randomly selected SNPs (i.e., 992 SNPs) and that dog breeds can be classified with 50% balanced accuracy with as few as 0.02% SNPs (i.e., 40 SNPs).
|
|
15:45-17:30, Paper ThEP-01.3 | |
Multimodal Neurophysiological Transformer for Emotion Recognition |
|
Koorathota, Sharath | Columbia University |
Khan, Zain | Columbia University |
Lapborisuth, Pawan | Columbia University |
Sajda, Paul | Columbia University |
Keywords: Data mining and big data methods - Machine learning and deep learning methods, Data mining and big data methods - Biosignal classification, Multivariate methods
Abstract: Understanding neural function often requires multiple modalities of data, including electrophysiogical data, imaging techniques, and demographic surveys. In this paper, we introduce a novel neurophysiological model to tackle major challenges in modeling multimodal data. First, we avoid non-alignment issues between raw signals and extracted, frequency-domain features by addressing the issue of variable sampling rates. Second, we encode modalities through ``cross-attention'' with other modalities. Lastly, we utilize properties of our parent transformer architecture to model long-range dependencies between segments across modalities and assess intermediary weights to better understand how source signals affect prediction. We apply our Multimodal Neurophysiological Transformer (MNT) to predict valence and arousal in an existing open-source dataset. Experiments on non-aligned multimodal time-series show that our model performs similarly and, in some cases, outperforms existing methods in classification tasks. In addition, qualitative analysis suggests that MNT is able to model neural influences on autonomic activity in predicting arousal. Our architecture has the potential to be fine-tuned to a variety of downstream tasks, including for BCI systems.
|
|
15:45-17:30, Paper ThEP-01.4 | |
Real-Time Pilot Crew’s Mental Workload and Arousal Assessment During Simulated Flights for Training Evaluation: A Case Study |
|
Borghini, Gianluca | Sapienza University of Rome |
Arico, Pietro | Sapienza University of Rome |
Di Flumeri, Gianluca | University of Rome Sapienza |
Sciaraffa, Nicolina | Dept. Molecular Medicine, Sapienza University of Rome |
Di Florio, Antonio | Dept. Molecular Medicine, University of Rome “Sapienza” |
Ronca, Vincenzo | Sapienza University of Rome |
Giorgi, Andrea | Sapienza University of Rome |
Mezzadri, Lorenzo | Urbe Aero Flight Academy, Rome |
Gasparini, Renzo | Urbe Aero Flight Academy, Rome |
Tartaglino, Roberto | Urbe Aero Flight Academy, Rome |
Trettel, Arianna | BrainSigns |
Babiloni, Fabio | University of Rome |
Keywords: Data mining and big data methods - Machine learning and deep learning methods, Data mining and big data methods - Biosignal classification, Time-frequency and time-scale analysis - Time-frequency analysis
Abstract: Training assessment is usually done by evaluating information derived from instructor’s supervision related to the pilot’s operational performance and behavior. However, this approach lacks objective measures, especially regarding the pilots’ mental states while accomplishing the flight training tasks. The study therefore aimed at developing and testing a method for gathering and analyzing in real-time pilots’ brain activity and skin conductance to improve the training evaluation. In this regard, Novice pilots’ neurophysiological signals were acquired throughout multi-crew training sessions. The results demonstrated how the methodology proposed was able to endow real-time pilots’ mental workload and arousal assessment for i) better evaluating training progress and operational behavior during the training session, and ii) for objectively comparing different training sessions.
|
|
15:45-17:30, Paper ThEP-01.5 | |
Hepatitis C Virus Load Prediction from Serum Samples Using NIRS and L1-Penalized Classification |
|
Barquero-Pérez, Óscar | University Rey Juan Carlos |
Gómez-Sánchez, José | University Rey Juan Carlos |
Riado-Mínguez, Daniel | Hospital Universitario Fundación De Alcorcón |
González-Segovia, Jennifer | University Rey Juan Carlos |
García-Carretero, Rafael | Hospital Universitario De Móstoles |
Casas-Losada, María Luisa | Hospital Universitario Fundación De Alcorcón |
Fernández-Rodríguez, S | Hospital Universitario Fundación De Alcorcón |
Gutiérrez-García, María Luisa | Hospital Universitario Fundación De Alcorcón |
Jaime-Lara, Elena | Hospital Universitario Fundación De Alcorcón |
Pérez-Martínez, Enrique | University Rey Juan Carlos |
Ramos-López, Javier | University Rey Juan Carlos |
Salgüero-Fernández, Sergio | Hospital Universitario Fundación De Alcorcón |
Fernández-Rodríguez, Conrado | Hospital Universitario Fundación De Alcorcón |
Catalá-Rodríguez, Myriam | University Rey Juan Carlos |
Keywords: Signal pattern classification, Data mining and big data methods - Patient outcome and risk analysis
Abstract: Aims: The hepatitis C virus (HCV) has developed a strategy to coexist with its host resulting in varying degrees of tissue and cell damage, which generate different pathological phenotypes, such as varying degrees of fibrosis, cirrhosis, and hepatocellular carcinoma (HCC). However, there is no integrated information that can predict the evolutionary course of the infection. We propose to combine Near-infrared spectroscopy (NIRS) and machine learning techniques to provide a predictive model. In this work, we propose to discriminate HCV positivity in biobank patient serum samples. Methods: 126 serum samples from 38 HCV patients in different stages of the disease were obtained from the Biobank of Hospital Universitario Fundación Alcorcón. NIRS spectrum was captured by a FT-NIRS Spectrum 100 (Perkin Elmer) device in reflectance mode. For each patient, the HCV positivity was identified (PCR) and labeled as detectable = 1 and undetectable = 0. We propose an L1-penalized logistic regression model to classify each spectrum as positive (1) or negative (0) for HCV presence (x). The regularization parameter is selected using 5-fold cross-validation. The penalized model will induce sparsity in the solution so that only a few relevant wavelengths will be different from zero. Results: L1-penalized logistic regression model provided 167 wavelengths different from zero. The accuracy on an independent test set was 0.78. Conclusions: We present a straightforward promising approach to detect HCV positivity from patient serum samples combining NIRS and machine learning techniques. This result is encouraging to predict HCV progression, among other applications. Clinical relevance — We presented a simple while promising approach to use machine learning and NIRS to analyze viral presence on sample serums.
|
|
ThEP-02 |
Hall 5 |
Theme 01. EEG/MEG Signal Processing |
Poster Session |
|
15:45-17:30, Paper ThEP-02.1 | |
Cortical Entrainment to Speech Produced by Cochlear Implant Users and Normal-Hearing Talkers |
|
Raghavendra, Shruthi | Graduate Teaching Assistant, University of Texas at Dallas |
Lee, Sungmin | Faculty, Tongmyong University |
Chen, Fei | Southern University of Science and Technology |
Martin, Brett A | Associate Professor, Program in Speech-Language-Hearing Sciences |
Tan, Chin-Tuan | University of Texas, Dallas |
Keywords: Physiological systems modeling - Multivariate signal processing, Physiological systems modeling - Signal processing in physiological systems
Abstract: The perceived sound quality of speech produced by hard-of-hearing individuals greatly depends on the degree and configuration of their hearing loss. A cochlear implant (CI) may provide some compensation and auditory feedback to monitor/control speech production. However, to date, the speech produced by CI users is still different in quality from that produced by normal-hearing (NH) talkers. In this study, we attempted to address this difference by examining the cortical activity of NH listeners when listening to continuous speech produced by 8 CI talkers and 8 NH talkers. We utilized a discriminative model to decode and reconstruct the speech envelope from the single-trial electroencephalogram (EEG) recorded from scalp electrode in NH listeners when listening to continuous speech. The correlation coefficient between the reconstructed envelope and original speech envelope was computed as a metric to quantify the difference in response to the speech produced by CI and NH talkers. The same listeners were asked to rate the perceived sound quality of the speech as a behavioral sound quality assessment. Both behavioral perceived sound quality ratings and the cortical entrainment to speech envelope were higher for the speech set produced by NH talkers than for the speech set produced by CI talkers.
|
|
15:45-17:30, Paper ThEP-02.2 | |
A Novel Method for ECG Artifact Removal from EEG without Simultaneous ECG |
|
Isler, Joseph | Columbia University |
Pini, Nicolò | Columbia University Irving Medical Center |
Lucchini, Maristella | Columbia University Irving Medical Center |
Shuffrey, Lauren C. | Columbia University Medical Center |
Mitsuyama, Mai | Columbia University |
Welch, Martha | Columbia University |
Fifer, William P. | Department of Psychiatry and Pediatrics, Columbia University Col |
Stark, Raymond | Columbia University |
Myers, Michael | Columbia University Medical Center |
Keywords: Physiological systems modeling - Signal processing in physiological systems
Abstract: The electrocardiogram (ECG) is a common source of electrical artifact in electroencephalogram (EEG). Here, we present a novel method for removing ECG artifact that requires neither simultaneous ECG nor transformation of the EEG signals. The approach relies upon processing a subset of EEG channels that contain ECG artifact to identify the times of each R-wave of the ECG. Within selected brief epochs, data in each EEG channel is signal-averaged ± 60 ms around each R-wave to derive an ECG template specific to each channel. This template is subtracted from each EEG channel which are aligned with the R-waves. The methodology was developed using two cohorts of infants: one with 128-lead EEG including an ECG reference and another with 32-lead EEG without ECG reference. The results for the first cohort validated the methodology the ECG reference and the second demonstrated its feasibility when ECG was not recorded. This method does not require independent, simultaneous recording of ECG, nor does it involve creation of an artifact template based on a mixture of EEG channel data as required by other methods such as Independent Component Analysis (ICA). Spectral analysis confirms that the method compares favorably to results using simultaneous recordings of ECG. The method removes ECG artifact on an epoch by epoch level and does not require stationarity of the artifact. This approach facilitates the removal of ECG noise in frequency bands known to play a central role in brain mechanisms underlying cognitive processes.
|
|
15:45-17:30, Paper ThEP-02.3 | |
Comparison of MI-EEG Decoding in Source to Sensor Domain |
|
fang, tao | Fudan University |
Song, Zuoting | Fudan University |
Mu, Wei | Fudan University |
Le, Song | Fudan University |
Zhang, Yuan | Fudan University |
zhang, xueze | Fudan University |
zhan, gege | Fudan University |
Wang, Pengchao | Fudan University |
Wang, Junkongshuai | Fudan University |
Bin, Jianxiong | Ji Hua Laboratory |
Zhang, Fan | Imperial College London |
Zhang, Lihua | Fudan University |
Kang, Xiaoyang | Fudan University |
Keywords: Physiological systems modeling - Signal processing in physiological systems, Signal pattern classification
Abstract: Brain-computer interface (BCI) system based on sensorimotor rhythm (SMR) is a more natural brain-computer interaction system. In this paper, we propose a new multi-task motor imagery EEG (MI-EEG) classification framework. Unlike traditional EEG decoding algorithms, we perform the decoding task in the source domain rather than the sensor domain. In the proposed algorithm, we first build a conduction model of the signal using the publicly available ICBM152 head model and the boundary element method (BEM). The sensory domain EEG was then mapped to the selected cortex region using standardized low-resolution electromagnetic tomography (sLORETA) technology, addressing volume conduction effects. Finally, the source domain features are extracted and classified by combining FBCSP and simple LDA. The results show that the classification-decoding algorithm performed in the source domain can well solve the classification task of MI-EEG. In addition, we found that the source imaging method can significantly increase the number of available EEG channels, which can be expanded to at least double. The preliminary results of this study encourage the implementation of EEG decoding algorithms in the source domain.
|
|
15:45-17:30, Paper ThEP-02.4 | |
Methods Used to Estimate EEG Source-Space Networks: A Comparative Simulation-Based Study |
|
Allouch, Sahar | Univ Rennes, INSERM, LTSI - UMR 1099, F-35000 Rennes, France |
Duprez, Joan | Univ Rennes, INSERM, LTSI - UMR 1099, F-35000 Rennes, France |
Khalil, Mohamad | Lebanese University, Doctoral School for Sciences Andtechnology, |
Hassan, Mahmoud | Université De Rennes 1 |
Modolo, Julien | Univ Rennes, INSERM, LTSI-U1099 |
Kabbara, Aya | Lebanese Association for Scientific Research (LASeR) |
Keywords: Physiological systems modeling - Signal processing in simulation, Connectivity
Abstract: Along with the study of the brain activity evoked by external stimuli, an important advance in current neuroscience involves understanding the spontaneous brain activity that occurs during resting conditions. Interestingly, the identification of the connectivity patterns in "resting-state" has been the subject of a great number of electrophysiology- -based studies. In this context, the Electroencephalography (EEG) source connectivity method enables estimating resting-state cortical networks from scalp-EEG recordings. However, there is still no consensus over a unified pipeline adapted in all cases (e.g., type of task, a priori on studied networks) and numerous methodological questions remain unanswered. In order to address this problem, we simulated, using neural mass models, EEG data corresponding to the default mode network (DMN), the most widely studied resting-state network, and tested the effect of different channel densities, two inverse solutions and two functional connectivity measures on the correspondence between the reconstructed networks and the reference networks. Results showed that increasing the number of electrodes enhances the accuracy of the network reconstruction, and that eLORETA/PLV led to better accuracy than other inverse solution/connectivity measure combinations in terms of the correlation between reconstructed and reference connectivity matrices. This work has a wide range of implications in the field of electrophysiology connectomics, and is a step towards a convergence and standardization of approaches in this emerging field.
|
|
15:45-17:30, Paper ThEP-02.5 | |
An ICA-Based Framework for Joint Analysis of Cognitive Scores and MEG Event-Related Fields |
|
Boonyakitanont, Poomipat | Chulalongkorn University |
Gabrielson, Benjamin | University of Maryland, Baltimore County, MLSP Lab |
Belyaeva, Irina | University of Maryland, Baltimore County |
Sathishkumar Olikkal, Parthan | University of Maryland Baltimore County |
Songsiri, Jitkomut | Chulalongkorn University |
Wang, Yu-Ping | University of Missouri-Kansas City |
Wilson, Tony W | University of Nebraska Medical Center |
Calhoun, Vince D | Tri-Institutional Center for Translational Research in Neuroimag |
Stephen, Julia | The Mind Research Network |
Adali, Tulay | University of Maryland Baltimore County |
Keywords: Principal and independent component analysis - Blind source separation
Abstract: This paper proposes an independent component analysis (ICA)-based framework for exploring associations between neural signals measured with magnetoencephalography (MEG) and non-neuroimaging data of healthy subjects. Our proposed framework contains methods for subject group identification, latent source estimation of MEG, and discriminatory source visualization. Hierarchical clustering on principal components (HCPC) is used to cluster subject groups based on cognitive scores, and ICA is performed on MEG evoked responses such that not only higher-order statistics but also sample dependence is taken into account. The clustered subject labels and estimated sources are jointly analyzed to determine discriminatory sources. Finally, discriminatory sources are used to calculate global difference maps (GDMs) for the summary. Results using a new data set reveal that estimated sources are significantly correlated with cognitive measures and subject demographics. Discriminatory sources have significant correlations with variables that have not been previously used for group identification, and GDMs can effectively identify group differences.
|
|
15:45-17:30, Paper ThEP-02.6 | |
Transformer Convolutional Neural Networks for Automated Artifact Detection in Scalp EEG |
|
Peh, Wei Yan | Nanyang Technological University |
Yao, Yuanyuan | Delft University of Technology |
Dauwels, Justin | NTU |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Data mining and big data methods - Biosignal classification, Signal pattern classification
Abstract: It is well known that electroencephalograms (EEGs) often contain artifacts due to muscle activity, eye blinks, and various other causes. Detecting such artifacts is an essential first step towards correct interpretation of EEGs. Although much effort has been devoted to semi-automated and automated artifact detection in EEG, the problem of artifact detection remains challenging. In this paper, we propose a convolutional neural network (CNN) enhanced by transformers using belief matching (BM) loss for automated detection of five types of artifacts: chewing, electrode pop, eye movement, muscle, and shiver. Specifically, we apply these five detectors at individual EEG channels to distinguish artifacts from background EEG. Next, for each of these five types of artifacts, we combine the output of these channel-wise detectors to detect artifacts in multi-channel EEG segments. These segment-level classifiers can detect specific artifacts with a balanced accuracy (BAC) of 0.947, 0.735, 0.826, 0.857, and 0.655 for chewing, electrode pop, eye movement, muscle, and shiver artifacts, respectively. Finally, we combine the outputs of the five segment-level detectors to perform a combined binary classification (any kind of artifact vs.~background EEG). The resulting detector achieves a sensitivity (SEN) of 42.0%, 32.0%, and 13.3%, at a specificity (SPE) of 95%, 97%, and 99%, respectively. This artifact detection module can reject EEG artifacts while only removing a small fraction of the background EEG, leading to a cleaner EEG for further analysis.
|
|
15:45-17:30, Paper ThEP-02.7 | |
Exploration of the Severity of Hepatic Encephalopathy Deterioration Process through Dynamics of the EEG Band Power Time Series |
|
Braverman, Dalia | Universidad Iberoamericana |
Santana-Vargas, Daniel | Universidad Nacional Autónoma De México |
Bojorges-Valdez, Erik Rene | Universidad Iberoamericana A.C |
Keywords: Nonlinear dynamic analysis - Deterministic chaos, Physiological systems modeling - Signal processing in physiological systems, Coupling and synchronization - Coherence in biomedical signal processing
Abstract: Cirrhosis is a liver disease that could impair the functionality of the neural system, limiting cognitive processes and reduce mobility, possibly because alterations on dynamics of neural communications. In this study the dynamics of band power fluctuations on beta and gamma bands were studied on three groups: control, patients with cirrhosis and patients diagnosed with minimal hepatic encephalopathy. EEG signals were recorded on an oddball paradigm and analyzed to obtain the latency and amplitude of the P300 wave and Detrended Fluctuation Analysis (DFA) exponent values over beta and gamma band power time series for each channel. As expected, the latency of the P300 wave was significantly different for control subjects (p < 10−12). Amplitudes were not as different, but they tend to decrease for cirrhosis and minimal hepatic encephalopathy groups. DFA exponent values also tends to describe a more regular process and seems to be related with presence of symptoms of hepatic encephalopathy. These subtle changes could be produced by the mechanisms of a mild neurological impairment and be used, if it is confirmed, as an index to evaluate such deterioration.
|
|
ThEP-03 |
Hall 5 |
Theme 01. Signal Processing & Classification of Muscle and Motion Signals |
Poster Session |
Chair: Leonhardt, Steffen | RWTH Aachen University |
|
15:45-17:30, Paper ThEP-03.1 | |
Detection of Osteoarthritis from Multimodal Hand Data |
|
Andrade Guerreiro, Julian Jorge | Keio University |
Saito, Shuntaro | Division of Rheumatology, Department of Internal Medicine, Keio |
Suzuki, Katsuya | Keio University |
Aoki, Yoshimitsu | Keio University |
Keywords: Data mining and big data methods - Machine learning and deep learning methods, Data mining and big data methods - Pattern recognition, Neural networks and support vector machines in biosignal processing and classification
Abstract: Osteoarthritis (OA) describes a degenerative joint disorder that is prevalent among older people and typically results in swollen and inflamed joints. The aim of this paper is to develop a method using images, videos and thermal data of 100 patients taken at Keio University Hospital to detect OA in hands. By using hand pose estimation on the video data, joint angles can be calculated and subsequently transformed into feature vectors. For the thermal and RGB images, hand keypoint detectors were trained to identify and crop the appropriate joints within the images. The resulting extracted features are combined and further trained on Support Vector Machines and Convolutional Neural Networks to obtain the final binary classification for each joint. While the proposed method generally shows favorable accuracy and F1-scores on the Proximal (PIP) and Distal Interphalangeal (DIP) joints, the performance on the Metacarpophalangeal (MCP) joints is limited by the low occurrence of affected joints in the dataset. We further compare the different modalities and found that, apart from the combined approach, using video data provides the best results.
|
|
15:45-17:30, Paper ThEP-03.2 | |
Muscle Fatigue Analysis by Visualization of Dynamic Surface EMG Signals Using Markov Transition Field |
|
Sasidharan, Divya | APJ Abdul Kalam Kerala Technological University, N.S.S. College |
Gopinathakaimal, Venugopal | NSS College of Engineering, Palakkad |
Ramakrishnan, Swaminathan | IIT Madras, India |
Keywords: Nonlinear dynamic analysis - Biomedical signals, Signal pattern classification - Markov models, Physiological systems modeling - Signal processing in physiological systems
Abstract: Muscle fatigue analysis is important in the diagnosis of neuromuscular diseases. Analysis of surface electromyography (sEMG) signals by non-linear probabilistic approach is useful in studying their transitions and thus the neuromuscular system. In this study, a method to visualize sEMG signals using Markov transition field (MTF) under fatigue conditions is proposed. sEMG signals are acquired from 45 healthy participants during biceps curl exercise. They are filtered and divided into ten equal segments. Markov transition matrix is constructed and corresponding MTF image is generated. The average self-transition probability is extracted and compared for both non-fatigue and fatigue segments. It is observed that the extracted feature shows high statistical significance with p value less than 0.001. The increase in average self-transition probability under fatigue condition correlates with the reduction in the degree of signal complexity. Thus, encoding of sEMG signals to images is helpful in analyzing the complexity of the neuromuscular system.
|
|
15:45-17:30, Paper ThEP-03.3 | |
Comparison of Blind Source Separation Methods to Surface Electromyogram for Extensor Muscles of the Index and Little Fingers |
|
MAGBONDE, ABILE SERGE | Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab, 38000 Greno |
Quaine, Franck | Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab, 38000 Greno |
Rivet, Bertrand | Grenoble Universities |
Keywords: Principal and independent component analysis - Blind source separation
Abstract: Crosstalk is the result of the propagation of muscle electrical signals on surface electromyogram channels simultaneously. The objective of this paper is to study the behavior of three blind source separation (BSS) methods for crosstalk reduction during finger extensor muscle contractions: FastICA, joint diagonalization of covariance matrices and optimal filtering. These methods have been tested on artificial mixtures defined by a temporal sum of the real signals from isolated contraction of two independent biomechanical muscles for the extension of the index and little finger. Artificial mixtures display a ground truth for comparison between the methods. The separation was better using the optimal filtering compared to the other two methods. The optimal filtering have then be tested on real mixtures recorded during a simultaneous contraction of the two muscles. The results are less satisfactory but open doors to new perspectives.
|
|
15:45-17:30, Paper ThEP-03.4 | |
EMG Data Augmentation for Grasp Classification Using Generative Adversarial Networks |
|
Vincent Mendez, Vincent | Ecole Polytechnique Fédérale De Lausanne |
Lhoste, Clément | EPFL |
Micera, Silvestro | Scuola Superiore Sant'Anna |
Keywords: Signal pattern classification, Data mining and big data methods - Machine learning and deep learning methods, Data mining and big data methods - Biosignal classification
Abstract: Electromyography (EMG) has been used as an interface for the control of robotic hands for decades but with the improvement of embedded electronics and decoding algorithms, many applications are now envisaged by companies. Deep learning has shown the possibility to increase decoding performance but it requires large amounts of data to show its full capabilities. However, recording such amounts of EMG signals face several issues since recording hours of data from patients is very time-consuming and can result in muscle fatigue. We explore a deep learning data augmentation strategy using generative adversarial networks (GANs) to create high-quality synthetic data to increase the performance of grasp classification. Clinical Relevance— This approach can increase the decoding performance of already existing decoding algorithms for patients with an amputation and suggests the possibility to increase the protection of personal data when recorded at a larger scale.
|
|
15:45-17:30, Paper ThEP-03.5 | |
Investigation of Muscle Fatigue During On-Water Rowing Using Surface EMG |
|
Schwensow, Daniel | TU Dresden |
Hohmuth, Richard | TU Dresden |
Malberg, Hagen | Dresden Technical University |
Schmidt, Martin | TU Dresden |
Keywords: Time-frequency and time-scale analysis - Time-frequency analysis, Signal pattern classification, Time-frequency and time-scale analysis - Wavelets
Abstract: In this work, four different algorithms (fast Fourier transform FFT, short-time Fourier transform STFT, continuous wavelet transform CWT, and instantaneous frequency IF) for calculating median frequency (MDF) from surface EMG signals were investigated for studying muscle fatigue during a on-water rowing training. The study protocol included 5 consecutive parts with increasing stroke rate. Six athletes participated in the study aged 36.6 ± 14.6 years and a rowing experience of 6 to 35 years. We considered eight muscles: biceps brachii right, biceps brachii left, latissimus dorsi right, latissimus dorsi left, erector spinae right, erector spinae left, rectus femoris and biceps femoris. By applying Friedmann test, we found a significant difference in MDF behavior between algorithms in assessing muscle fatigue (p<0.05). Correlation analyses showed significant correlations between muscle activity duration and MDF, which differs for the four considered algorithms and should be taken into account in further experiments. With CWT showing the smallest correlation to activity duration it might be more robust against time window variations. Our study provides a basis for the development of improved methods for more robust, non-invasive, and continuous detection of muscle fatigue in experiments with dynamic on-water rowing study designs.
|
|
15:45-17:30, Paper ThEP-03.6 | |
Optimised EMG Pipeline for Gesture Classification |
|
Warner, Jarlath | Queen's University, Belfast |
Gault, Richard | Queen's University, Belfast |
McAllister, John | Queen's University, Belfast |
Keywords: Data mining and big data methods - Biosignal classification, Signal pattern classification, Principal component analysis
Abstract: In the expanding field of robotic prosthetics, surface electromyography (sEMG) signals can be decoded to seamlessly control a robotic prosthesis to perform the desired gesture. It is essential to create a pipeline, which can acquire, process, and accurately classify sEMG signals in order to replicate the desired hand gesture in near real-time and in a reliable manner. In this study, an optimised pipeline is proposed. This pipeline encompasses the main stages of sEMG signal processing and hand gesture classification and implements a sliding window approach, which is the main focus of the optimisation. In this study, a range of different parameters and modelling approaches are evaluated. The main contributions of this work are a robust and extensive analysis of sliding window parameter selection and an optimised pipeline that could be implemented in practice with minimal overheads. The optimum pipeline is efficient and achieves accurate prediction of hand gestures with an uninterrupted processing pipeline.
|
|
15:45-17:30, Paper ThEP-03.7 | |
Classification-Guided Neural Network-Based Correction of Magnetic Resonance-Related Gradient Artifact Residuals in Simultaneously Recorded Surface Electromyography |
|
Schwartz, Martin | University of Tübingen |
Yang, Bin | Institute of Signal Processing and System Theory, University Of |
Schick, Fritz | Department of Diagnostic and Interventional Radiology, Universit |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Signal pattern classification, Time-frequency and time-scale analysis - Empirical mode decomposition in biosignal analysis
Abstract: Spontaneous muscular activities can be studied by simultaneous recordings of surface electromyography (sEMG) and diffusion-weighted magnetic resonance imaging (DW-MRI). For reliable assessment of the spontaneous activity rate in sEMG data during active MR imaging, it is necessary to have a decent gradient artifact (GA) correction algorithm enabling the detection of small spontaneous activities with an amplitude of few microvolts. In this work, a neural network with weak label annotations during the training process is utilized for enhanced correction of GA residuals in the sEMG recordings. Based on sEMG signal decomposition and class-activation maps from the neural network classification, the amount of GA residuals is iteratively decreased in the sEMG signal. This leads to a reduction of the false-positive rate in automated spontaneous activity detection. Quality of GA residual correction is therefore estimated by using a specialized second neural network model.
|
|
15:45-17:30, Paper ThEP-03.8 | |
Actor-Critic Reinforcement Learning Based Algorithm for Contaminant Minimization in sEMG Movement Recognition |
|
Tosin, Maurício C | UFRGS |
Bagesteiro, Leia B | San Francisco State University |
Balbinot, Alexandre | Federal University of Rio Grande Do Sul (UFRGS) |
Keywords: Signal pattern classification, Data mining and big data methods - Biosignal classification, Physiological systems modeling - Closed loop systems
Abstract: This paper aims to present an approach based on Reinforcement Learning (RL) concept to detect contaminants’ type and minimize their effect on surface electromyography signal (sEMG) based movement recognition. The referred method was applied in the pre-processing stage of a sEMG based motion classification system using the Ninapro database 2 artificially contaminated with electrocardiography (ECG) interference, motion artifact (MOA), powerline interference (PLI) and additive white Gaussian noise (WGN). Support Vector Machine was the method for movement classification. The results showed an improvement of 8.9%, 16.7%, 15.9%, 16.5%, and 11.9% in the movement recognition accuracy with the application of the pre-processing algorithm to restore, respectively, 1, 3, 6, 9, and 12 contaminated channels.
|
|
15:45-17:30, Paper ThEP-03.9 | |
On Selection of Threshold Values for Symbolic Entropy Analysis of Human Gait |
|
Abbasi, Anees Qumar | Karlsruhe Institute of Technology |
Abbasi, Mohsin Manshad | University of AJ&K |
Nahm, Werner | Karlsruhe Institute of Technology |
Keywords: Physiological systems modeling - Signal processing in physiological systems, Nonlinear dynamic analysis - Biomedical signals, Physiological systems modeling - Multivariate signal processing
Abstract: Human gait is a complex system affected by many other processes of human physiology. It has multiple inputs and multiple outputs. Due to its complex nature,signals obtained from this system also exhibit complexity and variability. It has been analyzed in many ways to extract the information inhabited by these signals. Entropy based methods showed a significant impact on analysis of gait signals. Threshold based symbolic entropy analysis is one of the entropy based method applied to human gait signals. In this method Normalized Corrected Shannon Entropy (NCSE) is calculated to compare the spontaneous output of the human locomotors system during different walking conditions. Selection of the threshold values is an important task and sometimes it depends upon the type and size of the data. Results are dependent on the proper selection of the threshold. In this paper, different threshold selection methods are discussed and their impact on the results are presented. It was observed that, variation in stride interval has performed better as a threshold value as compare to the other methods. It provided maximum separation among different groups of gait data used in this study. We concluded with the recommendations for the proper selection of the threshold values to apply symbolic entropy methods on human gait signals.
|
|
15:45-17:30, Paper ThEP-03.10 | |
Walking and Running Cadence Estimation Using a Single Trunk-Fixed Accelerometer for Daily Physical Activities Assessment |
|
Prigent, Gaelle | EPFL |
Barthelet, Estelle | EPFL |
Paraschiv-Ionescu, Anisoara | Ecole Polytechnique Federale |
Aminian, Kamiar | Ecole Polytechnique Federale De Lausanne |
Keywords: Physiological systems modeling - Signal processing in physiological systems, Nonlinear dynamic analysis - Biomedical signals, Time-frequency and time-scale analysis - Wavelets
Abstract: Accurate assessment of the type, duration, and intensity of physical activity (PA) in daily life is considered very important because of the close relationship between PA level, health, and well-being. Therefore, the assessment of PA using lightweight wearable sensors has gained interest in recent years. In particular, the use of activity monitors could help to measure the health-related effects of specific PA interventions. Our study, named as Run4Vit, focuses on evaluating the acute and long-term effects of an eight-week running intervention on PA behavior and vitality. To achieve this goal, we developed an algorithm to detect running and estimate instantaneous cadence using a single trunk-fixed accelerometer. Cadence was estimated using time and frequency domain approaches. Validation was performed over a wide range of locomotion speeds using an open-source gait database. Across all subjects, the cadence estimation algorithms achieved a mean bias and precision of -0.01 ± 0.69 steps/min for the temporal method and 0.02 ± 1.33 steps/min for the frequency method. The running detection algorithm demonstrated very good performance, with an accuracy of 98% and a precision superior to 99%. These algorithms could be used to extract metrics related to the multiple dimensions of PA, and provide reliable outcome measures for the Run4Vit longitudinal running intervention program.
|
|
15:45-17:30, Paper ThEP-03.11 | |
Musculoskeletal Synergies in the Grasping Hand |
|
Sathishkumar Olikkal, Parthan | University of Maryland Baltimore County |
Pei, Dingyi | University of Maryland Baltimore County |
Adali, Tulay | University of Maryland Baltimore County |
Banerjee, Nilanjan | University of Maryland Baltimore County |
Vinjamuri, Ramana | University of Maryland Baltimore County |
Keywords: Principal component analysis
Abstract: Investigations on how the central nervous system (CNS) effortlessly conducts complex hand movements have led to an extensive study of synergies or movement primitives. Of the different types of hand synergies, kinematic and muscle synergies have been widely studied in literature, but only a few studies have fused both. In this paper kinematic and muscle activities recorded from the activities of daily living were first fused and then dimensionally reduced through principal component analysis (PCA). By using these principal components or musculoskeletal synergies in a weighted linear combination, the recorded kinematics and muscle activities were reconstructed. The performance of these musculoskeletal synergies in reconstructing the movements was compared to the kinematic and muscle synergies reported previously in the literature by us and others. The results from these findings indicate that musculoskeletal synergies perform better than the synergies extracted without fusion. These newly demonstrated musculoskeletal synergies might improve neural control of robotics, prosthetics and exoskeletons.
|
|
15:45-17:30, Paper ThEP-03.12 | |
Using Synthesized IMU Data to Train a Long-Short Term Memory-Based Neural Network for Unobtrusive Gait Analysis with a Sparse Sensor Setup |
|
Lueken, Markus | RWTH Aachen |
Wenner, Joshua | RWTH Aachen University |
Leonhardt, Steffen | RWTH Aachen University |
Ngo, Chuong | RWTH Aachen University |
Keywords: Neural networks and support vector machines in biosignal processing and classification, Physiological systems modeling - Signal processing in simulation, Data mining and big data methods - Machine learning and deep learning methods
Abstract: Abstract - In this work, we evaluated the possibility to use synthesized IMU data for training a deep neural network to generate a more complex, full-body description of the human gait in terms of joint angle trajectories from a sparse sensor setup. In this context, a sparse sensor setup consists of a few sensors attached to human body segments in an unobtrusive manner to possibly provide a monitoring system in an everyday life scenario. Since the relation between the input IMU data and the output joint angle trajectories is highly non-linear, neural networks appear to provide an optimal framework to formulate a mapping description. Especially with respect to periodic signals, recurrent neural networks (RNNs) have gained importance in the recent years. In this work, we have used a special type of RNNs that can be implemented by using long-short term memory (LSTM) cells, which have shown promising results when being applied to sequential data. The artificial training data was generated by a simulative human gait model and virtually attached sensor devices. The trained network was subsequently validated by a dataset that was recorded from a treadmill walking trial using a motion capturing system and an IMU sensor system. The qualitative comparison already shows promising results, however, this study can only be considered to provide preliminary results in this area. Clinical relevance - This approach has the potential to be applied in the remote assessment of gait behavior during everyday life environments using an unobtrusive sensor network. In particular for monitoring older people suffering from an increased fall risk or any significant gait impairments, this work is of possible interest.
|
|
ThEP-04 |
Hall 5 |
Theme 01. Signal Processing and Classification for Wearable Systems |
Poster Session |
Chair: Subramanian, Sandya | Stanford University |
|
15:45-17:30, Paper ThEP-04.1 | |
Development of a Real-Time Chronic Stress Visualization System from Long-Term Physiological Data |
|
Kitade, Tasuku | NEC Corporation |
Tsujikawa, Masanori | NEC Corporation |
Keywords: Signal pattern classification
Abstract: We have developed a real-time system which can estimate and display chronic stress levels determined from a long-term physiological data. It consists of wearable sensors that measure physiological data, a smartphone application that receives data from the sensors and displays chronic stress levels, and a cloud system that estimates them on the basis of received data. To operate it, we have to treat irregularly uploaded user- physiological-data of varying sizes, calculate chronic stress levels from long-term features without delay on a daily basis, and display them in real-time on the smartphone application. For this purpose, we have developed a system that requires relatively little memory and processing time with one six-hundredth of maximum memory usage and one twentieth of processing time as compared to conventional method by subdividing uploaded physiological data, calculating features from them, and creating long-term features by combining the subdivided features.
|
|
15:45-17:30, Paper ThEP-04.2 | |
A Comparative Study on Recognizing Human Activities Applying Diverse Machine Learning Approaches |
|
Pappa, Lamprini | University of Ioannina |
Karvelis, Petros | University of Ioannina |
Stylios, Chrysostomos | Technological Educational Institute of Epirus |
Keywords: Signal pattern classification
Abstract: This paper deals with the problem of identifying and recognizing everyday human activities. The main goal is to compare a variety of implemented classification models founded on diverse machine learning approaches; one that utilizes features extracted from the time and frequency domain and three others that take advantage of the attributes of the symbolic space in order to extract conclusions regarding the performance and the potential usefulness of each of them. To guarantee the impartiality of the comparison, we used the signals contained in a free accessible dataset, which are subjected to the same preprocessing, and divided into equal time-length windows. The Nearest Neighour classifier is applied to compare the four approaches.
|
|
15:45-17:30, Paper ThEP-04.3 | |
Automated Classification of Sleep and Wake from Single Day Triaxial Accelerometer Data |
|
Subramanian, Sandya | Stanford University |
Coleman, Todd | UCSD |
Keywords: Signal pattern classification - Markov models, Physiological systems modeling - Signal processing in physiological systems, Data mining and big data methods - Biosignal classification
Abstract: Actigraphy allows for the remote monitoring of subjects’ activity for clinical and research purposes. However, most standard methods are built for proprietary measures from specific devices that are not widely used. In this study, we develop an algorithm for classifying sleep and awake using a single day of triaxial accelerometer data, which can be acquired from all smart devices. This algorithm consists of two stages, clustering and hidden Markov modeling, and outperforms standard algorithms in sensitivity (94%), specificity (93%), and overall accuracy (93%) across seven subjects. This method can help automate actigraphy analyses at scale using widely available technology using even a single day’s worth of data. Clinical Relevance— Automated monitoring of patients’ activity at home can help track recovery trajectories after surgery and injury, disease progression, and treatment response.
|
|
15:45-17:30, Paper ThEP-04.4 | |
Estimation of Temporal Parameters During Running with a Wrist-Worn Inertial Sensor: An In-Field Validation |
|
Kammoun, Nathan | EPFL |
Apte, Salil | Ecole Polytechnique Federale De Lausanne |
Karami, Hojjat | Swiss Federal Institute of Technology Lausanne (École Polytechni |
Aminian, Kamiar | Ecole Polytechnique Federale De Lausanne |
Keywords: Signal pattern classification, Data mining and big data methods - Machine learning and deep learning methods, Data mining and big data methods - Inter-subject variability and personalized approaches
Abstract: The aim of this study was to estimate the temporal gait parameters using a wrist-worn Inertial Measurement Unit (IMU) during an outdoor run. While it is easier to compute running gait parameters using foot IMUs, a wrist IMU is more convenient and less obtrusive when it comes to data acquisition. During a track run of 12 minutes, we equipped 14 highly-trained male runners with one IMU on the wrist and one on each foot. We trained machine learning models based on CNN, GPR, and Lasso regression using wrist IMU signals and validated them with a foot-worn IMU reference system. Lasso model performed the best, with the accuracy for cycle time, swing time, flight time, and contact time being 0.27 % ± 0.1 %, 2.6 % ± 1.7 %, 7.3 % ± 4.9 %, and 10.6 % ± 5.5 %, respectively.
|
|
ThEP-05 |
Hall 5 |
Theme 01. Time-Frequency and Time-Scale Analysis of Biosignals |
Poster Session |
Chair: Cheng, Leo K | The University of Auckland |
|
15:45-17:30, Paper ThEP-05.1 | |
A Pursuit of the Degree of Nonlinearity for β Oscillations under Motor Imagery |
|
Xu, Wenbin | Beijing Institute of Technology |
Yeh, Chien-Hung | Beijing Institute of Technology |
Shi, Wenbin | Beijing Institute of Technology |
Keywords: Nonlinear dynamic analysis - Biomedical signals, Time-frequency and time-scale analysis - Empirical mode decomposition in biosignal analysis, Physiological systems modeling - Signal processing in physiological systems
Abstract: The power of β oscillations is an essential pathological biomarker for movement disorders, parkinsonism in particular. Motor imagery training was reported to support self-regulate such β oscillations. Past studies had focused on the modulation of β oscillatory power per se, ignoring the intrinsic oscillatory characteristics—the nonlinearity of the waveform. This work applied ensemble empirical mode decomposition to decompose neural activities in multiple frequency bands without destroying the temporal characteristics of the raw signal at all scales. We explored the dynamics of the degree of nonlinearity plus the averaged power across all periods and frequency bands of interest and tested how motor imagery may or may not induce nonlinearities under various frequency bands. With motor imagery, the degree of nonlinearity for the β activity is significantly suppressed referenced to that without, of note, and the average power fails to present significant differences between segments with and without motor imagery training. Our results indicate that the degree of nonlinearity is a complementary and vital biomarker as the average power for β oscillations, thereby providing theoretical support for the possible application in motor imagery therapy.
|
|
15:45-17:30, Paper ThEP-05.2 | |
N170 Component Analysis of Single-Trial EEG Based on Electrophysiological Source Imaging |
|
Wang, Pengchao | Fudan University |
Mu, Wei | Fudan University |
zhan, gege | Fudan University |
Song, Zuoting | Fudan University |
fang, tao | Fudan University |
zhang, xueze | Fudan University |
Wang, Junkongshuai | Fudan University |
Niu, Lan | Ji Hua Laboratory |
Bin, Jianxiong | Ji Hua Laboratory |
Zhang, Fan | Imperial College London |
Zhang, Lihua | Fudan University |
JIA, JIE | Huashan Hospital Fudan University |
Kang, Xiaoyang | Fudan University |
Keywords: Nonlinear dynamic analysis - Biomedical signals, Time-frequency and time-scale analysis - Time-frequency analysis, Independent component analysis
Abstract: Event-related potentials (ERP) are brain-evoked potentials that reflect the neural activity of the brain. However, it is difficult to isolate the ERP components of our interest because single-trial EEG is disturbed by other signals, and the average ERP analysis in turn loses single-trial information. In this paper, we used electrophysiological source imaging (ESI) to analyze the N170 component of single-trial EEG triggered by face stimulation. The results show that ESI is feasible for the analysis of N170 and that there are left-right differences in the area of the fusiform gyrus associated with face stimulation in the brain.
|
|
15:45-17:30, Paper ThEP-05.3 | |
In Vivo Multi-Channel Measurement of Electrical Activity of the Non-Pregnant Rat Uterus |
|
Garrett, Amy | The University of Auckland |
Roesler, Mathias William | The University of Auckland |
Athavale, Omkar Nitin | The University of Auckland |
Du, Peng | The University of Auckland |
Clark, Alys | The University of Auckland |
Cheng, Leo K | The University of Auckland |
Keywords: Physiological systems modeling - Signal processing in physiological systems, Time-frequency and time-scale analysis - Wavelets
Abstract: In the uterus, the characteristics of smooth muscle contraction and the electrical activity that drives this contraction depends on hormonal cycles, and pregnancy status. Smooth muscle contraction is initiated by a change in membrane electrical potential, due to the flux of ions in and out of the intracellular space. Chains of action potentials throughout a section of muscle can result in coordinated contraction events. In this study, flexible printed circuit electrode arrays were applied to measure the bioelectric signals on the surface of a rat uterus in vivo. Variations in the electrical activity were quantified, including intermittent periods of activity and inactivity, which contain both slow-wave type activity (0.039 Hz ± 0.017 Hz) and faster, spike-like activity (3.26 Hz ± 0.27 Hz). The spike activity initiated at the ovarian end of the uterine horn, spreading towards the cervical end with a propagation velocity of 5.34 ± 2.32 mm s-1. In conclusion, this pilot study outlines a new method of in vivo measurement of uterine electrical activity in rats.
|
|
15:45-17:30, Paper ThEP-05.4 | |
PySio: A New Python Toolbox for Physiological Signal Visualization and Feature Analysis |
|
Nacitarhan, Ozgun Ozan | Koc University |
Semiz, Beren | Koc University |
Keywords: Physiological systems modeling - Signal processing in physiological systems, Nonlinear dynamic analysis - Biomedical signals, Time-frequency and time-scale analysis - Time-frequency analysis
Abstract: In physiological signal analysis, identifying meaningful relationships and inherent patterns in signals can provide valuable information regarding subjects' physiological state and changes. Although MATLAB has been widely used in signal processing and feature analysis, Python has recently dethroned MATLAB with the rise of data science, machine learning and artificial intelligence. Hence, there is a compelling need for a Python package for physiological feature analysis and extraction to achieve compatibility with downstream models often trained in Python. Thus, we present a novel visualization and feature analysis Python toolbox, PySio, to enable rapid, efficient and user-friendly analysis of physiological signals. First, the user should import the signal-of-interest with the corresponding sampling rate. After importing, the user can either analyze the signal as it is, or can choose a specific region for more detailed analysis. PySio enables the user to (i) visualize and analyze the physiological signals (or user-selected segments of the signals) in time domain, (ii) study the signals (or user-selected segments of the signals) in frequency domain through discrete Fourier transform and spectrogram representations, and (iii) investigate and extract the most common time (energy, entropy, zero crossing rate and peaks) and frequency (spectral entropy, rolloff, centroid, spread, peaks and bandpower) domain features, all with one click.
|
|
15:45-17:30, Paper ThEP-05.5 | |
Class-Distinctiveness-Based Frequency Band Selection on the Riemannian Manifold for Oscillatory Activity-Based BCIs: Preliminary Results |
|
Yamamoto, Maria Sayu | University Paris-Saclay |
Lotte, Fabien | Inria Bordeaux Sud-Ouest |
Yger, Florian | LAMSADE - PSL Université Paris-Dauphine |
Chevallier, Sylvain | Université Paris-Saclay, UVSQ, LISV, |
Keywords: Data mining and big data methods - Inter-subject variability and personalized approaches, Physiological systems modeling - Signal processing in physiological systems, Time-frequency and time-scale analysis - Time-frequency analysis
Abstract: Considering user-specific settings is known to enhance Brain-Computer Interface (BCI) performances. In particular, the optimal frequency band for oscillatory activity classification is highly user-dependent and many frequency band selection methods have been developed in the past two decades. However, it is not well studied whether those conventional methods can be efficiently applied to the Riemannian BCIs, a recent family of BCI systems that utilize the non-Euclidean nature of the data unlike conventional BCI pipelines. In this paper, we proposed a novel frequency band selection method working on the Riemannian manifold. The frequency band is selected considering the class distinctiveness as quantified based on the inter-class distance and the intra-class variance on the manifold. An advantage of this method is that the frequency bandwidth can be adjusted for each individual without intensive optimization steps. In a comparative experiment using a public dataset of motor imagery-based BCI, our method showed a substantial improvement in average accuracy over both a fixed broad frequency band and a popular conventional frequency band selection method. In particular, our method substantially improved performances for subjects with initially low accuracies. This preliminary result suggests the importance of developing new user-specific setting algorithms considering the manifold properties, rather than directly applying methods developed prior to the rise of the Riemannian BCIs.
|
|
15:45-17:30, Paper ThEP-05.6 | |
Multivariate Empirical Mode Decomposition of EEG for Mental State Detection at Localized Brain Lobes |
|
Islam, Monira | The Chinese University of Hong Kong |
Lee, Tan | The Chinese University of Hong Kong |
Keywords: Time-frequency and time-scale analysis - Empirical mode decomposition in biosignal analysis, Time-frequency and time-scale analysis - Time-frequency analysis, Neural networks and support vector machines in biosignal processing and classification
Abstract: In this study, the Multivariate Empirical Mode Decomposition (MEMD) approach is applied to extract features from multi-channel EEG signals for mental state classification. MEMD is a data-adaptive analysis approach which is suitable particularly for multi-dimensional non-linear signals like EEG. Applying MEMD results in a set of oscillatory modes called intrinsic mode functions (IMFs). As the decomposition process is data-dependent, the IMFs vary in accordance with signal variation caused by functional brain activity. Among the extracted IMFs, it is found that those corresponding to high-oscillation modes are most useful for detecting different mental states. Non-linear features are computed from the IMFs that contribute most to mental state detection. These MEMD features show a significant performance gain over the conventional tempo-spectral features obtained by Fourier transform and Wavelet transform. The dominance of specific brain region is observed by analysing the MEMD features extracted from associated EEG channels. The frontal region is found to be most significant with a classification accuracy of 98.06%. This multi-dimensional decomposition approach upholds joint channel properties and produces most discriminative features for EEG based mental state detection.
|
|
15:45-17:30, Paper ThEP-05.7 | |
The Effectiveness of Narrowing the Window Size for LD & HD EMG Channels Based on Novel Deep Learning Wavelet Scattering Transform Feature Extraction Approach |
|
Al Taee, Ahmed | Charles Stuart University |
Khushaba, Rami N. | The University of Sydney |
Al-Jumaily, Adel | Charles Sturt University |
Tanveer Zia, Tanveer | Charles Sturt University |
Keywords: Time-frequency and time-scale analysis - Empirical mode decomposition in biosignal analysis, Time-frequency and time-scale analysis - Wavelets, Time-frequency and time-scale analysis - Time-frequency analysis
Abstract: One of the most useful biomedical signals is the electromyogram (EMG) signal. However, employing an EMG signal as a diagnostic or control signal with high classification accuracy is challenging due to its complexity and non-stationary behaviour. Mainly, two factors affect classification accuracy: selecting the optimum feature extraction methods and overlapping segmentation/window size. Nowadays, studies attempt to use deep learning methods to improve classification accuracy. Although deep learning models provide promising outcomes, they are frequently hampered by their requirements of a vast quantity of training data to attain decent performance and the high computing costs. Therefore, researchers tried to replace the deep learning models with other low computational cost methods like deep wavelet scattering transform (DWST) as a feature extraction technique. In terms of windows size, selecting a larger window size increases the classification accuracy, but at the same time, it increases the processing time, which makes the system unsuitable for real-time applications. Accordingly, researchers attempted to minimise the size of the overlapping windows as much as possible without impacting classification performance. This work efforts to utilise DWST transform to achieve two goals (a) extracting the features from EMG signal with low computational cost. Even though many studies have used DWST approaches to extract features from other biological signals, but not been examined before for EMG signals. (b) study the effect of extracting the features from high-density EMG datasets (HD EMG) and low-density EMG datasets (LD EMG) with significant reductions in an analysis window size of up to 32msec with minimal impact on classification performance. The outcomes of the proposed method are compared with other well-known feature extraction algorithms to validate these achievements. The proposed strategy exceeds others methods of more than 25% inaccuracy.
|
|
15:45-17:30, Paper ThEP-05.8 | |
Changes in EEG Measures of a Recipient of the mRNA COVID-19 Vaccine – a Case Study |
|
Uudeberg, Tuuli | Tallinn University of Technology |
Hinrikus, Hiie | Tallinn University of Technology |
Päeske, Laura | Department of Health Technologies, School of Information Technol |
Lass, Jaanus | Tallinn University of Technology |
Bachmann, Maie | Tallinn University of Technology |
Keywords: Time-frequency and time-scale analysis - Empirical mode decomposition in biosignal analysis
Abstract: Abstract:— The current study is aimed to evaluate the effect of COVID-19 vaccine on human EEG and the persistence of the effect. Within a one-year-long resting EEG study period, the healthy male subject was administered two Comirnaty doses three weeks apart to prevent COVID-19. Fourteen recordings were acquired from the subject in one year: twelve reference and two post-vaccination recordings after administrating the second dose of Comirnaty. The changes in absolute powers of EEG frequency bands, EEG spectral asymmetry index (SASI), and Higuchi’s fractal dimension (HFD) were analyzed. The results indicated a statistically significant increase in absolute gamma power, SASI and HFD values on the fifth day after the vaccination, while the EEG had restored its normal character on the twelfth day after vaccination. These measures seem to have higher sensitivity for the detection of the effects of the vaccine Clinical Relevance – This is the first study evaluating COVID-19 vaccine effect on healthy human EEG. The study indicated that the vaccine disturbs EEG, but the impact is not long-lasting.
|
|
15:45-17:30, Paper ThEP-05.9 | |
Involvement of the Anterior Nucleus of the Thalamus During Focal Automatisms in Epileptic Seizures: A First Evidence Study |
|
Lopes, Elodie M. | INESC TEC and Faculty of Engineering, University of Porto, Portu |
Sampaio, Ana R. | INESC TEC and Faculty of Engineering, University of Porto, Portu |
Campos, António | Neurology Department, Centro Hospitalar Vila Nova De Gaia, Gaia, |
Santos, Angela | Neurophysiology Unit Neurology Department, Centro Hospitalar Uni |
Rego, Ricardo | Neurophysiology Unit Neurology Department, Centro Hospitalar Uni |
Cunha, Joao Paulo Silva | INESC TEC / University of Porto |
Keywords: Time-frequency and time-scale analysis - Time-frequency analysis, Time-frequency and time-scale analysis - Wavelets, Physiological systems modeling - Closed loop systems
Abstract: The Anterior Nucleus of Thalamus (ANT) Deep Brain Stimulation (DBS) has long been touted as the most effective DBS-target for interrupting seizures in focal refractory epilepsy patients. The ANT is primarily involved in cognitive tasks but has extensive reciprocal connections with motor-related regions, suggesting that it is also involved in motor-cognitive tasks. In this work, we aimed to assess the involvement of the ANT during voluntary upper limbs movements. For this purpose, we analyzed Local Field Potentials (LFPs) signals recorded during a movement protocol from one of the first epilepsy patients implanted with a PerceptTM PC system, who performed a 5-day period of simultaneous video electroencephalography (vEEG) and Percept PC-LFPs recordings. We estimated time-frequency maps and performed event-related desynchronization (ERD) or synchronization (ERS) analysis and we found that synchronizations found in left hemisphere 7-17 Hz map corresponded to maximum hand rotations. Positive peaks on the ERD/ERS curve occurred at a similar frequency of the hand movements (1.09±0.99 Hz against 1.27±0.90 Hz). These results suggested that the ANT may be involved in the execution of automatisms. Moreover, we found that ERD/ERS appeared approximately 2 seconds before the movement onset, as it was found on the EEG of healthy subjects performing the same protocol.
|
|
15:45-17:30, Paper ThEP-05.10 | |
Comparison of Different Emotion Stimulation Modalities: An EEG Signal Analysis |
|
Farabbi, Andrea | Politecnico Di Milano |
Polo, Edoardo Maria | Sapienza, University of Rome |
Barbieri, Riccardo | Politecnico Di Milano |
Mainardi, Luca | Politecnico Di Milano |
Keywords: Time-frequency and time-scale analysis - Time-frequency analysis, Physiological systems modeling - Signal processing in physiological systems
Abstract: Emotions processing is a complex mechanism that involves different physiological systems. In particular, the Central Nervous System (CNS) is considered to play a key role in this mechanism and one of the main modalities to study the CNS activity is the Electroencephalographic signal (EEG). To elicit emotions, different kinds of stimuli can be used e.g.: audio, visual or a combination of the two. Literature studies focus more on the correct classification of the different types of emotions or which kind of stimulation gives the best performance in terms of classification accuracy. However, it is still unclear how the different stimuli elicit the emotions and which are the results in terms of brain activity. In this paper, we analysed and compared EEG signals given by eliciting emotions using audio and visual stimuli or a combination of the latter two. Data were collected during experiments conducted in our laboratories using IAPS and IADS dataset. Our study confirmed literature physiological studies about emotions highlighting higher brain activity in the frontal and central regions and in the δ and θ bands for each kind of stimulus. However, audio stimulation was found to have higher responses when compared to the other two modalities of stimulation in almost all the comparisons performed. Higher values of the δ/β ratios, an index related to negative emotions, have been achieved when using only sounds as stimuli. Moreover, the same type of stimuli, resulted in higher δ-β coupling, suggesting a better attention control. We concluded that stimulating subjects without letting them know (seeing) what is actually happening may give a higher perception of emotions, even if this mechanism remains highly subjective.
|
|
15:45-17:30, Paper ThEP-05.11 | |
Validation of an EEG-Based Neurometric for Online Monitoring and Detection of Mental Drowsiness While Driving |
|
Ronca, Vincenzo | Sapienza University of Rome |
Di Flumeri, Gianluca | University of Rome Sapienza |
Vozzi, Alessia | Sapienza University of Rome |
Giorgi, Andrea | Sapienza University of Rome |
Arico, Pietro | Sapienza University of Rome |
Sciaraffa, Nicolina | BrainSigns Srl, Rome |
Babiloni, Fabio | University of Rome |
Borghini, Gianluca | Sapienza University of Rome |
Keywords: Time-frequency and time-scale analysis - Time-frequency analysis, Physiological systems modeling - Signal processing in physiological systems
Abstract: The driving drowsiness has been identified as one of the major causes of road traffic accidents, causing fatalities and permanent injuring. Drowsy drivers are prone to suddenly lose control of the car, mostly without any prior behavioral cue. The present study involved 19 participants in a simulated driving protocol, designed to induce mental drowsiness into the drivers. The objective of the study consisted in testing an innovative Electroencephalographic (EEG)-based index, the MDrow index, in detecting the driving drowsiness. Such an index, derived from parietal EEG channels, was already validated in our previous work achieving outstanding performance with respect to more conventional techniques. In this study, the possibility of obtaining a similar index from the frontal sites in order to foster its exploitation in real environments has been investigated. The results demonstrated the capability of the “frontal” MDrow index in evaluating the driving drowsiness experienced by the participants with performance comparable to that one previously validated over parietal sites. Also, the impact of the reduction of the electrodes number on index reliability has been investigated, in order to evaluate its compatibility with current wearable EEG devices.
|
|
15:45-17:30, Paper ThEP-05.12 | |
Detrusor Pressure Estimation from Single-Channel Urodynamics |
|
Zareen, Farhath | University of South Florida |
Ouyang, Zhonghua | University of Michigan Ann Arbor |
Majerus, Steve | APT Center, Cleveland VAMC |
Bruns, Tim M. | University of Michigan |
Damaser, Margot S. | Lerner Research Institute, the Cleveland Clinic Foundation |
Karam, Robert | University of South Florida |
Keywords: Time-frequency and time-scale analysis - Time-frequency analysis, Parametric filtering and estimation, Nonlinear dynamic analysis - Biomedical signals
Abstract: Urodynamics is the current gold-standard for diagnosing lower urinary tract dysfunction, but uses nonphysiologically fast, retrograde cystometric filling to obtain a brief snapshot of bladder function. Ambulatory urodynamics allows physicians to evaluate bladder function during natural filling over longer periods of time, but artifacts generated from patient movement necessitate the use of an abdominal pressure sensor, which makes long-term monitoring and feedback for closed-loop treatment impractical. In this paper, we analyze the characteristics of single-channel bladder pressure signals from human and feline datasets, and present an algorithm designed to estimate detrusor pressure, which is useful for diagnosis and treatment. We utilize multiresolution analysis techniques to maximize the attenuation of probable abdominal pressure components in the vesical pressure signal. Results indicate a strong correlation, averaging 0.895±0:121 (N = 40) and 0.812±0:113 (N = 16) between the estimated detrusor pressure obtained by the proposed method and recorded urodynamic data from human and feline subjects, respectively.
|
|
15:45-17:30, Paper ThEP-05.13 | |
Energy-Efficient Tree-Based EEG Artifact Detection |
|
Ingolfsson, Thorir Mar | ETH Zurich |
Cossettini, Andrea | ETH Zurich |
Benatti, Simone | University of Bologna |
Benini, Luca | University of Bologna |
Keywords: Time-frequency and time-scale analysis - Wavelets, Neural networks and support vector machines in biosignal processing and classification, Data mining and big data methods - Machine learning and deep learning methods
Abstract: In the context of epilepsy monitoring, EEG artifacts are often mistaken for seizures due to their morphological similarity in both amplitude and frequency, making seizure detection systems susceptible to higher false alarm rates. In this work we present the implementation of an artifact detection algorithm based on a minimal number of EEG channels on a parallel ultra-low-power (PULP) embedded platform. The analyses are based on the TUH EEG Artifact Corpus dataset and focus on the temporal electrodes. First, we extract optimal feature models in the frequency domain using an automated machine learning framework, achieving a 93.95% accuracy, with a 0.838 F1 score for a 4 temporal EEG channel setup. The achieved accuracy levels surpass state-of-the-art by nearly 20%. Then, these algorithms are parallelized and optimized for a PULP platform, achieving a 5.21× improvement of energy-efficient compared to state-of-the-art low-power implementations of artifact detection frameworks. Combining this model with a low-power seizure detection algorithm would allow for 300h of continuous monitoring on a 300 mAh battery in a wearable form factor and power budget. These results pave the way for implementing affordable, wearable, long-term epilepsy monitoring solutions with low false-positive rates and high sensitivity, meeting both patients’ and caregivers’ requirements. Clinical relevance— The proposed EEG artifact detection framework can be employed on wearable EEG recording devices, in combination with EEG-based epilepsy detection algorithms, for improved robustness in epileptic seizure detection scenarios.
|
|
ThEP-06 |
Hall 5 |
Theme 02. Brain Imaging & Image Analysis |
Poster Session |
|
15:45-17:30, Paper ThEP-06.1 | |
Longitudinal Changes in Resting State Fmri Spectra in Children |
|
Agcaoglu, Oktay | Tri-Institutional Center for Translational Research in Neuroimag |
Wilson, Tony W | University of Nebraska Medical Center |
Wang, Yu-Ping | University of Missouri-Kansas City |
Stephen, Julia | The Mind Research Network |
Calhoun, Vince D | Tri-Institutional Center for Translational Research in Neuroimag |
Keywords: Brain imaging and image analysis, Image analysis and classification - Machine learning / Deep learning approaches, Magnetic resonance imaging - MR neuroimaging
Abstract: Abstract—Longitudinal studies can provide more precise measure of brain development, as they focus on within-subject variability, as opposed to cross-sectional studies. In this study, we track longitudinal changes in resting state fMRI data using spectrum of time-courses generated via group independent component analysis (gICA), in a multi time point dataset containing healthy children 8-18 years old, collected on both eyes open and eyes closed resting state conditions. Clinical Relevance— Tracking normal brain development and identifying biomarkers of healthy brain development are critically important to diagnose mental disorders at early ages. We found increased spectral power in low frequencies and decreased spectral power in high frequencies in children with typical development in both the eyes open and eyes closed conditions, though the eyes closed condition showed greater changes with development, mostly in the visual networks. Results are also replicated on an independent dataset.
|
|
15:45-17:30, Paper ThEP-06.2 | |
Deep Metric Representation Learning for Clinical Resting State FMRI |
|
Mittal, Arunesh | Columbia University |
Paisley, John | Columbia University |
Sajda, Paul | Columbia University |
Keywords: Brain imaging and image analysis, Image feature extraction
Abstract: With growing size of resting state fMRI datasets and advances in deep learning methods, there are ever increasing opportunities to leverage progress in deep learning to solve challenging tasks in neuroimaging. In this work, we build upon recent advances in deep metric learning, to learn embeddings of rs-fMRI data, which can then be potentially used for several downstream tasks. We propose an efficient training method for our model and compare our method with other widely used models. Our experimental results indicate that deep metric learning can be used as an additional refinement step to learn representations of fMRI data, that significantly improves performance on downstream modeling tasks.
|
|
15:45-17:30, Paper ThEP-06.3 | |
A 5D Approach to Study Spatio-Temporal Dynamism of Resting-State Brain Networks in Schizophrenia |
|
Kazemivash, Behnam | Georgia State University |
Calhoun, Vince D | Tri-Institutional Center for Translational Research in Neuroimag |
Keywords: Brain imaging and image analysis, Functional image analysis, Magnetic resonance imaging - MR neuroimaging
Abstract: Abstract— Schizophrenia is a serious brain disorder that can affect all aspects of patient’s life such as thinking, behaving and even feeling. The principal cause of schizophrenia is still unknown, but there is some evidence that differences in brain networks interactions along with functional dysconnectivity may play a significant role. Prior work has mostly focused on static summaries of functional data, or more recently changes in temporal coupling between fixed networks. Here, we study differences in spatio-temporal brain dynamics using resting state fMRI images in a dataset including 510 control and 708 schizophrenia patients. To do this, we utilized a deep residual network to extract 5 different spatiotemporal networks each of which captures spatial and temporal dynamics within sensory-motor, auditory, and default mode domains. Our analysis shows significant group differences in various aspects of spatio-temporal dynamics including magnitude, voxel-wise variability, and temporal functional network connectivity. Clinical Relevance— Our study explores effects of spatio-temporal brain dynamism in schizophrenia, which is rarely taken into account, but could provide unique and more sensitive information about the disorder. Here we incorporate a novel 5D brain parcellation model, that enables us to encode spatio-temporal dynamics, to extract and characterize multiple resting fMRI brain networks.
|
|
15:45-17:30, Paper ThEP-06.4 | |
A Two-Step Clustering-Based Pipeline for Big Dynamic Functional Network Connectivity Data |
|
Eslampanah Sendi, Mohammad Sadegh | Georgia Institute of Technology |
Miller, Robyn | The Tri-Institutional Center for Translational Neuroimaging And |
Salat, David | Massachusetts General Hospital, Harvard Medical School |
Calhoun, Vince D | Tri-Institutional Center for Translational Research in Neuroimag |
Keywords: Functional image analysis, Machine learning / Deep learning approaches, Brain imaging and image analysis
Abstract: Dynamic functional network connectivity (dFNC) estimated from resting-state functional magnetic imaging (rs-fMRI) studies the temporal properties of FNC among brain networks by putting them into distinct states using the clustering method. The computational cost of clustering dFNCs has become a significant practical barrier given the availability of enormous neuroimaging datasets. To this end, we developed a new dFNC pipeline to analyze large dFNC data without accessing hug processing capacity. We validated our proposed pipeline and compared it with the standard one using a publicly available dataset. We found that both standard and iSparse kmeans generate similar dFNC states while our approach is 27 times faster than the traditional method in finding the optimum number of clusters and creating better clustering quality.
|
|
ThEP-07 |
Hall 5 |
Theme 02. Image Segmentation - P2 |
Poster Session |
Chair: Pontiki, Antonia, A | King's College London |
|
15:45-17:30, Paper ThEP-07.1 | |
Weakly Supervised Polyp Segmentation from an Attention Receptive Field Mechanism |
|
Ruiz García, Lina Marcela | Universidad Industrial De Santander |
Martinez, Fabio | Universidad Industrial De Santander |
Keywords: Image segmentation, Machine learning / Deep learning approaches, Image feature extraction
Abstract: Colorectal cancer is the third most incidence cancer world-around. Colonoscopies are the most effective resource to detect and segment abnormal polyp masses, considered as the main biomarker of this cancer. Nonetheless, some recent clinical studies have revealed a polyp miss rate up to 26% during the clinical routine. Also, the expert bias introduced during polyp shape characterization may induce to false-negative diagnosis. Current computational approaches have supported polyp segmentation but over controlled scenarios, where polyp frames have been labeled by an expert. These supervised representations are fully dependent of well-segmented polyps, in crop sequences that always report these masses. This work introduces an attention receptive field mechanism, that robustly recover the polyp shape, by learning non-local pixel relationship. Besides this deep representation is learning from a weakly supervised scheme that includes unlabeled background frames, to discriminate polyps from near structures like intestinal folds. The achieved results outperform state-of-the-art approaches achieving a 95.1% precision in the public CVC-Colon DB, with also competitive performance on other datasets.
|
|
15:45-17:30, Paper ThEP-07.2 | |
A Memory-Efficient Deep Framework for Multi-Modal MRI-Based Brain Tumor Segmentation |
|
Hashemi, Nima | Electrical and Computer Engineering, University of Tehran |
Masoudnia, Saeed | Tehran University of Medical Sciences |
Nejad, Ashkan | University of Groningen |
Nazem-Zadeh, Mohammad-Reza | Tehran University of Medical Sciences |
Keywords: Image segmentation, Machine learning / Deep learning approaches, Multimodal image fusion
Abstract: Automatic Brain Tumor Segmentation (BraTS) from MRI plays a key role in diagnosing and treating brain tumors. Although 3D U-Nets achieve state-of-the-art results in BraTS, their clinical use is generally limited due to requiring high-end GPU with high memory. To address the limitation, we provide a feasible yet accurate solution based on 2D U-net. In order to address the technical challenges of BraTS, extensive data augmentations on multi-modal MRI are first applied. We also combine two previously modifications and applied them to our proposed dice loss. In order to be runnable on a budget-GPU, the simultaneous multi-label tumor segmentation is decomposed into some binary sequential segmentations. Experiments on BraTS 2020 demonstrate that our proposed method achieves state-of-the-art results. Dice scores of 0.905, 0.903, and 0.822 for whole tumor, tumor core, and enhancing tumor are accomplished on the testing set. Moreover, our proposed method could be runnable on budget-GPUs with only 4G RAM.
|
|
15:45-17:30, Paper ThEP-07.3 | |
Edge-Preserving Image Synthesis for Unsupervised Domain Adaptation in Medical Image Segmentation |
|
Vo, Thong | Ryerson University |
Khan, Naimul | Ryerson University |
Keywords: Image segmentation, Image analysis and classification - Machine learning / Deep learning approaches
Abstract: Domain Adaptation is a technique to address the lack of massive amounts of labeled data in different application domains. Unsupervised domain adaptation is the process of adapting a model to an unseen target dataset using solely labeled source data and unlabeled target domain data. Though many image-spaces domain adaptation methods have been proposed to capture pixel-level domain-shift, such techniques may fail to maintain high-level semantic information for the segmentation task. For the case of biomedical images, fine details such as blood vessels can be lost during the image transformation operations between domains. In this work, we propose a model that adapts between domains using cycle-consistent loss while maintaining edge details of the original images by enforcing an edge-based loss during the adaptation process. We demonstrate the effectiveness of our algorithm by comparing it to other approaches on two eye fundus vessels segmentation datasets. We achieve 3.1% increment in Dice score compared to the SOTA and ~7.02% increment compared to a vanilla CycleGAN implementation.
|
|
15:45-17:30, Paper ThEP-07.4 | |
Development and Evaluation of a Rib Statistical Shape Model for Thoracic Surgery |
|
Pontiki, Antonia, A | King's College London |
De Angelis, Sara | King's College London |
Dibblin, Connor | King's College London |
Trujillo-Cortes, Isabella | King's College London |
Lamata, Pablo | Dept. of Biomedical Engineering, St Thomas’ Hospital, King’s Col |
Housden, Richard James | King's College London |
Benedetti, Giulia | Guy's and St Thomas' NHS Foundation Trust |
Bille, Andrea | Guy's and St Thomas' NHS Foundation Trust |
Rhode, Kawal | King's College London |
Keywords: Image segmentation, Image registration, segmentation, compression and visualization - Volume rendering, CT imaging
Abstract: Patients with advanced cancer undergoing chest wall resection may require reconstruction. Currently, rib prostheses are created by segmenting computed tomography images, which is time-consuming and labour intensive. The aim was to optimise the production of digital rib models based on a patient’s age, weight, height and gender. A statistical shape model of human ribs was created and used to synthetise rib models, which were compared to the ones produced by segmentation and mirroring. The segmentation took 11.56 ± 1.60 min compared to 0.027 ± 0.009 min using the new technique. The average mesh error between the mirroring technique and segmentation was 0.58 ± 0.25 mm (right ribs), and 0.87 ± 0.18 mm (left ribs), compared to 1.37 ± 0.66 mm (p < 0.0001) and 1.68 ± 0.77 mm (p < 0.05), respectively, for the new technique. The new technique is promising for the efficiency and ease-of-use in the clinical environment.
|
|
15:45-17:30, Paper ThEP-07.5 | |
An Optimized U-Net for Unbalanced Multi-Organ Segmentation |
|
Berzoini, Raffaele | Politecnico Di Milano |
Colombo, Aurora Anna | Politecnico Di Milano |
Bardini, Susanna | Politecnico Di Milano |
Conelli, Antonello | Politecnico Di Milano |
D'Arnese, Eleonora | Politecnico Di Milano |
Santambrogio, Marco | Politecnico Di Milano |
Keywords: Image segmentation, Machine learning / Deep learning approaches, CT imaging applications
Abstract: Medical practice is shifting towards the automation and standardization of the most repetitive procedures to speed up the time-to-diagnosis. Semantic segmentation represents a critical stage in identifying a broad spectrum of regions of interest within medical images. Indeed, it identifies relevant objects by attributing to each image pixels a value representing pre-determined classes. Despite the relative ease of visually locating organs in the human body, automated multi-organ segmentation is hindered by the variety of shapes and dimensions of organs and computational resources. Within this context, we propose BIONET, a U-Net-based Fully Convolutional Network for efficiently semantically segmenting abdominal organs. BIONET deals with unbalanced data distribution related to the physiological conformation of the considered organs, reaching good accuracy for variable organs dimension with low variance, and a Weighted Global Dice Score score of 93.74±1.1%, and an inference performance of 138 frames per second.
|
|
15:45-17:30, Paper ThEP-07.6 | |
A Hybrid Capsule Network for Automatic 3D Mandible Segmentation Applied in Virtual Surgical Planning |
|
moghaddasi, hadis | Tehran University of Medical Sciences (TUMS) |
Amiri Tehrani Zade, Amin | Image-Guided Surgery Group, Research Centre of Biomedical Techno |
Jalili Aziz, Maryam | Image-Guided Surgery Group, Research Centre of Biomedical Techno |
parhiz, alireza | Tehran University of Medical Sciences (TUMS) |
Farnia, Parastoo | Tehran University of Medical Siences |
Ahmadian, Alireza | Tehran University of Medical Sciences |
Alirezaie, Javad | Ryerson University, Univ of Waterloo |
Keywords: Image segmentation, Machine learning / Deep learning approaches, CT imaging applications
Abstract: Automatic mandible segmentation from CT images is an essential step for three-dimensional (3D) virtual surgical planning. It is required to achieve an accurate preoperative prediction of an intended target; Therefore, precise segmentation of the mandible is desired. Segmentation of mandible is a challenging task due to the complexity of the mandible structure, imaging artifacts, and metal implants or dental filling materials, which affect the quality of CT images. In recent years, utilizing convolutional neural networks (CNNs) have made significant improvements in mandible segmentation. However, aggregating data at pooling layers and collecting and labeling a large volume of data for training CNNs are significant issues in medical practice. In this study, for the first time, we have optimized data-efficient 3D-UCaps to achieve advantages of both the capsule network and the CNN, for accurate mandible segmentation on volumetric CT images. Furthermore, to handle the problem of voxel class imbalance, we have proposed a novel hybrid loss function that uses a weighted combination of the focal and margin loss functions. To evaluate the performance of our proposed method, a similar experiment is conducted with the 3D U-Net. All experiments are performed on the public domain database for computational anatomy (PDDCA). The proposed method and 3D U-Net achieved an average dice coefficient of 90% and 88% on the PDDCA, respectively. The results indicate that the proposed method leads to accurate mandible segmentation and achieves comparable and even higher results than the other popular deep learning models. It is concluded that the proposed network is very effective as it requires up to 4 million fewer parameters than the 3D U-Net.
|
|
15:45-17:30, Paper ThEP-07.7 | |
Applying Machine Learning for Intelligent Assessment of Wheelchair Cushions from Pressure Mapping Images |
|
Farahani, Behnam | Simon Fraser University |
Fadil, Rabie | University of North Dakota |
Aboonabi, Arina | Simon Fraser University |
Loscheider, Jane | University of North Dakota |
Tavakolian, Kouhyar | Assistant Professor |
Arzanpour, Siamak | Simon Fraser University |
Keywords: Image segmentation, Machine learning / Deep learning approaches
Abstract: Abstract— Pressure ulcers are skin and underlying tissue injuries caused by the cells’ lack of oxygen and nutrition due to blood flow obstruction from constant pressure on the skin. It is prevalent in people with motion disabilities, such as wheelchair users. For both prevention and healing, wheelchair users should occasionally change their sitting posture, use cushions that evenly distribute the pressure, or relieve pressure from the sensitive areas. Occupational therapists (OTs) often use pressure mapping systems (PMS) to assess their clients and recommend them a cushion. A cushion with more uniform pressure distribution and fewer pressure concentration points is ranked the highest. This paper offers a novel approach to enhance the objectivity of PMS readings and rankings for OTs. Our method relies on image segmentation techniques to generate quantifiable measures for cushions assessment. We implemented a sequential process to generate a score representing a cushion’s suitability for an individual, which begins with PMS image segmentation using machine learning, followed by a deep learning algorithm for identifying high-risk pressure points. We introduced a Cushion Index for quantifying and ranking the cushions. Clinical Relevance— By selecting proper cushions for wheelchair users, the risk of developing PUs is reduced.
|
|
15:45-17:30, Paper ThEP-07.8 | |
Skin Lesion Segmentation Using a Semi-Supervised U-NetSC Model with an Adaptive Loss Function |
|
Barzegar, Somayeh | Ryerson University |
Khan, Naimul | Ryerson University |
Keywords: Image segmentation, Machine learning / Deep learning approaches
Abstract: Skin lesion segmentation is a crucial step in cancer detection. Deep learning has shown promising results for lesion segmentation. However, the performance of these models depends on accessing lots of training samples with pixel-level annotations. Employing a semi-supervised approach reduces the need for a large number of annotated samples. Accordingly, a semi-supervised strategy is proposed based on the high correlation of segmentation and classification tasks. The U-Net Segmentation and Classification model (U-NetSC) is a unified architecture containing segmentation and classification modules. The classification module uses feature maps from the last layer of the segmentation model to increase the collaboration of two tasks. U-NetSC can be trained with only class-level or both class-level and pixel-level ground truth using an adaptive loss function. U-NetSC achieves ∼2%, ∼2%, ∼3%, and ∼1% improvement in Jaccard Index, Dice coefficient, precision, and accuracy, respectively, in comparison with a supervised attention-gated U-Net model.
|
|
15:45-17:30, Paper ThEP-07.9 | |
Deformable Attention (DANet) for Semantic Image Segmentation |
|
Rajamani, Kumar | BNM Institute of Technology |
D Gowda, Sahana | RV University |
N, Vishwa Tej | Amrita Vishwa Vidyapeetham |
Tirunellai Rajamani, Srividya | University of Augsburg |
Keywords: Image segmentation, Machine learning / Deep learning approaches, Image analysis and classification - Machine learning / Deep learning approaches
Abstract: Deep learning based medical image segmentation is currently a widely researched topic. Attention mechanism used with deep networks significantly benefit semantic segmentation tasks. The recent criss-cross-attention module captures global self-attention while remaining memory and time efficient. However, capturing attention from only the pertinent non-local locations can cardinally boost the accuracy of semantic segmentation networks. We propose a new Deformable Attention Network (DANet) that enables a more accurate contextual information computation in a similarly efficient way. Our novel technique is based on learning the deformation of the query, key and value attention feature maps in a continuous way. A deep segmentation network with this attention mechanism is able to capture attention from germane non-local locations. This boosts the segmentation performance of COVID-19 lesion segmentation compared to criss-cross attention within a U-Net. Our validation experiments show that the performance gain of the recursively applied deformable attention blocks comes from their ability to capture dynamic and precise (wider) attention context. DANet achieves Dice scores of 60.17% for COVID-19 lesions segmentation and improves the accuracy by 4.4% points compared to a baseline U-Net.
|
|
15:45-17:30, Paper ThEP-07.10 | |
Automated Quantification of Inflamed Lung Regions in Chest CT by UNet++ and SegCaps: A Comparative Analysis in COVID-19 Cases |
|
Bhatia, Priya | IIT Hyderabad |
Sinha, Abhishar | IIT Hyderabad |
Joshi, Swati | Mahatma Gandhi Medical College and Hospital (MGMCH) |
Ghosh, Rajesh | East Kent Hospitals University NHS |
Sarkar, Rahuldeb | Medway NHS Foundation Trust |
Jana, Soumya | Indian Institute of Technology Hyderabad |
Keywords: Image segmentation, Machine learning / Deep learning approaches, CT imaging
Abstract: During the current COVID-19 pandemic, a high volume of lung imaging has been generated in the aid of the treating clinician. Importantly, lung inflammation severity, associated with the disease outcome, needs to be precisely quantified. Producing consistent and accurate reporting in high-demand scenarios can be a challenge that can compromise patient care with significant inter- or intra-observer variability in quantifying lung inflammation in a chest CT scan. In this backdrop, automated segmentation has recently been attempted using UNet++, a convolutional neural network (CNN), and results comparable to manual methods have been reported. In this paper, we hypothesize that the desired task can be performed with comparable efficiency using capsule networks with fewer parameters that make use of an advanced vector representation of information and dynamic routing. In this paper, we validate this hypothesis using SegCaps, a capsule network, by direct comparison, individual comparison with CT severity score, and comparing the relative effect on a ML(machine learning)-based prognosis model developed elsewhere. We further provide a scenario, where a combination of UNet++ and SegCaps achieves improved performance compared to individual models.
|
|
ThEP-08 |
Hall 5 |
Theme 02. Machine Learning/Deep Learning Applications - P2 |
Poster Session |
|
15:45-17:30, Paper ThEP-08.1 | |
Cross-Modal Transfer Learning Methods for Alzheimer's Disease Diagnosis |
|
Pereira, Pedro Miguel | Instituto Superior Técnico |
Silveira, Margarida | Institute for Systems and Robotics - Instituto Superior Técnico |
|
|
15:45-17:30, Paper ThEP-08.2 | |
A Bounding-Box Regression Model for Colorectal Tumor Detection in CT Images Via Two Contrary Networks |
|
Kim, Yongsoo | Korea Institute of Science and Technology |
Park, Seungbin | Purdue University |
Kim, Hannah | Imagoworks Inc |
Kim, Seung-seob | Yonsei University College of Medicine |
Lim, Joon Seok | Yonsei University College of Medicine |
Kim, Sungwon | Yonsei University College of Medicine |
Choi, Kihwan | Korea Institute of Science and Technology |
Seo, Hyunseok | Korea Institute of Science and Technology |
Keywords: Image analysis and classification - Machine learning / Deep learning approaches, Image analysis and classification - Digital Pathology, CT imaging applications
Abstract: Abstract— The field of medical image analysis has been attracted to deep learning. Various deep learning-based techniques have been introduced to aid diagnosis in the CT image of the patient. The auxiliary model for diagnosis that we proposed is to detect colorectal tumors in the CT image. The model is combined with two contrary networks of ‘Detection Transformer’ and ‘Hourglass’. Furthermore, to improve the performance of the model, we propose an efficient connection method for two contrary models by using intermediate prediction information. A total of 3,509 patients (193,567 CT images) were applied to the experiment and our model outperforms the conventional models in colorectal tumor detection. Clinical Relevance— The proposed model in this paper automatically detects colorectal tumors and provides the bounding box in the CT images. Colorectal tumor is one of the common diseases. In addition, the mortality rate is so high that in-time treatment is required. The model we present here has a sensitivity (or recall) of 84.73 % for tumor detection and a precision of 88.25 % in the patient CT data. The in-slice performance of the tumor detection shows an IoU of 0.56, a sensitivity of 0.67, and a precision of 0.68.
|
|
15:45-17:30, Paper ThEP-08.3 | |
Automatic Feature Construction Based on Genetic Programming for Survival Prediction in Lung Cancer Using CT Images |
|
Scalco, Elisa | National Research Council |
Rizzo, Giovanna | National Research Council (CNR) |
Gómez-Flores, Wilfrido | Centro De Investigación Y De Estudios Avanzados Del Instituto Po |
Keywords: Image analysis and classification - Machine learning / Deep learning approaches, Image feature extraction, CT imaging
Abstract: In the radiomics workflow, machine learning builds classification models from a set of input features. However, some features can be irrelevant and redundant, reducing the classification performance. This paper proposes using the Genetic Programming (GP) algorithm to automatically construct a reduced number of independent and relevant radiomic features. The proposed method is applied to patients affected by Non-Small Cell Lung Cancer (NSCLC) with pre-operative computed tomography (CT) images to predict the two-year survival by the use of linear classifiers. The model built using GP features is compared with benchmark models built using traditional features. The use of the GP algorithm increased classification performance: AUC=0.69 for the proposed model vs. AUC=0.66 and 0.64 for the benchmark models. Hence, the proposed approach better stratifies patients at high and low risk according to their overall postoperative survival time.
|
|
15:45-17:30, Paper ThEP-08.4 | |
Cardiac Anomaly Detection from Cine MRI Images Using Physiological Features and Random Forest Classifier |
|
Kanakatte, Aparna | Tata Consultancy Services |
Bhatia, Divya | TCS-Research and Innovation |
Ghose, Avik | TCS Research & Innovation |
Keywords: Cardiac imaging and image analysis, Image analysis and classification - Machine learning / Deep learning approaches, Magnetic resonance imaging - Cardiac imaging
Abstract: Computer-aided diagnosis (CAD) of cardiovascular diseases (CVD) with cine MRI is a foremost research topic to enable improved, faster, and more accurate diagnosis of CVD patients. However, current approaches that use manual visualization or conventional clinical indices can lack accuracy for borderline cases. Also, manual visualization of 3D/4D MR data is time-consuming and expert-dependent. We try to simplify this process by creating an end-to-end automated CAD system that segments the critical substructures of the heart. The new domain-related physiological values are then calculated from the segmented regions. These features are fed to a classifier that identifies the anomaly. We have obtained a very high accuracy when testing this end-to-end approach on the ACDC dataset (4 pathologies, 1 normal). ACDC datasets were compiled on a single clinical center using the same imaging protocol. To prove the generalizability of the method we have blind-tested this approach on M&Ms-2 dataset which is a multi-center, multi-vendor, and multi-disease dataset with good results.
|
|
15:45-17:30, Paper ThEP-08.5 | |
Mmmna-Net for Overall Survival Time Prediction of Brain Tumor Patients |
|
Tang, Wen | Infervision |
Zhang, Haoyue | UCLA |
Yu, Pengxin | Infervision |
Kang, Han | Infervision |
Zhang, Rongguo | Infervision |
Keywords: Magnetic resonance imaging - MR neuroimaging, Brain imaging and image analysis
Abstract: Overall survival (OS) time is one of the most important evaluation indices for gliomas situations. Multi-modal Magnetic Resonance Imaging (MRI) scans play an important role in the study of glioma prognosis OS time. Several deep learning-based methods are proposed for the OS time prediction on multi-modal MRI problems. However, these methods usually fuse multi-modal information at the beginning or at the end of the deep learning networks and lack the fusion of features from different scales. In addition, the fusion at the end of networks always adapts global with global (eg. fully connected after concatenation of global average pooling output) or local with local (eg. bilinear pooling), which loses the information of local with global. In this paper, we propose a novel method for multi-modal OS time prediction of brain tumor patients, which contains an improved non-local features fusion module introduced on different scales. Our method obtains a relative 8.76% improvement over the current state-of-art method (0.6989 vs. 0.6426 on accuracy). An extra testing demonstrates that our method could adapt to the situations with missing modalities. The code is available at https://github.com/TangWen920812/mmmna-net.
|
|
15:45-17:30, Paper ThEP-08.6 | |
Automated Torso Contour Extraction from Clinical Cardiac MR Slices for 3D Torso Reconstruction |
|
Smith, Hannah | University of Oxford |
Banerjee, Abhirup | University of Oxford |
Choudhury, Robin P. | University of Oxford |
Grau, Vicente | University of Oxford |
Keywords: Magnetic resonance imaging - Cardiac imaging, Regularized image Reconstruction, Machine learning / Deep learning approaches
Abstract: Whilst the electrocardiogram (ECG) is an essential tool for diagnosing cardiac electrical abnormalities, its characteristics are dependent on anatomical variability. Specifically variation in torso geometry affects relative positions of the leads with respect to the heart. We propose a novel pipeline that uses standard cardiac magnetic resonance images to reconstruct the torso and heart, and recreate the ECG considering torso and cardiac anatomy. This requires automated extraction of the torso contours. Our method combines an initial u-net segmenter with a second network that refines contours and removes spurious segments. The networks were evaluated on a cross validation study dataset and an independent test set. The use of two-channel input, including both original image and initial segmentation, in the refinement network significantly improved performance on the independent test set, reducing the Hausdorff distance from 9.1 pixels to 4.3 pixels and increasing Dice coefficient from 0.75 to 0.93.
|
|
15:45-17:30, Paper ThEP-08.7 | |
Deep Learning Prediction and Visualization of Gender Related Brain Changes from Longitudinal Structural MRI Data in the ABCD Study |
|
Bi, Yuda | TReNDS Center |
Abrol, Anees | Georgia State University, the Mind Research Network |
Fu, Zening | Georgia State University |
Calhoun, Vince D | Tri-Institutional Center for Translational Research in Neuroimag |
Keywords: Magnetic resonance imaging - Cardiac imaging, Image classification, Image visualization
Abstract: Deep learning algorithms for predicting from neuroimaging data have shown considerable promise. Deep learning models that take advantage of the data's 3D structure have been proven to outperform ordinary machine learning on a number of learning tasks. The majority of past research in this area, however, has focused on data from adults. Within the Adolescent Brain and Cognitive Development (ABCD) dataset, a major longitudinal development research, we examine the use of structural MRI data to predict gender and to identify gender related changes in brain structure. The results demonstrate that gender prediction accuracy is extremely high (>94%), and that this accuracy increases with age. Brain regions identified as the most discriminative in the task under study include predominantly frontal regions in addition to temporal lobe. When evaluating gender predictive changes specific to a two year increase in age, a broader set of visual, cingulate, and insular regions are revealed. Overall, our findings show a robust pattern of gender related structural brain changes, even over a small age range. This suggests the potential for evaluating the relationship of these changes to various behavioral and environmental factors to further study how the brain develops during adolescence.
|
|
15:45-17:30, Paper ThEP-08.8 | |
White Matter Lesion Segmentation for Multiple Sclerosis Patients Implementing Deep Learning |
|
Papadopoulos, Theofilos | Unit of Medical Technology and Intelligent Information Systems, |
Tripoliti, Evanthia | University of Ioannina |
Plati, Daphne | Department of Biomedical Research, Institute of Molecular Biolog |
Zelilidou, Styliani | Unit of Medical Technology and Intelligent Information Systems, |
Vlachos, Kostas | Ippokratio Ioanninon S. A., GR45333, Ioannina, Greece |
Konitsiotis, Spiros | Medical School, University of Ioannina |
Fotiadis, Dimitrios I. | University of Ioannina |
Keywords: Magnetic resonance imaging - MR neuroimaging, Image segmentation, Machine learning / Deep learning approaches
Abstract: The aim of this work is to address the problem of White Matter Lesion (WML) segmentation employing MRI images from Multiple Sclerosis (MS) patients through the application of deep learning. A U-net based architecture containing a contrastive path and an expanding path prior to the final pixel-wise classification is implemented. The data are provided by the Ippokratio Radiology Center of Ioannina and include FLAIR MRI images from 30 patients in three phases, baseline and two follow ups. The prediction results are quite significant in terms of pixel-wise classification. The implemented deep learning model demonstrates Dice coefficient 0.7292, Precision 75.92% and Recall 70.16% in 2D slices of FLAIR MRI non-skull stripped images.
|
|
15:45-17:30, Paper ThEP-08.9 | |
Learning Active Multimodal Subspaces in the Brain |
|
Batta, Ishaan | Georgia Institute of Technology |
Abrol, Anees | Georgia State University, the Mind Research Network |
Fu, Zening | Georgia State University |
Calhoun, Vince D | Tri-Institutional Center for Translational Research in Neuroimag |
Keywords: Multimodal image fusion, Brain imaging and image analysis, Machine learning / Deep learning approaches
Abstract: Here we introduce a multimodal framework to identify subspaces in the human brain that are defined by collective changes in structural and functional measures and are actively linked to demographic, biological and cognitive indicators in a population. We determine the multimodal subspaces using principles of active subspace learning (ASL) and demonstrate its application on a sample learning task (biological ageing) on a schizophrenia dataset. The proposed multimodal ASL method successfully identifies latent brain representations as subsets of brain regions and connections forming covarying subspaces in association with biological age. We show that schizophrenia is characterized by different subspace patterns compared to those in a cognitively normal brain. The multimodal features generated by projecting structural and functional MRI components onto these active subspaces perform better than several PCA-based transformations and equally well when compared to non-transformed features on the studied learning task. In essence, the proposed method successfully learns active brain subspaces associated with a specific brain condition but inferred from the brain imaging data along with the biological/cognitive traits of interest.
|
|
15:45-17:30, Paper ThEP-08.10 | |
Deep Learning Using Pre-Brachytherapy MRI to Automatically Predict Applicator Induced Complex Uterine Deformation |
|
Ghosh, Shrimanti | University of Alberta, Canada |
Punithakumar, Kumaradevan | University of Alberta |
Huang, Fleur | University of Alberta |
Menon, Geetha | University of Alberta |
Boulanger, Pierre | University of Alberta |
Keywords: Magnetic resonance imaging - Other organs, Image segmentation, Machine learning / Deep learning approaches
Abstract: This novel deep-learning algorithm addresses the challenging task of predicting uterine shape and location when deformed from its natural anatomy by the presence of an intrauterine (tandem)/intravaginal (ring) applicator during brachytherapy (BT) treatment for locally advanced cervical cancer. Paired pelvic MRI datasets from 92 subjects, acquired without (pre-BT) and with (at-BT) applicators, were used. We propose a novel automated algorithm to segment the uterus in pre-BT MR images using a deep convolutional neural network (CNN) incorporated with autoencoders. The proposed neural net is based on a pre-trained CNN Inception V4 architecture. It predicts a compressed vector by applying a multi-layer autoencoder, which is then back-projected into the segmentation contour of the uterus. Following this, another transfer learning approach using a modified U-net model is employed to predict the at-BT uterus shape from pre-BT MRI. The complex and large deformations of the uterus are quantified using free form deformation method. The proposed algorithm yielded an average Dice Coefficient (DC) of 94.1 ± 3.3 and an average Hausdorff Distance (HD) of 4.0 ± 3.1 mm compared to the manually defined ground truth by expert clinicians. Further, the modified U-net prediction of the at-BT uterus resulted in a DC accuracy of 88.1 ± 3.8 and HD of 5.8 ± 3.6 mm. The mean uterine surface point-to-point displacement was 25.0 [10.0 - 62.5] mm from the pre- BT position. Our unique deep learning (DL) method can thus successfully predict tandem-deformed uterine shape and position from MR images taken before the BT implant procedure i.e. without the applicator in place.
|
|
ThEP-09 |
Hall 5 |
Theme 02. Optical and CT Imaging and Applications |
Poster Session |
|
15:45-17:30, Paper ThEP-09.1 | |
Semantic Segmentation of Micro-CT Images to Analyze Bone Ingrowth into Biodegradable Scaffolds |
|
Gnanavel, Ganeshaaraj | University of Moratuwa |
Sivayogaraj, Kaushalya | University of Moratuwa |
Kondarage, Achintha Iroshan | University of Moratuwa |
Karunaratne, Angelo | Department of Mechanical Engineering, University of Moratuwa |
Jones, Julian | Department of Materials, Imperial College London |
Nanayakkara, Nuwan Dayananda | University of Moratuwa |
Keywords: Micro-CT imaging, Image registration, segmentation, compression and visualization - Volume rendering, Machine learning / Deep learning approaches
Abstract: The healing of bone fractures is a complex and well-orchestrated physiological process, but normal healing is compromised when the fracture is large. These large non-union fractures often require a template with surgical intervention for healing. The standard treatment, autografting, has drawbacks such as donor site pain and risk of infection. Biodegradable scaffolds developed using biomaterials such as bioactive glass are a potential solution. Investigation of bone ingrowth into biodegradable scaffolds is an important aspect of their development. Micro-CT (µ-CT) imaging is widely used to evaluate and quantify tissue ingrowth into scaffolds in 3D. Existing segmentation techniques have low accuracy in differentiating bone and scaffold, and need improvements to accurately quantify the bone in-growth into the scaffold using µ-CT scans. This study proposes a novel 3-stage pipeline for better outcome. The fist stage of the pipeline is based on a convolutional neural network for the segmentation of the scaffold, bone, and pores from µ-CT images to investigate bone ingrowth. A 3D rigid image registration procedure was employed in the next stage to extract the volume of interest (VOI) for the analysis. In the final stage, algorithms were developed to quantitatively analyze bone ingrowth and scaffold degradation. The best model for segmentation produced a dice similarity coefficient score of 90.1, intersection over union score of 83.9, and pixel accuracy of 93.1 for unseen test data.
|
|
15:45-17:30, Paper ThEP-09.2 | |
Gradient-Based Optimization Algorithm for Hybrid Loss Function in Low-Dose CT Denoising |
|
Niknejad Mazandarani, Farzan | Ryerson University |
Marcos, Luella | Ryerson University |
Babyn, Paul | University of Saskatchewan |
Alirezaie, Javad | Ryerson University, Univ of Waterloo |
Keywords: CT imaging, Image enhancement - Denoising, Image reconstruction and enhancement - Machine learning / Deep learning approaches
Abstract: Computed tomography (CT) is a widely used non-invasive medical image tool for diagnosis. However, the X-ray radiation dose that is being used in CT scanners has increased concerns among researchers for it can cause medical illnesses like cancer. The safest way to address this problem is to reduce the amount of ionizing radiation dose to patients then apply restoration methods to denoise and enhance the quality of low-dose CT images affected by noise. The primary purpose of this work is to determine and analyze the most effective and efficient hybrid loss function in deep learning (DL)-based denoising network. Various combinations of the most common objective functions in CT denoising networks, namely L1 loss, per-pixel loss, perceptual loss, and structural dissimilarity loss, were investigated. Further, a hyperparameter learning algorithm was introduced to find the best scalable factors of the loss functions in each hybrid loss function combination. This algorithm contributes to the generalizability prediction of designing future CT denoising networks.
|
|
15:45-17:30, Paper ThEP-09.3 | |
Segmentation of the Left Atrium Using CT Images and a Deep Learning Model |
|
Grigoriadis, Grigoris | University of Ioannina |
Zaridis, Dimitris | University of Ioannina |
Nikopoulos, Sotirios | Medical School, University of Ioannina |
Tachos, Nikolaos | Unit of Medical Technology and Intelligent Information Systems, |
Sakellarios, Antonis | Forth-Biomedical Research Institute |
Naka, Katerina | University of Ioannina |
Michalis, Lampros | University of Ioannina |
Fotiadis, Dimitrios I. | University of Ioannina |
Keywords: CT imaging, Machine learning / Deep learning approaches, Cardiac imaging and image analysis
Abstract: The left atrium (LA) is one of the cardiac cavities with the most complex anatomical structures. Its role in the clinical diagnosis and patient’s management is critical, as it is responsible for the atrial fibrillation, a condition that promotes the thrombogenesis inside the left atrial appendage. The development of an automated approach for LA segmentation is a demanding task mainly due to its anatomical complexity and the variation of its shape among patients. In this study, we focus to develop an unbiased pipeline capable to segment the atrial cavity from CT images. For evaluation purposes state-of-the-art metrics were used to assess the segmentation results. Particularly, the results indicated the mean values of the dice score 80%, the hausdorff distance 11.78mm, the average surface distance 2.24mm and the rand error index 0.2.
|
|
15:45-17:30, Paper ThEP-09.4 | |
MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-Aware CT-Projections from a Single X-Ray |
|
Corona-Figueroa, Abril | Durham University |
Frawley, Jonathan | Durham University |
Bond-Taylor, Sam | Durham University |
Bethapudi, Sarath | County Durham and Darlington NHS Foundation Trust |
Shum, Hubert P. H. | Durham University |
Willcocks, Chris G. | Durham University |
Keywords: CT imaging, X-ray radiography, Image reconstruction and enhancement - Machine learning / Deep learning approaches
Abstract: Computed tomography (CT) is an effective medical imaging modality, widely used in the field of clinical medicine for the diagnosis of various pathologies. Advances in Multidetector CT imaging technology have enabled additional functionalities, including generation of thin slice multiplanar cross-sectional body imaging and 3D reconstructions. However, this involves patients being exposed to a considerable dose of ionising radiation. Excessive ionising radiation can lead to deterministic and harmful effects on the body. This paper proposes a Deep Learning model that learns to reconstruct CT projections from a few or even a single-view X-ray. This is based on a novel architecture that builds from neural radiance fields, which learns a continuous representation of CT scans by disentangling the shape and volumetric depth of surface and internal anatomical structures from 2D images. Our model is trained on chest and knee datasets, and we demonstrate qualitative and quantitative high-fidelity renderings and compare our approach to other recent radiance field-based methods. Our code and link to our datasets are available at https://github.com/abrilcf/mednerf
|
|
15:45-17:30, Paper ThEP-09.5 | |
Beware the Black-Box of Medical Image Generation: An Uncertainty Analysis by the Learned Feature Space |
|
Qu, Yunni | University of Toronto |
Yan, David | University of Kentucky |
Xing, Eric | The Gatton Academy of Mathematics and Science in Kentucky |
Zheng, Fengbo | Tianjin Normal University |
Zhang, Jie | University of Kentucky |
liu, liangliang | Henan Agricultural University, Zhengzhou, Henan 450046, P.R. Chi |
Liang, Gongbo | Texas A&M University-San Antonio |
Keywords: CT imaging applications, CT imaging, Image reconstruction and enhancement - Machine learning / Deep learning approaches
Abstract: Deep neural networks (DNNs) are the primary driving force for the current development of medical imaging analysis tools and often provide exciting performance on various tasks. However, such results are usually reported on the overall performance of DNNs, such as the F1 score for imaging classification and mean square error (MSE) for imaging generation, while insightful analysis is often missing. As a black-box, DNNs usually produce a relatively stable performance on the same task across multiple training trials. However, the learned feature spaces could be significantly different between training trials. We believe additional insightful analysis, such as uncertainty analysis of the learned feature space, is equally important, if not more. Through this work, we evaluate the learned feature space of multiple U-Net architectures for image generation tasks using computational analysis and clustering analysis methods. We demonstrate that the learned feature spaces are easily separable between different training trials of the same architecture with the same hyperparameter setting, indicating the models of the training trials using different criteria for image generation. Such a phenomenon naturally raises the question of which criteria are correct to use. Our work suggests that assessments other than overall performance are needed before applying a DNN model to real-world practice.
|
|
15:45-17:30, Paper ThEP-09.6 | |
A Random Forest-Based Classifier for MYCN Status Prediction in Neuroblastoma Using CT Images |
|
Pereira, Tania | INESC TEC - Institute for Systems and Computer Engineering, Tech |
Silva, Francisco | INESC TEC |
Pedro, Claro | INESC TEC - Institute for Systems and Computer Engineering, Tech |
Diogo Costa, Carvalho | CHUSJ - Centro Hospitalar E Universitário De São João |
Sílvia Costa, Dias | CHUSJ - Centro Hospitalar E Universitário De São João |
Helena, Torrão | IPO-Porto - Instituto Português De Oncologia Do Porto FG |
Oliveira, Hélder P. | INESC TEC, Faculdade De Ciências, Universidade Do Porto |
Keywords: CT imaging applications, CT imaging, Image analysis and classification - Machine learning / Deep learning approaches
Abstract: Neuroblastoma (NB) is the most common extracranial solid tumor in childhood. Genomic amplification of MYCN is associated with poor outcomes and is detected in 16% of all NB cases. CT scans and MRI are the imaging techniques recommended for diagnosis and disease staging. The assessment of imaging features such as tumor volume, shape, and local extension represent relevant prognostic information. Radiogenomics have shown powerful results in the assessment of the genotype-based on imaging findings automatically extracted from medical images. In this work, random forest was used to classify the MYCN amplification using radiomic features extracted from CT slices in a population of 46 NB patients. The learning model showed an area under the curve (AUC) of 0.85 +/- 0.13, suggesting that radiomic-based methodologies might be helpful in the extraction of information that is not accessible by human naked eyes but could aid the clinicians on the diagnosis and treatment plan definition. Clinical relevance — This approach represents a random forest-based model to predict the MYCN amplification in NB patients that could give a faster, earlier, and repeatable analysis of the tumor along the time.
|
|
15:45-17:30, Paper ThEP-09.7 | |
Automatic Classification of Macular Diseases from OCT Images Using CNN Guided with Edge Convolutional Layer |
|
Nasr-Esfahani, Ebrahim | Isfahan University of Technology |
Ghaderi Daneshmand, Parisa | Medical Image & Signal Processing Research Center, Isfahan Univ |
Rabbani, Hossein | Isfahan Univ. of Medical Sciences |
Plonka, Gerlind | University of Goettingen |
Keywords: Optical imaging - Coherence tomography, Machine learning / Deep learning approaches, Image classification
Abstract: Abstract— Optical Coherence Tomography (OCT) is a non-invasive imaging technology that is widely applied for the diagnosis of retinal pathologies. In general, the structural information of retinal layers plays an important role in the diagnosis of various eye diseases by ophthalmologists. In this paper, by focusing on this information, we first introduce a new layer called the edge convolutional layer (ECL) to accurately extract the retinal boundaries in different sizes and angles with a much smaller number of parameters than the conventional convolutional layer. Then, using this layer, we propose the ECL-guided convolutional neural network (ECL-CNN) method for the automatic classification of the OCT images. For the assessment of the proposed method, we utilize a publicly available data comprising 45 OCT volumes with 15 age-related macular degeneration (AMD), 15 diabetic macular edema (DME), and 15 normal volumes, captured by using the Heidelberg OCT imaging device. Experimental results demonstrate that the suggested ECL-CNN approach has an outstanding performance in OCT image classification, which achieves an average precision of 99.43% as a three-class classification work. Clinical Relevance — The objective of this research is to introduce a new approach based on CNN for the automated classification of retinal OCT images. Clinically, the ophthalmologists should manually check each cross-sectional B-scan and classify retinal pathologies from B-scan images. This manual process is tedious and time-consuming in general. Hence, an automatic computer-assisted technique for retinal OCT image classification is demanded.
|
|
15:45-17:30, Paper ThEP-09.8 | |
Detection of Retinal Abnormalities in OCT Images Using Wavelet Scattering Network |
|
Baharlouei, Zahra | Medical Image & Signal Processing Research Center, Isfahan Univ |
Rabbani, Hossein | Isfahan Univ. of Medical Sciences |
Plonka, Gerlind | University of Goettingen |
Keywords: Optical imaging - Coherence tomography, Image classification
Abstract: Abstract— Diagnosis retinal abnormalities in Optical Coherence Tomography (OCT) images assist ophthalmologist in the early detection and treatment of patients. To do this, different Computer Aided Diagnosis (CAD) methods based on machine learning and deep learning algorithms have been proposed. In this paper, wavelet scattering network is used to identify normal retina and four pathologies namely, Central Serous Retinopathy (CSR), Macular Hole (MH), Age-related Macular Degeneration (AMD) and Diabetic Retinopathy (DR). Wavelet scattering network is a particular convolutional network which is formed from cascading wavelet transform with nonlinear modulus and averaging operators. This transform generates sparse, translation invariant and deformation stable representations of signals. Filters in the layers of this network are predefined wavelets and not need to be learned which causes decreasing the processing time and complexity. The extracted features are fed to a Principal Component Analysis (PCA) classifier. The results of this research show the accuracy of 97:4% and 100% in diagnosis abnormal retina and DR from normal ones, respectively. We also achieved the accuracy of 84:2% in classifying OCT images to five classes of normal, CSR, MH, AMD and DR which outperforms other state of the art methods with high computational complexity. Clinical Relevance — Clinically, the manually checking of each OCT B-scan by ophthalmologists is tedious and time consuming and may lead to an erroneous decision specially for multiclass problems. In this study, a low complexity CAD system for retinal OCT image classification based on wavelet scattering network is introduced which can be learned by a small number of data.
|
|
15:45-17:30, Paper ThEP-09.9 | |
Mixture of Symmetric Stable Distributions for Macular Pathology Detection in Optical Coherence Tomography Scans |
|
Tajmirriahi, Mahnoosh | Medical Image & Signal Processing Research Center, Isfahan Univ |
Rostamian, Reyhaneh | Medical Image & Signal Processing Research Center, Isfahan Univ |
amini, zahra | MUI |
Hamidi, Arsham | University of Basel |
Zam, Azhar | New York University |
Rabbani, Hossein | Isfahan Univ. of Medical Sciences |
Keywords: Optical imaging - Coherence tomography, Image classification
Abstract: Abstract— Optical coherence tomography (OCT) is widely used to detect retinal disorders. In this study a new methodology is proposed for automatic detection of macular pathologies in the OCT images. Our approach is based on modeling the normal and abnormal OCT images with α-stable mixture model represented by stochastic differential equations (SDE). Parameters of the model are used to detect abnormal OCT images. The α-stable mixture model is created after applying a fractional Laplacian operator to the image and Expectation-Maximization (EM) algorithm is applied to estimate its parameters. The classification of an OCT image as normal or abnormal would be done by training SVM classifier based on estimated parameters of the mixture model. This method is examined for macular abnormality detection such as AMD, DME, and MH and achieve maximum accuracy of 97.8%. Clinical Relevance— This study establishes automatic method for anomaly detection on OCT images and provides fast and accurate OCT interpretation in clinical application.
|
|
15:45-17:30, Paper ThEP-09.10 | |
Stochastic Differential Equations for Automatic Quality Control of Retinal Optical Coherence Tomography Images |
|
Tajmirriahi, Mahnoosh | Medical Image & Signal Processing Research Center, Isfahan Univ |
Rostamian, Reyhaneh | Medical Image & Signal Processing Research Center, Isfahan Univ |
amini, zahra | MUI |
Hamidi, Arsham | University of Basel |
Zam, Azhar | New York University |
Rabbani, Hossein | Isfahan Univ. of Medical Sciences |
Keywords: Optical imaging - Coherence tomography, Image retrieval
Abstract: Abstract—Optical coherence tomography is widely used to provide high resolution images from retina. During data acquisition, several artifacts may be associated with OCT images which clearly remove information of retinal layers and degrade the quality of images. Manual assessment of the acquired OCT images is hard and time consuming. Therefore, an automatic quality control step is necessary to detect poor images for next decisions of eliminating them and even re-scanning. In this study, a novel automatic quality control methodology is proposed for early assessment of the OCT images quality by employing stochastic differential equations (SDE). In this method α-stable nature of OCT images is represented by applying a fractional Laplacian filter and parameters of the obtained α-stable are fed to an SVM to automatically detect high quality vs poor quality images. The simulation results on a large dataset of normal and abnormal OCT images show that proposed method has outstanding performance in detection of poor vs high quality images. The methodology is applicable to the image quality assessment of other OCT scanning devices as well. Clinical Relevance— Automatic quality control assessment of retinal OCT images provides reliable data for diagnosis of retinal and systematic diseases in clinical applications.
|
|
15:45-17:30, Paper ThEP-09.11 | |
Automated Characterization of Catalytically Active Inclusion Body Production in Biotechnological Screening Systems |
|
Ruzaeva, Karina | RWTH Aachen University, Aachen, Germany |
Kira, Kuesters | RWTH Aachen, Forschungszentrum Juelich GmbH |
Wolfgang, Wiechert | Forschungszentrum Jülich GmbH |
Benjamin Berkels, Benjamin | RWTH Aachen University |
Oldiges, Marco | Forschungszentrum Jülich |
Nöh, Katharina | Forschungszentrum Jülich GmbH |
Keywords: Optical imaging and microscopy - Microscopy, Image segmentation, Image feature extraction
Abstract: We here propose an automated pipeline for the microscopy image-based characterization of catalytically active inclusion bodies (CatIBs), which includes a fully automatic experimental high-throughput workflow combined with a hybrid approach for multi-object microbial cell segmentation. For automated microscopy, a CatIB producer strain was cultivated in a microbioreactor from which samples were injected into a flow chamber. The flow chamber was fixed under a microscope and an integrated camera took a series of images per sample. To explore heterogeneity of CatIB development during the cultivation and track the size and quantity of CatIBs over time, a hybrid image processing pipeline approach was developed, which combines an ML-based detection of in-focus cells with model-based segmentation. The experimental setup in combination with an automated image analysis unlocks high-throughput screening of CatIB production, saving time and resources.
|
|
ThEP-10 |
Hall 5 |
Theme 02. Ultrasound Imaging and Applications |
Poster Session |
Chair: Sumi, Chikayoshi | Sophia University |
|
15:45-17:30, Paper ThEP-10.1 | |
Comparative Analysis of Current Deep Learning Networks for Breast Lesion Segmentation in Ultrasound Images |
|
Rocha Ferreira, Margarida | 2Ai - School of Technology, IPCA, Barcelos, Portugal |
Torres, Helena | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Oliveira, Bruno | 2Ai - Applied Artificial Intelligence Laboratory |
Gomes-Fonseca, João | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Morais, Pedro | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Novais, Paulo | Algoritmi Center, School of Engineering, University of Minho, Gu |
Vilaça, João | 2Ai - Applied Artificial Intelligence Laboratory |
Keywords: Ultrasound imaging - Breast, Image segmentation, Machine learning / Deep learning approaches
Abstract: Automatic lesion segmentation in breast ultrasound (BUS) images aids in the diagnosis of breast cancer, the most common type of cancer in women. Accurate lesion segmentation in ultrasound images is a challenging task due to speckle noise, artifacts, shadows, and lesion variability in size and shape. Recently, convolutional neural networks have demonstrated impressive results in medical image segmentation tasks. However, the lack of public benchmarks and a standardized evaluation method hampers the networks’ performance comparison. This work presents a benchmark of seven state-of-the-art methods for the automatic breast lesion segmentation task. The methods were evaluated on a multi-center BUS dataset composed of three public datasets. Specifically, the U-Net, Dynamic U-Net, Semantic Segmentation Deep Residual Network with Variational Autoencoder (SegResNetVAE), U-Net Transformers, Residual Feedback Network, Multiscale Dual Attention-Based Network, and Global Guidance Network (GG-Net) architectures were evaluated. The training was performed with a combination of the cross-entropy and Dice loss functions and the overall performance of the networks was assessed using the Dice coefficient, Jaccard index, accuracy, recall, specificity, and precision. Despite all networks having obtained Dice scores superior to 75%, the GG-Net and SegResNetVAE architectures outperform the remaining methods, achieving 82.56% and 81.90%, respectively.
|
|
15:45-17:30, Paper ThEP-10.2 | |
Considerations about L2 and L1-Norm Regularizations for Ultrasound Reverberation Characteristics Imaging and Vectoral Doppler Measurement |
|
Sumi, Chikayoshi | Sophia University |
Wang, Chenyu | Dept of Info & Commun Sci, Sophia University |
Junya, Takishima | Dept of Info & Commun Sci, Sophia University |
Shirafuji, Sayaka | Dept of Info & Commun Sci, Sophia University |
Keywords: Ultrasound imaging - Breast, Ultrasound imaging - Doppler, Regularized image Reconstruction
Abstract: The L1-norm regularization is applied to ultrasonic reverberation characteristics imaging and vectoral Doppler measurement, of which performances are compared with those of L2-norm regularizations. The L1 regularization yields the sharper image than the L2 regularization. Alternatively, for the Doppler measurement, the L1 regularization yields less accuracy than the L2 regularization. This study will permit us to perform quantitative ultrasonic reverberation characteristics and accurate vectoral Doppler observation.
|
|
15:45-17:30, Paper ThEP-10.3 | |
An Enhanced Method for Full-Inversion-Based Ultrasound Elastography of the Liver |
|
Aboutaleb, Mohamed | York University |
Kheirkhah, Niusha | Western University |
Samani, Abbas | Western University |
Sadeghi-Naini, Ali | York University |
Keywords: Ultrasound imaging - Elastography, Ultrasound imaging - Other organs, Image visualization
Abstract: Similar to many other types of cancer, liver cancer is associated with biological changes that lead to tissue stiffening. An effective imaging technique that can be used for liver cancer detection through visualizing tissue stiffness is ultrasound elastography. In this paper, we show the effectiveness of an enhanced method of quasi-static ultrasound elastography for liver cancer assessment. The method utilizes initial estimates of axial and lateral displacement fields obtained using conventional time delay estimation (TDE) methods in conjunction with a recently proposed strain refinement algorithm to generate enhanced versions of the axial and lateral strain images. Another primary objective of this work is to investigate the sensitivity of the proposed method to the quality of these initial displacement estimates. The strain refinement algorithm is founded on the tissue mechanics principles of incompressibility and strain compatibility. Tissue strain images can serve as input for full-inversion-based elasticity image reconstruction algorithm. In this work, we use strain images generated by the proposed method with an iterative elasticity reconstruction algorithm. Ultrasound RF data collected from a tissue-mimicking phantom and in-vivo data of a liver cancer patient were used to evaluate the proposed method. Results show that while there is some sensitivity to the displacement field initial estimates, overall, the proposed method is robust to the quality of the initial estimates.
|
|
15:45-17:30, Paper ThEP-10.4 | |
Estimating Echocardiographic Myocardial Strain of Left Ventricle with Deep Learning |
|
Romero-Pacheco, Alan | Universidad Nacional Autonoma De Mexico |
Perez-Gonzalez, Jorge | Universidad Nacional Autonoma De Mexico |
Hevia-Montiel, Nidiyare | Universidad Nacional Autonoma De Mexico |
Keywords: Ultrasound imaging - Cardiac, Machine learning / Deep learning approaches
Abstract: The global longitudinal strain of the myocardial tissue has been shown to be a better indicator of cardiac pathologies in the subclinical stage than other indices, such as the ejection fraction. This article presents a new deep learning approach for strain estimation in 2D echocardiograms. The proposed method improves the performance of the state of the art without losing stability with noisy echocardiograms and achieved an average end point error of 0.14 +/- 0.17 pixels in the estimation of the optical flow in the myocardium and an error of 1.34 +/- 2.34 % in the estimation of the global longitudinal strain indicator when evaluated in a synthetic echocardiographic dataset. Further research will validate the proposed method by a clinical in-vivo dataset.
|
|
15:45-17:30, Paper ThEP-10.5 | |
Feasibility of a Deep Learning Approach to Estimate Shear Wave Speed Using the Framework of Reverberant Shear Wave Elastography: A Numerical Simulation Study |
|
Quispe Sánchez, Pierol Salvador | Pontificia Universidad Católica Del Perú |
Romero, Stefano | Pontificia Universidad Católica Del Perú |
Castañeda, Benjamín | Pontificia Universidad Católica Del Perú |
Keywords: Ultrasound imaging - Elastography, Image reconstruction and enhancement - Machine learning / Deep learning approaches
Abstract: Reverberant Shear Wave Elastography (RSWE) is an ultrasound elastography technique that offers great advantages, however, current estimators generate underestimations and time-consuming issues. As well, the involvement of Deep Learning into the medical imaging field with new tools to assess complex problems, makes it a great candidate to serve as a new approach for a RSWE estimator. This work addresses the application of a Deep Neural Network (DNN) for the estimation of Shear Wave Speed (SWS) maps from particle velocity using numerically simulated data. The architecture of the proposed network is based on a U-Net, which works with a custom loss function specifically adopted for the reconstruction task. Four DNNs were trained using four different databases: clean, noisy, acquired at variable frequency, and noisy and acquired at variable frequency data. After the training of the DNNs, the predicted SWS maps were evaluated based on different metrics related to segmentation, regression and similarity of images. The model for clean data showed better results with a Mean Absolute Error (MAE) of 0.011, Mean Square Error(MSE) of 0.001, modified Intersection over Union (mIoU) of 98.4%, Peak Signal to Noise Ratio (PSNR) of 32.925 and a Structural Similarity Index Measure (SSIM) of 0.99, for 250 (size of Testing Sets); while the other models delivered SSIM in the range of ~0.87 to ~0.96. It was concluded that noisy and clean data could be effectively handled by the model, while the other ones still need enhancement.
|
|
15:45-17:30, Paper ThEP-10.6 | |
Dynamic 3D Ultrasound Imaging of the Tibialis Anterior Muscle |
|
Sahrmann, Annika Stephanie | University of Stuttgart |
Gizzi, Leonardo | University of Stuttgart |
Zanker, Annika | University of Stuttgart |
Handsfield, Geoffrey | University of Auckland |
Röhrle, Oliver | University of Stuttgart |
Keywords: Ultrasound imaging - Other organs
Abstract: Skeletal muscle volume has been mainly investigated under static conditions, i.e. isometric contractions. The aim of our study is to use ultrasound imaging to determine muscle deformation during movement. We used a custom designed scanning rig to obtain 3D ultrasound images of a subject moving the foot from plantarflexion to dorsiflexion at constant velocity. Using motion capture, we computed the respective angle of the ankle for each frame and collected them in bins based on the measured angle (rounded on the next normal number). For each degree, we used Stradwin for the 3D reconstruction of the respective volume. We found increasing cross-sectional areas for increasing dorsiflexion angles. The proposed method is a promising approach for determining muscle volume during movement. Future studies aim at collecting more data to compute muscle volume and length during contraction and compare the results to isometric measurements.
|
|
15:45-17:30, Paper ThEP-10.7 | |
Panoramic Reconstruction of B-Mode Lung Ultrasound Images Acquired Using a Longitudinal Volume Sweep Imaging Protocol |
|
Alarcón, Rodrigo | Pontificia Universidad Católica Del Perú |
Romero, Stefano | Pontificia Universidad Católica Del Perú |
Guevara, Naomi | Pontificia Universidad Católica Del Perú |
Montoya, Ximena | Pontificia Universidad Católica Del Perú |
Rios, Gloria | Medical Innovation and Technology |
Terrones, Rosa | Medical Innovation and Technology |
Marini, Thomas | University of Rochester |
Castañeda, Benjamín | Pontificia Universidad Católica Del Perú |
Keywords: Ultrasound imaging - Other organs, Image visualization
Abstract: The ongoing COVID-19 pandemic has already affected more than 300 million people worldwide. Medical imaging shortage affects an estimated of 4 billion people, especially in rural and remote areas (RAs), limiting diagnostic assessment of respiratory illness. Lung ultrasound imaging (LUS) together with volume sweep imaging (VSI) acquisition protocols have been successfully piloted as a solution for lung screening in RAs eliminating the need for trained operators and on-site radiologists. Nevertheless, this protocol requires the acquisition of 12 videos for 6 areas with both longitudinal and transverse positions of the transducer. Nonetheless, bandwidth limitations can hamper the transmission of these videos for remote interpretation. This work aimed to developed a stitching algorithm capable of generating a panoramic reconstruction of LUS cine clips. The results show reconstructions with minimal loss of information as 92.5% of the panoramic images conserved the presence of A-lines. These results show that LUS can be represented as an image without significantly compromising its quality. This can be useful to overcome bandwidth issues as well as improve the time on lung assessment of the patient.
|
|
15:45-17:30, Paper ThEP-10.8 | |
Deep Estimation of Speckle Statistics Parametric Images |
|
kafaei Zad Tehrani, Ali | PhD Student at Concordia University |
Rivaz, Hassan | Concordia University |
Rosado-Mendez, Ivan Miguel | Instituto De Fisica, Universidad Nacional Autonoma De Mexico |
Keywords: Ultrasound imaging - Other organs, Image analysis and classification - Machine learning / Deep learning approaches, Image registration, segmentation, compression and visualization - Volume rendering
Abstract: Quantitative Ultrasound (QUS) provides important information about the tissue properties. QUS parametric image can be formed by dividing the envelope data into small overlapping patches and computing different speckle statistics such as parameters of the Nakagami and Homodyned K-distributions (HK-distribution). The calculated QUS parametric images can be erroneous since only a few independent samples are available inside the patches. Another challenge is that the envelope samples inside the patch are assumed to come from the same distribution, an assumption that is often violated given that the tissue is usually not homogenous. In this paper, we propose a method based on Convolutional Neural Networks (CNN) to estimate QUS parametric images without patching. We construct a large dataset sampled from the HK-distribution, having regions with random shapes and QUS parameter values. We then use a well-known network to estimate QUS parameters in a multi-task learning fashion. Our results confirm that the proposed method is able to reduce errors and improve border definition in QUS parametric images.
|
|
15:45-17:30, Paper ThEP-10.9 | |
A Deep Learning Method for Kidney Segmentation in 2D Ultrasound Images |
|
Valente, Simão | 2Ai - School of Technology, IPCA, Barcelos, Portugal |
Morais, Pedro | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Torres, Helena | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Oliveira, Bruno | 2Ai - Applied Artificial Intelligence Laboratory |
Gomes-Fonseca, João | 2Ai – School of Technology, IPCA, Barcelos, Portugal |
Buschle, L. R. | Karl Storz SE & Co. KG, Tuttlingen, Germany |
Fritz, Andreas | Karl Storz SE & Co. KG, Tuttlingen, Germany |
Correia-Pinto, Jorge | Life and Health Sciences Research Institute (ICVS), School of Me |
Lima, Estêvão | ICVS/3Bs |
Vilaça, João | 2Ai - Applied Artificial Intelligence Laboratory |
Keywords: Ultrasound imaging - Other organs, Image segmentation, Machine learning / Deep learning approaches
Abstract: Ultrasound (US) is a medical imaging modality widely used for diagnosis, monitoring, and guidance of surgical procedures. However, the accurate interpretation of US images is a challenging task. Recently, portable 2D US devices enhanced with Artificial intelligence (AI) methods to identify, in real-time, specific organs are widely spreading worldwide. Nevertheless, the number of available methods that effectively work in such devices is still limited. In this work, we evaluate the performance of the U-NET architecture to segment the kidney in 2D US images. To accomplish this task, we studied the possibility of using multiple sliced images extracted from 3D US volumes to achieve a large, variable, and multi-view dataset of 2D images. The proposed methodology was tested with a dataset of 66 3D US volumes, divided in 51 for training, 5 for validation, and 10 for testing. From the volumes, 3792 2D sliced images were extracted. Two experiments were conducted, namely: (i) using the entire database (WWKD); and (ii) using images where the kidney area is > 500 mm2 (500KD). As a proof-of-concept, the potential of our strategy was tested in real 2D images (acquired with 2D probes). An average error of 2.88 ± 2.63 mm in the testing dataset was registered. Moreover, satisfactory results were obtained in our initial proof-of-concept using pure 2D images. In short, the proposed method proved, in this preliminary study, its potential interest for clinical practice. Further studies are required to evaluate the real performance of the proposed methodology.
|
|
ThEP-11 |
Hall 5 |
Theme 03. Micro/Nano-Bioengineering; Cellular/Tissue Engineering &
Biomaterials P1 |
Poster Session |
|
15:45-17:30, Paper ThEP-11.1 | |
Synthesis and Characterization of a New Alginate-Gelatine Aerogel for Tissue Engineering |
|
Greco, Immacolata | Université Libre De Bruxelles |
Varon, Carolina | Université Libre De Bruxelles |
Iorio, Carlo Saverio | Univesité Libre De Bruxelles |
Keywords: Scaffolds in tissue engineering, Biomimetic materials, Biomaterial-cell interactions - Engineered vascular tissue
Abstract: Scaffolds have been used to stimulate cell migration, cell adhesion, and cell proliferation as extracellular matrix analogues. This study proposes a novel method for creating hybrid alginate–gelatine aerogel-based scaffold, which could be suitable for cell adhesion. To this end, alginate-gelatine at 4% was first used to make stable hydrogels, which were then frozen at -70°C and dried under a vacuum to produce aerogels. Aerogels are materials known for their extremely low density, which, by definition, should be lower than 0.5 g/cm3. In this study, a bulk density of 0.16 g/cm3 was reached, confirming that the created material fits within the definition of an aerogel. In addition, the material presented a sponge-like structure, high absorption properties, and high-porosity, with an average pore size of 193µm. These properties fit within the requirements for fibroblast cell infiltrate and survival, demonstrating that the proposed alginate-gelatine aerogels are suitable candidates for various applications such as tissue engineering and regenerative medicine.
|
|
15:45-17:30, Paper ThEP-11.2 | |
Towards Non-Wettable Neural Electrodes for a Minimized Foreign Body Reaction |
|
Ashouri Vajari, Danesh | University of Freiburg |
Sharbatian, Ali | University of Freiburg |
Devkota, Kalyani | Uni Freiburg |
Stieglitz, Thomas | University of Freiburg |
Keywords: Biomimetic materials
Abstract: Functionality of neural implants can be seriously impaired by scarring during the foreign body reaction (FBR). Tailoring of the material-tissue interface is supposed to modulate part of the FBR. Surface structures might physically modulate the foreign body reaction in the acute phase directly after implantation. This work focuses on fabrication and characterization of bioinspired microtextures comprising reentrant cavities with non-wettable surface characteristics. The Selected microstructure patterns were fabricated using direct laser writing and were characterized by means of contact angle measurements and immersion tests.
|
|
15:45-17:30, Paper ThEP-11.3 | |
Recreating Cellular Barriers in Human Microphysiological Systems In-Vitro |
|
Mancinelli, Elena | University of Leeds |
Takuma, Megumi | Tokyo Institute of Technology |
Fujie, Toshinori | Tokyo Institute of Technology |
Pensabene, Virginia | University of Leeds |
Keywords: Microfluidic applications, Biomaterial-cell interactions - Biologics, Micro- and nano-technology
Abstract: Within cellular barriers, cells are separated by basement membranes (BMs), nanometer-thick extracellular matrix layers. In existing in-vitro cellular-barrier models, cell-to-cell signaling can be preserved by culturing different cells in individual chambers separated by a semipermeable membrane. Their structure does not always replicate the BM thickness nor diffusion through it. Here, a porous polymeric nanofilm made of poly(D-L-lactic acid) (PDLLA) is proposed to recreate the BM in a microfluidic blood-brain-barrier model. Nanofilms showed an average thickness of 275 nm ± 25 nm and a maximum pore diameter of 1.6 μm. Human umbilical vein endothelial cells (HUVECs) were cultured on PDLLA. After 7 days, viability was >95% and cell morphology did not show relevant differences with HUVECs grown on control substrates. A protocol for suspending the nanofilm between 2 microfluidic chambers was identified and showed no leakage and good sealing.
|
|
15:45-17:30, Paper ThEP-11.4 | |
Nanoparticle Rigidity for Brain Tumor Cell Uptake |
|
Kuo, Chung-Fan | University of Houston |
Mirab, Fereshtehsadat | University of Houston |
Abidian, Mohammad Reza | University of Houston |
Majd, Sheereen | University of Houston |
Keywords: Micro- and nano-technology, Biomaterial-cell interactions - Functional biomaterials
Abstract: Nanoparticles (NPs) have emerged as versatile and widely used platforms for a variety of biomedical applications. For delivery purposes, while some of NPs’ physiochemical aspects such as size and shape have been extensively studied, their mechanical properties remain understudied. Recent studies have reported NPs’ rigidity as a significant factor for their cell interactions and uptake. Here, we aim to study how NPs’ rigidity affects their interactions with brain glioma tumor cells. To produce NPs with different rigidities, we encapsulate poly(ethylene glycol) diacrylate (PEGDA) of different volume ratios (0, 10, 30 v/v%) within the lumen of nanoliposomes and study the uptake of these NPs in a glioblastoma cell line U87. PEGDA with volume ratios of 10 and 30% were selected to provide a significant increase of the elastic modulus of the hydrogel (0.1 to 4 MPa) as determined by compression testing. Dynamic light scattering (DLS) and zeta potential measurements indicated that despite differences in their core formulation, all examined NPs had a similar size range (106 to 132 nm) and surface charge (-2.0 to -3.0 mV). Confocal microscopy revealed that all NP groups accumulated inside U87 cells, and flow cytometry data showed that liposomes with a gel core (10 and 30 v/v% PEGDA) had significantly higher cellular uptake (up to 9-fold), compared to liposomes with an aqueous core. Notably, we did not find any substantial difference between the uptake of liposomes with PEGDA core of 10 and 30% volume ratios.
|
|
15:45-17:30, Paper ThEP-11.5 | |
Development of an Intervertebral Disc for Cervical Spondylosis Composed of Seeded Biomaterials |
|
Vasquez-Alvarez, Mariana | Universidad EAFIT |
Zapata, Uriel | EAFIT University |
Casado, Fanny | Pontificia Universidad Catolica Del Peru |
Keywords: Biomaterial-cell interactions - Functional biomaterials, Translational issues in tissue engineering and biomaterials - Osseointegration, Scaffolds in tissue engineering - Fabrication of cell seeded scaffolds
Abstract: Most of the current artificial disc prosthesis presented a restricted range of motion. Here we propose the design of a novel intervertebral disc composed of carbon fiber, hyaluronic methylcellulose hydrogel loaded with mesenchymal stem cells and polycaprolactone. The prosthesis was biomechanically evaluated under two static physiological conditions to study the mechanical influence of the material on the device. The results obtained in the simulations showed a not only a congruent behavior with preclinical condition, but also that the proposed materials met the desired biomechanical properties Clinical Relevance— Cervical spondylosis is a degenerative disease of the human spine that causes wear and tear of the cervical intervertebral discs. Nowadays, the proposed surgical solutions do not allow fully recovery of normal movement because the surgical intervention do not emulate the natural range of motion, may lack shock absorption mechanisms, show signs of fatigue over time affecting its durability, and do not have good bone adhesion. Therefore, hypermobility and problems of heterotopic ossification may restrict the range of motion.
|
|
ThEP-12 |
Hall 5 |
Theme 04. Tissue and Organ Modeling |
Poster Session |
|
15:45-17:30, Paper ThEP-12.1 | |
Anatomically Constrained Gastric Slow Wave Localization Using Biomagnetic Data |
|
Eichler, Chad Ephraim | Auckland Bioengineering Institute, the University of Auckland |
Cheng, Leo K | The University of Auckland |
Paskaranandavadivel, Niranchan | The University OfAuckland |
Angeli-Gordon, Timothy Robert | Auckland Bioengineering Institute, University of Auckland |
Du, Peng | The University of Auckland |
Bradshaw, Alan | Vanderbilt University |
Avci, Recep | The University of Auckland |
Keywords: Computational modeling - Analysis of high-throughput systems biology data
Abstract: Detection of dysrhythmic gastric slow wave (SW) activity could have significant clinical utility because dysrhythmias have been linked to gastric motility disorders. The electrogastrogram (EGG) and magnetogastrogram (MGG) enable the non-invasive assessment of SW activity, but most analysis methods can only resolve frequency and velocity. Improved characterization of dysrhythmic propagation patterns from non-invasive measurements is important for the diagnosis of motility disorders and could allow early treatment stratification. In this study, we demonstrate the use of a penalized linear regression framework to localize SW events on the longitudinal stomach axis using simulated MGG data. Priors relating to spatial sparsity, the organization of wavefronts into complete circumferential rings, and the local distribution of depolarization and repolarization phases were used to constrain the inverse solution. This method was applied to MGG computed for a single wavefront case and a multiple wavefront case that were constructed from simulated 3 cycle-per-minute normal SW activity. Propagation patterns along the longitudinal stomach axis were identifiable from reconstructed SW activity for both cases. Localization error was 5.7 ± 0.1 mm and 7.7 ± 0.1 mm for each respective case within the distal stomach when the signal-to-noise ratio was 10 dB. Results indicate that penalized linear regression can successfully localize SW events provided the 3D geometry of the stomach and torso were acquired.
|
|
15:45-17:30, Paper ThEP-12.2 | |
Investigating the Effects of Anatomical Structures on the Induced Electric Field in the Brain in Transcranial Magnetic Stimulation |
|
Zhong, Xiaojing | Tsinghua University |
Jiang, Hanjun | Tsinghua University |
Jiles, David C. | Iowa State University |
Wang, Zhihua | Tsinghua University |
Li, Jingyi | China Medical University |
Song, Bing | Shenzhen Institute of Advanced Technology, Chinese Academy of Sc |
Keywords: Computational modeling - Biological networks
Abstract: Transcranial magnetic stimulation (TMS) is capable of stimulating neurons in the brain non-invasively and provides numerous possibilities for the treatment of various neurological disorders such as major depressive disorder, Parkinson’s disease, obsessive compulsive disorder. TMS coils can affect the distribution of induced electric fields significantly, thus the design of TMS coils is always a popular topic in TMS studies. Yet the importance of the role of anatomical structures in the induced electric field has not been thoroughly investigated. Therefore, this work has compared the strength of electric fields induced from fifty realistic head models with twelve commercial or novel TMS coils to explore how anatomical structures affect the electric field. It has been found that the electric field strengths among the fifty head models showed highly correlated patterns. The coils were placed at two positions, where all the twelve coils were placed at the vertex and eight of them were placed at the dorsolateral prefrontal cortex of the head due to the coil geometry. Notably, fifty heterogeneous head models that are derived from MRI data were used in the simulations for examining the difference on the performance of TMS coils caused by different anatomical structures. A total of one thousand simulations have been conducted, providing a large amount of data for analysis.
|
|
15:45-17:30, Paper ThEP-12.3 | |
Integration of Surrogate Huxley Muscle Model into Finite Element Solver for Simulation of the Cardiac Cycle |
|
Milicevic, Bogdan | Faculty of Engineering, University of Kragujevac |
Simic, Vladimir | BioIRC, Research and Development Center for Bioengineering, Krag |
Milosevic, Miljan | BioIRC, Research and Development Center for Bioengineering, Krag |
Ivanovic, Milos | Faculty of Science, University of Kragujevac |
Stojanovic, Boban | Faculty of Science, University of Kragujevac |
Kojic, Milos | BioIRC, Research and Development Center for Bioengineering, Krag |
Filipovic, Nenad | University of Kragujevac |
Keywords: High throughput data - Machine learning and deep learning, Models of organ physiology, Data-driven modeling
Abstract: Clinicians can use biomechanical simulations of cardiac functioning to evaluate various practical and fictional events. Our present understanding of the molecular processes behind muscle contraction has inspired Huxley-like muscle models. Huxley-type muscle models, unlike Hill-type muscle models, can model non-uniform and unstable contractions. Huxley's computing needs, on the other hand, are substantially higher than those of Hill-type models, making large-scale simulations impractical to use. We created a data-driven surrogate model that acts similarly to the original Huxley muscle model but requires substantially less processing power in order to make the Huxley muscle models easier to use in computer simulations. We gathered data from multiple numerical simulations and trained a deep neural network based on gated-recurrent units. Once we accomplished satisfying precision we integrated the surrogate model into our finite element solver and simulated a full cardiac cycle. Clinical Relevance— This enables clinicians to track the effects of changes in muscles at the microscale to the cardiac contraction (macroscale).
|
|
15:45-17:30, Paper ThEP-12.4 | |
Computational Modelling of Human Femur after Total Hip Arthroplasty |
|
Gkaintes, Orestis | Unit of Medical Technology and Intelligent Information Systems, |
Potsika, Vassiliki | Unit of Medical Technology and Intelligent Information Systems, |
Loukas, Vasileios | Research Committee of the University of Ioannina, GR 45110 Ioann |
Gkiatas, Ioannis | Department of Orthopaedic Surgery, University of Ioannina, Schoo |
Pakos, Emilios | Laboratory of Biomechanics, School of Medicine, University of Io |
Fotiadis, Dimitrios I. | University of Ioannina |
|
|
15:45-17:30, Paper ThEP-12.5 | |
A Transmurally Heterogeneous Model of the Ventricular Tissue and Its Application for Simulation of Brugada Syndrome |
|
Biasi, Niccolò | University of Pisa |
Seghetti, Paolo | Scuola Superiore Sant'Anna |
tognetti, alessandro | University of Pisa |
Keywords: Modeling of cell, tissue, and regenerative medicine - 2d and 3d cell modeling, Data-driven modeling, Model building - Parameter estimation
Abstract: We present a transmurally heterogeneous phenomenological model of ventricular tissue that is designed to reproduce the most important features of action potential propagation of endocardial, midmyocardial, and epicardial tissue. Our model consists of only 3 variables and 20 parameters. Therefore, it is highly computational efficient and easy to fit to experimental data. We exploited our myocyte model to simulate action potential propagation in a 3D slab of cardiac tissue both in healthy conditions and in presence of Brugada syndrome. The results show that our model can accurately reproduce the transmural heterogeneity of the ventricular wall and the main characteristics of electrocardiographic pattern both in healthy and pathological conditions.
|
|
15:45-17:30, Paper ThEP-12.6 | |
Numerical Analysis of Temperature Distribution Profiles of Breast Tissues with Cyst and Tumor of Different Sizes and Locations |
|
SINHA, KUMAR NANDAN | Indian Institute of Technology, Madras |
Makaram, Navaneethakrishna | Indian Institute of Technology Madras |
Chaudhuri, Abhijit | Indian Institute of Technology, Madras |
Ramakrishnan, Swaminathan | IIT Madras, India |
Keywords: Models of organ physiology, Data-driven modeling, Systems modeling - Patient stratification
Abstract: Breast cancer causes more deaths among all types of cancers. Efforts have been put to study the change in temperature distribution profile of breast in presence of abnormality. By applying Pennes’s bio-heat equation, a 2D finite element model is developed for heat transfer mechanism. Surface temperature gradients due to presence of abnormalities at various depths and sizes are analyzed. The results shows that presence of cyst decreases the temperature whereas the occurence of a tumor increases temperature inside breast. It is observed that abnormal tissue having radius less than 1.5cm and depth greater than 5cm, have negligible effect on the surface temperature profile. The highest change of surface temperature is observed when cyst or tumor is larger and present near the skin. The simulation results help in the better interpretation of the thermal images and calibration of infrared camera. This study could be helpful in early diagnosis of breast cancer.
|
|
15:45-17:30, Paper ThEP-12.7 | |
Influence of Wall-Lumen Ratio of Umbilical Arteries on the Stress Distribution in Wharton's Jelly |
|
Pande, Omkar | Indian Institute of Technology Madras |
Makaram, Harikrishna | Indian Institute of Technology Madras |
Ramakrishnan, Swaminathan | IIT Madras, India |
Keywords: Models of organ physiology, Organ modeling
Abstract: Umbilical Cord is the link between fetus and the placenta. It consists of one vein and two arteries, encased inside Wharton’s jelly. In this study, the influence of morphological parameters of umbilical arteries, namely the wall-lumen ratio and lumen diameter, on the stress distribution in Wharton’s jelly is analyzed using a 3D finite element model. The lumen diameter of the arteries is varied from 0.4 mm to 2.0 mm in steps of 0.4 mm. The variation of average and maximum effective stresses in the Wharton’s jelly with wall-lumen ratio is analyzed. Further, differences in stresses between the placental and fetal ends of umbilical cord are analyzed. Results show that, the average and maximum effective stresses at both ends of the umbilical cord vary nonlinearly with the wall-lumen ratio. For all the considered lumen diameters, the average effective stress is found to decrease with an increase in wall-lumen ratio at both the ends. An increase in the lumen diameter is found to be associated with a nonlinear decrease in average stress ratios. Clinical Relevance— The results of this study could be useful for the early diagnosis of fetal abnormalities and might be helpful to develop better treatment strategies.
|
|
15:45-17:30, Paper ThEP-12.8 | |
An Aqueous Humour Fluid Dynamic Study for Normal and Glaucomatous Eye Conditions |
|
Basson, Nicol | University of the Witwatersrand |
Alimahomed, Fatma | Aston University |
Geoghegan, Patrick Henry | Aston University |
Williams, Susan Eileen | University of Witwatersrand |
Ho, Wei Hua | University of Witwatersrand |
Keywords: Organ modeling
Abstract: Glaucoma is the leading cause of irreversible blindness worldwide. Currently, the only treatable risk factor for glaucoma is elevated intraocular pressure (IOP). Glaucoma is commonly caused due to a decreased permeability of the trabecular meshwork, a porous structure at the eye outlet. This prevents the effective outflow of aqueous humour, increasing IOP. This study aims to simulate both normal and glaucomatous conditions of aqueous humour flow in the eye via computational fluid dynamics (CFD). Using clinical data, an idealised geometrical model of the eye was created. Darcy’s law was employed to calculate the permeability values for various IOPs, which was then applied to the CFD model. Subsequently, verifiable and validated models for a normal and glaucomatous eye were achieved.
|
|
15:45-17:30, Paper ThEP-12.9 | |
Computational Fluid Dynamic Model of Left Atrium to Analyze Hemodynamic Manifestation During Atrial Fibrillation |
|
Mazumder, Oishee | Tata Consultance Services |
Gupta, Shivam | Indian Institute of Technology (Indian School of Mines) Dhanbad, |
Roy, Dibyendu | TCS Research |
Sinha, Aniruddha | Tata Consultancy Services Ltd |
Keywords: Systems modeling - Patient stratification, Models of organ physiology, Computational modeling - Analysis of high-throughput systems biology data
Abstract: In this paper, we present a computational fluid dynamic (CFD) model of left atrium (LA) to analyze the manifestation and progression of atrial fibrillation (AF) in terms of hemodynamic metrics. We propose a coupled lumped-CFD (0d-3d) pipeline to model and predict the pulsatile flow and pressure fields of three-dimensional cardiac chamber under the influence of sinus rhythm, high frequency AF (HF-AF) and LA remodeled AF, considering the interactions between the heart and the arterial system through a separately modeled 0d lumped hemodynamic cardiac model. A novel rhythm generator is modeled to generate modulated cardiac chamber compliance and decoupled auricular and ventricular contraction rate to synthesize variation in sinus rhythm and subsequent AF generation. CFD simulation were solved using subject specific CT scan. Systemic and pulmonary flow and pressure along with metrics related to wall shear stress in LA were derived. Left ventricular (LV) hemodynamic parameters associated with global cardio vascular evaluation like ejection fraction, stroke volume, cardiac output, etc. were also generated for all the rhythmic disturbance under consideration. The proposed 0d-3d coupled hemodynamic model of the LA can provide useful insights on the dynamics of AF manifestation and predict vulnerable regions in the cardiac chambers as well as arterial vasculature for probable thrombogenic plaque formation that leads to stroke and infraction, leading to heart failure.
|
|
ThEP-13 |
Hall 5 |
Theme 05. Cardiovascular Modeling |
Poster Session |
|
15:45-17:30, Paper ThEP-13.1 | |
Numerical Analysis on Effect of Coronary Supply-Demand Equilibrium on Varying Coronary Blockage and Stress Conditions |
|
Mazumder, Oishee | Tata Consultance Services |
Gupta, Shivam | Indian Institute of Technology (Indian School of Mines) Dhanbad, |
Roy, Dibyendu | TCS Research |
khandelwal, sundeep | Tata Consultancy Services |
Sinha, Aniruddha | Tata Consultancy Services Ltd |
Keywords: Vascular mechanics and hemodynamics - Vascular Hemodynamics, Cardiovascular and respiratory system modeling - Cardiovascular Disease, Coronary blood flow
Abstract: In this paper, we present a computational fluid dynamic (CFD) analysis to capture the effect of physical stress and stenosis severity in coronary arteries leading to changes in coronary supply demand oxygen equilibrium. We propose a coupled 0d-3d coronary vessel model to predict the variation in flow dynamics of coronary as well as arterial system, modeled using an in-silico model replicating cardiovascular hemodynamics. CFD simulation were solved using subject specific CT scan for coronary and arterial flow and pressure along with metrics related to arterial wall shear stress. Simulations were performed for three heart rates (75, 90 and 120 bpm) and four stenosis states representing different stages of Coronary artery disease (CAD) namely healthy, 50%, 75%, 90% blockage in left anterior descending artery (LAD). Myocardial oxygen supply demand equilibrium were calculated for each cases using hemodynamic surrogate markers naming Diastolic pressure time index for supply and Tension time index for demand. The proposed 0d3d coupled hemodynamic model of the coronary vessel bed along with supply-demand equilibrium estimated for different stress level and stenosis severity may provide useful insights on the dynamics of CAD manifestation and predict vulnerable regions in coronary bed for early screening and interventions.
|
|
15:45-17:30, Paper ThEP-13.2 | |
Helical Flow in Healthy and Diseased Patient-Specific Coronary Bifurcations |
|
SHEN, CHI | University of New South Wales |
Gharleghi, Ramtin | University of New South Wales |
Li, Darson Dezheng | UNSW Sydney |
Beier, Susann | University of New South Wales |
Keywords: Coronary blood flow, Vascular mechanics and hemodynamics - Vascular Hemodynamics, Coronary artery disease
Abstract: Helical flow (HF) exists in healthy and diseased coronary bifurcations and was found to have a protective atherosclerotic vascular effect in other vessels. However, the role of HF in patient-specific human coronary arteries still needs further study, and is therefore the objective of this study in both healthy and diseased bifurcations. Computational studies were conducted on 16 patient-specific coronary bifurcations, including eight healthy and eight identical cases with idealized narrowing to represent disease. In general, higher HF intensity may have a favorable effect as it corelated to the reduction of the percentage vessel area exposed to adverse time averaged wall shear stress (TAWSS%) in both healthy and diseased models. The HF intensity and distribution of each model varies due to the complex shape of patient-specific models. The presence of disease appears to have an important impact on the downstream HF patterns and the TAWSS distributions.
|
|
15:45-17:30, Paper ThEP-13.3 | |
Bayesian Model Averaging for Improving the Accuracy of Cuffless Blood Pressure Estimation |
|
Shen, Zhan | University of Electronic Science and Technology of China |
Liu, Lei | University of Electronic Science and Technology of China |
Ding, Xiao-Rong | University of Electronic Science and Technology of China |
Keywords: Cardiovascular and respiratory signal processing - Blood pressure measurement, Cardiovascular and respiratory signal processing - Pulse transit time, Cardiovascular, respiratory, and sleep devices - Wearables
Abstract: In recent decades, many researches have proposed various models for continuous, cuffless blood pressure (BP) estimation. However, due to aleatoric uncertainty and epistemic uncertainty existing in the problem, it is very challenging to evaluate cuffless BP with acceptable accuracy. This paper innovatively proposes a cuffless BP ensemble estimation model based on Bayesian Model Average (BMA) method to reduce the epistemic uncertainty. We combine four most frequently cited physiological models and four regression models based on Photoplethysmogram (PPG) and Electrocardiogram (ECG) signals, and use the BMA method to assign weights to each model to achieve accurate cuffless BP prediction. The proposed method was validated on 17 healthy and 13 hypertensive subjects with continuous Finometer BP as a reference. The results showed that the error mean ± SD (standard deviations) of both SBP and DBP predicted by the proposed method were 2.13 ± 5.68 mmHg and 1.42 ± 5.11 mmHg, respectively, which were both lower than each of the model. And the MAE was 6% and 8% lower than the best member of the model ensemble. We also analyzed the relationship between the number of training epochs and model prediction performance. When 15 cardiac cycles were choosed for training, it could get a good balance between model prediction accuracy and algorithm complexity. Therefore, the proposed BMA method can solve the model uncertainty problem, providing robust and deterministic BP prediction.
|
|
15:45-17:30, Paper ThEP-13.4 | |
A Proof-Of-Concept Study for the Simulation of Blood Flow in a Post Arterial Segment for Different Blood Rheology Models |
|
Karanasiou, Giannoula | University of Ioannina |
Loukas, Vasileios | Research Committee of the University of Ioannina, GR 45110 Ioann |
Tsompou, Panagiota | Unit of Medical Technology and Intelligent Information Systems, |
Karanasiou, Georgia | Institute of Molecular Biology and Biotechnology, FORTH, Ioannin |
Kyriakidis, Savvas | Institute of Molecular Biology and Biotechnology, FORTH |
Antonini, Luca | Department of Chemistry, Materials and Chemical Engineering “Giu |
Poletti, Gianluca | Politecnico Di Milano |
Pennati, Giancarlo | Department of Chemistry, Materials and Chemical Engineering Depa |
Papafaklis, Michail | Medical School, University of Ioannina |
Gergidis, Leonidas | University of Ioannina, Department of Material Science and Engin |
Fotiadis, Dimitrios I. | University of Ioannina |
Sakellarios, Antonis | Forth-Biomedical Research Institute |
Keywords: Vascular mechanics and hemodynamics - Vascular Disease, Coronary artery disease, Coronary blood flow
Abstract: Cardiovascular disease (CVD) and especially atherosclerosis are chronic inflammatory diseases which cause the atherosclerotic plaque growth in the arterial vessels and the blood flow reduction. Stents have revolutionized the treatment of this disease to a great extent by restoring the blood flow in the vessel. The present study investigates the performance of the blood flow after stent implantation in patient-specific coronary artery and demonstrates the effect of using Newtonian vs. non-Newtonian blood fluid models in the distribution of endothelial shear stress. In particular, the Navier-Stokes and continuity equations were employed, and three non-Newtonian fluid models were investigated (Carreau, Carreau-Yasuda and the Casson model). Finite elements models were used for the simulation of blood flow. The comparison of the results demonstrates that the Newtonian fluid model underestimates the calculation of Endothelial Shear Stress, while the three non-Newtonian fluids present similar distribution of shear stress. Keywords: Blood flow dynamics, stented artery, non-Newtonian fluid. Clinical Relevance— This work demonstrates that when blood flow modeling is performed at stented arteries and predictive models are developed, the non-Newtonian nature of blood must be considered.
|
|
15:45-17:30, Paper ThEP-13.5 | |
Comparison of Approximated and Actual Bramwell-Hill Equation Implementation for Local Pulse Wave Velocity: Ex-Vivo Study |
|
V, Raj Kiran | IIT Madras |
Manoj, Rahul | Indian Institute of Technology Madras |
Ishwarya, S | Healthcare Technology Innovation Centre |
P M, Nabeel | Indian Institute of Technology Madras |
Joseph, Jayaraj | HTIC, Indian Institute of Technology Madras |
Keywords: Vascular mechanics and hemodynamics - Pulse wave velocity, Vascular mechanics and hemodynamics - Vascular Hemodynamics, Vascular mechanics and hemodynamics - Vascular mechanics
Abstract: Bramwell-Hill (BH) equation is widely adopted for the evaluation of local pulse wave velocity (PWV), primarily for its theoretical association with the vessel’s distensibility. Its implementation, however, requires arterial pressure and diameter waveforms simultaneously from a single site. Owing to the challenges associated with such a noninvasive recording, an approximated BH equation is adopted without requiring the entire pressure waveform but only the diastolic and systolic values. The approximated BH method yields a single value of local PWV as opposed to the actual method that provides instantaneous PWV within a cardiac cycle. This study aims to provide the currently lacking insights into how the approximate versus actual BH implementations compare. The study also addresses the pivotal question of which instantaneous value within the cardiac cycle corresponds to the approximated BH. An ex-vivo study was conducted for this purpose, emulating different flow conditions (changing mean and pulse pressures) to vary the local PWV within the range of 4.4 to 8.9 m/s. The results revealed the expected (pressure-dependent) incremental nature of local PWV due to hyper-elastic behavior of the artery, with systolic BH-PWV > diastolic BH-PWV by 13.6%. The approximate BH-PWV was similar to actual BH-PWV obtained from mean pressure level. It further underestimated the systolic, and overestimated the diastolic PWVs by 8.5% and 6.6%, respectively.
|
|
15:45-17:30, Paper ThEP-13.6 | |
Simulating Stenotic Conditions of the Coronary Artery in a Lumped Parameter Model of the Cardiovascular System |
|
Sahoo, Karuna Prasad | Indian Institute of Technology, Kharagpur |
DASH, ASHUTOSH | Indian Institute of Technology, Kharagpur |
Ghosh, Nirmalya | Indian Institute of Technology (IIT), Kharagpur |
Patra, Amit | Indian Institute of Technology Kharagpur |
Sinha, Aniruddha | Tata Consultancy Services Ltd |
khandelwal, sundeep | Tata Consultancy Services |
Keywords: Cardiovascular and respiratory system modeling - Cardiac models, Cardiovascular and respiratory system modeling - Compartmental modeling, Coronary blood flow
Abstract: Coronary flow control mechanisms maintain the average coronary blood flow (CBF) at 4% of the cardiac output (CO) in normal adults, with no prior diagnosis of coronary artery disease (CAD), under resting conditions. This paper explores a pulsatile sixth order lumped parameter (LP) model of the cardiovascular system (CVS) which utilizes the average CBF approximated from CO along with arterial blood pressure (ABP) waveform to estimate the coronary microvascular resistance using non-linear least square optimization techniques. The CVS model includes a third order model of the coronary vascular bed and is shown to achieve phasic coronary flow. The coronary epicardial resistance is varied to emulate different degrees of stenosis and achieve realistic behavior of coronary microvascular resistance under these conditions.
|
|
15:45-17:30, Paper ThEP-13.7 | |
Association of Local Arterial Stiffness and Windkessel Model Parameters with Ageing in Normotensives and Hypertensives |
|
Sudarsan, Nimmi | IIT Madras - EE Dept. - HTIC Lab |
Manoj, Rahul | Indian Institute of Technology Madras |
P M, Nabeel | Indian Institute of Technology Madras |
Sivaprakasam, Mohanasankar | Indian Institute of Technology Madras |
Joseph, Jayaraj | HTIC, Indian Institute of Technology Madras |
Keywords: Vascular mechanics and hemodynamics - Vascular Hemodynamics, Cardiovascular and respiratory system modeling - Blood flow models
Abstract: Computation of arterial stiffness is a well-established, widely accepted method for estimating vascular age. Although carotid-femoral pulse wave velocity is typically used for vascular age assessment, most recent studies have reported the need to consider a combination of local and regional stiffness indices possessing distinct association with the vascular structure and/or function for better prediction of early prediction vascular ageing syndrome. In this work, we investigate the association of clinically validated local stiffness (obtained using biomechanical relations), global stiffness (obtained from 3-element Windkessel modelling), and pulse contour indices from the aorta with ageing and their distribution in normotensives and hypertensives. The analysis was performed on 420 (virtual) subjects (age: 65 ± 11 years) with an equal proportion of hypertensive (age: 65 ± 11 years) and normotensive (age: 65 ± 11 years) subjects. Multivariate linear regression analysis revealed an independent association of each of the indices with age (Adjusted r = 0.75 p < 0.01). Specific stiffness index (r = 0.67, p < 0.001), Augmentation index (r = 0.55, p < 0.001) and total arterial compliance (r = -0.50, p < 0.001) depicted highest correlation with age. There was a significant difference (> 16%, p < 0.001) in mean values of the measured indices between hypertensive and normotensive subjects. The study findings further emphasize the need to combine multiple non-invasive vascular markers to capture the unique aspects of age-induced arterial wall remodelling for reliable monitoring and management of the early vascular ageing syndrome.
|
|
15:45-17:30, Paper ThEP-13.8 | |
In Vitro Modelling for Bulging Sinus Effects of an Expanded Polytetrafluoroethylene Valved Conduit Based on High-Speed 3D Leaflet Evaluation |
|
Shiraishi, Yasuyuki | Tohoku University |
Narracott, Andrew James | University of Sheffield |
Yamada, Akihiro | Tohoku University |
Fukaya, Aoi | Tohoku University |
Sahara, Genta | Tohoku University |
Yambe, Tomoyuki | Tohoku Univ |
Keywords: Cardiac mechanics, structure & function - Artificial heart and valves, Vascular mechanics and hemodynamics - Pulmonary Circulation, Cardiovascular and respiratory system modeling - Blood flow models
Abstract: The study aimed to develop a pulmonary circulatory system capable of high-speed 3D reconstruction of valve leaflets to elucidate the local hemodynamic characteristics in the valved conduits with bulging sinuses. Then a simultaneous measurement system for leaflet structure and pressure and flow characteristics was designed to obtain valve leaflet dynamic behaviour with different conduit structures. An image preprocessing method was established to obtain the three leaflets behaviour simultaneously for one sequence with two leaflets images from each pair of three high-speed cameras. Firstly, the multi-digital image correlation analyses were performed, and then the valve leaflet structure was measured under the static condition with fixed opening angles in the water-filled visualization chamber and the pulsatile flow tests simulating paediatric pulmonary flow conditions in the different types of conduit structures; with or without bulging sinuses. The results showed the maximum 3D reconstruction error to be around 0.06 mm. In the steady flow test, the evaluation of opening angles under the different flow rates conditions was achieved. In the pulsatile flow test, each leaflet's opening and closing behaviours were successfully reconstructed simultaneously at the high-frequency recording rate of 960fps. Therefore, the system developed in this study confirms the design evaluation method of an ePTFE valved conduit behaviour with leaflet structures interacting with local fluid dynamics in the vicinity of valves.
|
|
15:45-17:30, Paper ThEP-13.9 | |
Physiological Control Algorithm for a Pulsatile-Flow 3D Printed Circulatory Model to Simulate Human Cardiovascular System |
|
Peak, Preston | Texas Heart Institute |
Tedesco V, Victor | Texas Heart Institute |
Kiang, Simon | Rice University |
Smith, P. Alex | Texas Heart Institute at St. Luke's Hospital |
Nissim, Lee | University of Bath |
Fraser, Katharine H. | University of Bath |
Frazier, O.H. | Texas Heart Institute @ St. Luke's Hospital |
Wang, Yaxin | Texas Heart Institute |
Keywords: Cardiac mechanics, structure & function - Ventricular mechanics, Vascular mechanics and hemodynamics - Vascular Hemodynamics, Cardiovascular and respiratory system modeling - Vascular mechanics and hemodynamics
Abstract: The human heart is responsible for maintaining constant, pulsatile blood flow in the human body. Mock circulatory loops (MCLs) have long been used as the mechanical representations of the human cardiovascular system and as test beds for mechanical circulatory support (MCS) devices and other interventional medical devices. This technology could also be used as a training and educational tool for surgeons/clinicians. To ensure the MCL can accurately simulate the pulsatile human cardiovascular system, it is essential that the MCL can reproduce human physiological responses, e.g., the Frank-Starling Mechanism, in a controllable operating environment. In this study, by using an elastance function template to control the simulated left ventricle, we created controllable pulsatile physiological flow in a 3D printed silicone vascular structure to successfully simulate the hemodynamic environment of the human cardiovascular system.
|
|
ThEP-14 |
Hall 5 |
Theme 05. Imaging for Cardiovascular Diseases |
Poster Session |
Chair: Rad, Laleh Golestani | Northwestern University |
|
15:45-17:30, Paper ThEP-14.1 | |
Evaluation of Pulse Contour Markers Using an A-Mode Ultrasound: Association with Carotid Stiffness Markers and Ageing |
|
Manoj, Rahul | Indian Institute of Technology Madras |
V, Raj Kiran | IIT Madras |
P M, Nabeel | Indian Institute of Technology Madras |
Sivaprakasam, Mohanasankar | Indian Institute of Technology Madras |
Joseph, Jayaraj | HTIC, Indian Institute of Technology Madras |
Keywords: Vascular mechanics and hemodynamics - Vascular Hemodynamics, Cardiovascular and respiratory signal processing - Cardiovascular signal processing
Abstract: Vascular ageing is directly associated with the blood vessel wall structural and functional abnormalities. Pulse morphology carries information on these abnormalities, and pulse contour analysis (PCA) identifies key amplitudes and timing information on the pulse waveforms that has a prognostic value towards cardiovascular risk stratification. PCA markers derived from second derivative waveforms represent the accelerative and decelerative phase of an arterial pulse. In this work, second derivative diameter waveforms of central arteries such as carotid artery are obtained using an A-mode ultrasound device. The derived PCA markers (b/a, c/a, d/a, e/a, (b-c-d-e)/a) from diameter waveform is investigated for its association with central stiffness markers and aging. An observational and cross-sectional study on 106 subjects (51 male/55 females) was conducted for this investigation. The highest correlation (r = 0.5, p < 0.001) was observed between c/a and PWV, and the lowest correlation was between e/a and AC. Group average values of PCA markers for each age decade group was correlated strongly (r > 0.9, p < 0.001) with age. A change > 19% was observed between the group average values of PCA markers of the normotensive and hypertensive population. The applicability of aforesaid PCA markers on central pulse waveforms, measured using a noninvasive device in resource-limited field settings, would accelerate such large scale vascular screening that is essential to understand the cardiovascular risks at a population level.
|
|
15:45-17:30, Paper ThEP-14.2 | |
A Comparative Study of MRI-Induced RF Heating in Pediatric and Adult Populations with Epicardial and Endocardial Implantable Electronic Devices |
|
Jiang, Fuchang | Northwestern University |
Bhusal, Bhumi | Northwestern University |
Sanpitak, Pia | Northwestern Memorial Hospital |
Webster, Gregory | Ann and Robert H. Lurie Children's Hospital of Chicago |
Popescu, Andrada | Ann & Robert H. Lurie Children’s Hospital of Chicago |
Kim, Daniel | Northwestern University |
Bonmassar, Giorgio | Harvard Medical School, Massachusetts General Hospital |
Rad, Laleh Golestani | Northwestern University |
Keywords: Cardiac electrophysiology - Pacemakers
Abstract: Patients with congenital heart defects, inherited arrhythmia syndromes, and congenital disorders of cardiac conduction often receive a cardiac implantable electronic device (CIED). At least 75% of patients with CIEDs will need magnetic resonance imaging (MRI) during their lifetime. In 2011, the US Food and Drug Administration approved the first MR-conditional CIEDs for patients with endocardial systems, in which leads are passed through the vein and affixed to the endocardium. The majority of children, however, receive an epicardial CIED, where leads are directly sewn to the epicardium. Unfortunately, an epicardial CIED is a relative contraindication to MRI due to the unknown risk of RF heating. In this work, we performed anthropomorphic phantom experiments to investigate differences in RF heating between endocardial and epicardial leads in both pediatric and adult-sized phantoms, where adult endocardial CIED was the control.
|
|
15:45-17:30, Paper ThEP-14.3 | |
Operator Variabilities in Local Pulse Wave Velocity Measured by an Image-Free Ultrasound Device |
|
V, Raj Kiran | IIT Madras |
Manoj, Rahul | Indian Institute of Technology Madras |
Ishwarya, S | Healthcare Technology Innovation Centre |
P M, Nabeel | Indian Institute of Technology Madras |
Joseph, Jayaraj | HTIC, Indian Institute of Technology Madras |
Keywords: Vascular mechanics and hemodynamics - Pulse wave velocity, Vascular mechanics and hemodynamics - Vascular Hemodynamics, Vascular mechanics and hemodynamics - Vascular mechanics
Abstract: Local pulse wave velocity (PWV) has gained much attention in the last decade due to its ability to provide localized stiffness information from a target vessel and cater to several applications beyond regional PWV. Transit time-based methods are the most straightforward, but their reliability is highly dependent on the blood pulse sensing modality. Conventional ultrasound systems directly measure the blood pulse (as diameter or flow velocity); however, they offer limited frame rates resulting in poor resolution signals. Advanced systems supporting high frame rates are expensive, complex, and not amenable to field and resource-constraint settings. We have developed a high frame image-free ultrasound system to address this gap for automated and online measurement of local PWV. In an earlier in-vitro study, we have demonstrated its accuracy. In this work, we aim to investigate its in-vivo reliability. A study on 15 young, healthy subjects was conducted to assess the intra- and inter-operator repeatability of the developed system. The yielded local PWVs from the left carotid artery were within the range of 2.5 to 5.8 m/s. The device provided highly repeatable intra- and inter-operator measurements with ICC of 0.94 and 0.88, respectively. The bias for the intra- and inter-operator trials was statistically negligible (p > 0.005). The study demonstrated the potential of the high frame rate device to perform reliable measurements in-vivo.
|
|
15:45-17:30, Paper ThEP-14.4 | |
High Frame-Rate A-Mode Ultrasound System for Jugular Venous Pulse Tracking: A Feasibility Study |
|
George, Navya Rose | Indian Institute of Technology Madras |
V, Raj Kiran | IIT Madras |
P M, Nabeel | Indian Institute of Technology Madras |
Sivaprakasam, Mohanasankar | Indian Institute of Technology Madras |
Joseph, Jayaraj | HTIC, Indian Institute of Technology Madras |
Keywords: Cardiovascular and respiratory signal processing - Cardiovascular signal processing, Vascular mechanics and hemodynamics - Vascular Hemodynamics, Cardiovascular, respiratory, and sleep devices - Diagnostics
Abstract: Jugular venous pulse (JVP) helps in the early detection of central venous pressure abnormalities and various cardiovascular diseases. Studies have been reported indicating that contour features of the JVP waveform provide crucial information regarding cardiac function. Although current ultrasound systems reliably provide the diameter measurements, they are limited by low frame rates resulting in poor resolution JVP cycles that are inadequate to yield distinguishable critical points. In this work, we propose an image-free high frame rate system for the assessment of JVP signals. The proposed is an A-mode ultrasound system that acquires high fidelity JVP pulses with a temporal resolution of 4 ms and amplitude resolution of 10 μm. The functionality verification of the proposed system was performed by comparing it against a clinical-grade B-mode imaging system. A study was conducted on a cohort of 25 subjects in the 20-30 age group. While the system provided diameter measurements comparable to that of the imaging ones (r > 0.98, p < 0.05), it also yielded high-resolution JVP exhibiting the presence of all fiduciary points. This was a leveraging feature as opposed to the imaging system that possessed limited temporal and amplitude resolution.
|
|
ThEP-15 |
Hall 5 |
Theme 06. EEG for Neurorehabilitation |
Poster Session |
Chair: Rutkowski, Tomasz Maciej | RIKEN AIP |
|
15:45-17:30, Paper ThEP-15.1 | |
EEG-Based Evaluation of Motion Sickness and Reducing Sensory Conflict in a Simulated Autonomous Driving Environment |
|
Li, Zhibin | Tsinghua University |
Zhao, Leilei | Tsinghua University |
Chang, Jing | Tsinghua University |
Li, Wei | Tsinghua University |
Yang, Menghui | Tsinghua University |
Li, Chong | Tsinghua University |
WANG, Rencheng | Tsinghua University |
Ji, Linhong | Tsinghua University |
Keywords: Human performance - Driving, Brain functional imaging - EEG, Human performance - Vestibular functions
Abstract: Autonomous driving offers significant potential for changes in the automotive industry. However, sensory conflict during autonomous driving can lead to motion sickness. Quantitative evaluation and effective preventions to predict and reduce motion sickness are needed. The goal of this study is to verify the objective indicator of motion sickness level based on encephalography (EEG) that we proposed before and investigate the influence of attenuating sensory conflict on motion sickness. A 6-degree of freedom (DOF) driving simulator platform was used to provide an autonomous driving environment to the subjects, and the subjective motion sickness level (MSL), as well as the EEG signals of 15 healthy subjects, were collected simultaneously during 3 conditions, i) autonomous driving, ii) autonomous driving with eyes blindfolded and iii) active driving. The MSLs were reported by the subjects every two minutes, providing a reference to the recorded EEG signals. The EEG signals were analyzed and compared among different conditions. Average MSLs were higher in autonomous driving than in autonomous driving with eyes blindfolded and active driving, together with the increase of the mean EEG frequency of theta band in the central, parietal and occipital areas (FC5, Cz, CP5, P3, and POz). These findings validated that EEG mean frequency of theta band could be an indicator of motion sickness, besides an attenuated visual input or active control of the vehicle can effectively reduce the generation of motion sickness.
|
|
15:45-17:30, Paper ThEP-15.2 | |
Novel EEG-Based Neurofeedback System Targeting Frontal Gamma Activity of Schizophrenia Patients to Improve Working Memory |
|
Lin, Yayu | University of California, San Diego |
Shu, I-Wei | University of California, San Diego |
Hsu, Sheng-Hsiou | UCSD |
Pineda, Jaime | University of California, San Diego |
Granholm, Eric | University of California, San Diego |
Singh, Fiza | University of California, San Diego |
Keywords: Brain physiology and modeling - Cognition, memory, perception, Brain-computer/machine interface, Neural signal processing
Abstract: Patients with schizophrenia (SCZ) exhibit working memory (WM) deficits that are associated with deficient dorsal-lateral prefrontal cortical activity, including decreased frontal gamma power. We thus hypothesized that training patients with SCZ to increase frontal gamma activity would improve WM performance. In an open-label study of 30 participants with SCZ, we administered 12 weeks (24 sessions) of electroencephalographic (EEG) neurofeedback (NFB), which provides real-time visual and auditory feedback signals coupled to frontal gamma activity. EEG-NFB training significantly improved EEG markers of optimal WM, e.g., task-related frontal P3 amplitude and gamma power. Based on these promising results, we developed a novel, EEGLAB/MATLAB-based brain computer interface (BCI) designed to deliver F3-F4 gamma coherence NFB with dynamic threshold (versus placebo-NFB), to participants with SCZ randomized in a double-blind, placebo-controlled clinical trial. Data from the first 12 participants (n = 6/group) completing gamma- or placebo-NFB training support our novel BCI effectively increasing F3-F4 gamma coherence 12 weeks (24 sessions) of training.
|
|
15:45-17:30, Paper ThEP-15.3 | |
Using Pre-Stimulus EEG to Predict Driver Reaction Time to Road Events |
|
Ur Rahman, Shams | Dublin City University |
O'Connor, Noel | Dublin City University |
Lemley, Joe | Xperi |
Healy, Graham | Dublin City University |
Keywords: Human performance - Driving
Abstract: The ability to predict a driver's reaction time to road events could be used in driver safety assistance systems, allowing for autonomous control when a driver may be about to react with sup-optimal performance. In this paper, we evaluate a number of machine learning and feature engineering strategies that we use to predict the reaction time(s) of 24 drivers to road events using EEG (Electroencephalography) captured in an immersive driving simulator. Subject-independent models are trained and evaluated using EEG features extracted from time periods that precede the road events that we predict the reaction times for. Our paper has two contributions: 1) we predict the reaction times corresponding to individual road events using EEG spectral features from a time period before the onset of the road event, i.e. we take EEG data from 2 seconds before the event, and 2) we predict whether a subject will be a slow or fast responder compared to other drivers.
|
|
15:45-17:30, Paper ThEP-15.4 | |
Neural Entrainment to Rhythms of Imagined Syllables |
|
| |