| |
Last updated on May 5, 2020. This conference program is tentative and subject to change
Technical Program for Tuesday April 7, 2020
|
TuAaO1 Oral Session, Oakdale I-II |
Add to My Program |
Machine Learning for Brain Studies |
|
|
Chair: Salvado, Olivier | CSIRO Data61 |
Co-Chair: Renard, Félix | University of Grenoble |
|
09:00-09:15, Paper TuAaO1.1 | Add to My Program |
3D Mapping of Tau Neurofibrillary Tangle Pathology in the Human Medial Temporal Lobe |
|
Yushkevich, Paul | University of Pennsylvania |
Iñiguez de Onzoño Martin, María Mercedes | Human Neuroanatomy Laboratory, University of Castilla-La Mancha |
Ittyerah, Ranjit | Penn Image Computing and Science Laboratory, Department of Radio |
Lim, Sydney | University of Pennsylvania |
Lavery, Madigan | University of Pennsylvania |
Wang, Jiancong | PICSL Lab, University of Pennsylvannia |
Hung, Ling Yu | University of Pennsylvania |
Vergnet, Nicolas | University of Pennsylvania |
Ravikumar, Sadhana | Penn Image Computing and Science Laboratory, Department of Radio |
Xie, Long | Penn Image Computing and Science Laboratory (PICSL), Department |
Dong, Mengjin | University of Pennsylvania |
DeFlores, Robin | University of Pennsylvania |
Cui, Salena | University of Pennsylvania |
McCollum, Lauren | University of Pennsylvania |
Ohm, Daniel | University of Pennsylvania |
Robinson, John | Center for Neurodegenerative Disease Research (CNDR), University |
Schuck, Theresa | Center for Neurodegenerative Disease Research (CNDR), University |
Grossman, Murray | Department of Neurology, University of Pennsylvania |
Tisdall, M. Dylan | University of Pennsylvania |
Prabhakaran, Karthik | University of Pennsylvania |
Mizsei, Gabor | University of Pennsylvania |
Das, Sandhitsu | Department of Neurology, University of Pennsylvania |
Artacho Pérula, Emilio | Human Neuroanatomy Laboratory, University of Castilla-La Mancha |
Arroyo Jiménez, María del Mar | Human Neuroanatomy Laboratory, University of Castilla-La Mancha |
Muñoz López, Mónica | Human Neuroanatomy Laboratory, University of Castilla-La Mancha |
Marcos Rabal, María Pilar | Human Neuroanatomy Laboratory, University of Castilla-La Mancha |
Molina Romero, Francisco Javier | Human Neuroanatomy Laboratory, University of Castilla-La Mancha |
Lee, Edward B | University of Pennsylvania |
Trojanowski, John | Center for Neurodegenerative Disease Research (CNDR), University |
Wisse, Laura | Penn Image Computing and Science Laboratory, Department of Radio |
Wolk, David | Department of Neurology, University of Pennsylvania |
Irwin, David J | University of Pennsylvania |
Insausti, Ricardo | Human Neuroanatomy Laboratory, University of Castilla-La Mancha |
Keywords: Histopathology imaging (e.g. whole slide imaging), Integration of multiscale information, Atlases
Abstract: Tau protein neurofibrillary tangles (NFT) are linked to neuronal and synaptic loss and cognitive decline in Alzheimer's disease (AD) and related dementias. In AD, NFT pathology is known to spread through the cortex in a characteristic pattern, starting in the medial temporal lobe. However, the exact 3D pattern of NFT progression has not been described, and capturing this pattern quantitatively can help inform in vivo AD imaging biomarkers. We present a computational framework for generating 3D maps of NFT load from ex vivo MRI and serial histology. Weakly supervised deep learning is used to detect NFTs on histology slides prepared with an anti-tau immunohistochemistry stain, and a multi-stage registration pipeline that leverages 3D printing is used for histology-MRI alignment. Derived maps of NFT density are strongly concordant with manual NFT counting, as well as categorical NFT severity ratings used for clinical diagnosis.
|
|
09:15-09:30, Paper TuAaO1.2 | Add to My Program |
Weakly-Supervised Brain Tumor Classification with Global Diagnosis Label |
|
Zhou, Yufan | University at Buffalo, SUNY |
Li, Zheshuo | University at Buffalo, SUNY |
Ma, Chunwei | University at Buffalo |
Gao, Mingchen | University at Buffalo, SUNY |
Chen, Changyou | University at Buffalo, SUNY |
Zhu, Hong | Xuzhou Medical University |
Xu, Jinhui | SUNY Buffalo |
Keywords: Machine learning, Brain, Magnetic resonance imaging (MRI)
Abstract: There is an increasing need for efficient and automatic evaluation of brain tumors on magnetic resonance images (MRI). Most of the previous works focus on segmentation, registration, and growth modeling of the most common primary brain tumor gliomas, or the classification of up to three types of brain tumors. In this work, we extend the study to eight types of brain tumors where only global diagnosis labels are given but not the slice-level labels. We propose a weakly supervised method and demonstrate that inferring disease types at the slice-level would help the global label prediction. We also provide an algorithm for feature extraction via randomly choosing connection paths through class-specific autoencoders with dropout to accommodate the small-dataset problem. Experimental results on both public and proprietary datasets are compared to the baseline methods. The classification with the weakly supervised setting on the proprietary data, consisting of 295 patients with eight different tumor types, shows close results to the upper bound in the supervised learning setting.
|
|
09:30-09:45, Paper TuAaO1.3 | Add to My Program |
Encoding Human Cortex Using Spherical CNNs - a Study on Alzheimer's Disease Classification |
|
Barbaroux, Hugo | Imperial College London |
Feng, Xinyang | Columbia University |
Yang, Jie | Columbia University |
Laine, Andrew | Columbia University |
Angelini, Elsa | Imperial NIHR BRC, Imperial College London |
Keywords: Machine learning, Brain, Magnetic resonance imaging (MRI)
Abstract: In neuroimaging studies, the human cortex is commonly mod elled as a sphere to preserve the topological structure of the cortical surface. In this work, we explore the analysis of the human cortex using spherical CNN in an Alzheimer’s disease (AD) classification task, using morphometric measures derived from T1-weighted structural MRI. Our results show superior performance in classifying AD versus cognitively normal subjects and in predicting mild cognitive impairment progression within two years. This work demonstrates the feasibility and superiority of the spherical CNN directly applied on the spherical representation in the discriminative analysis of the human cortex and could be readily extended to other imaging modalities and other neurological diseases.
|
|
09:45-10:00, Paper TuAaO1.4 | Add to My Program |
Predicting Longitudinal Cognitive Scores Using Baseline Imaging and Clinical Variables |
|
Saboo, Krishnakant | University of Illinois at Urbana-Champaign |
Hu, Chang | University of Illinois Urbana-Champaign |
Varatharajah, Yogatheesan | University of Illinois at Urbana Champaign |
Vemuri, Prashanthi | Mayo Clinic, Rochester |
Iyer, Ravishankar | University of Illinois at Urbana-Champaign |
Keywords: Machine learning, Brain, Magnetic resonance imaging (MRI)
Abstract: Predicting the future course of a disease with limited information is an essential but challenging problem in health care. For older adults, especially the ones suffering from Alzheimer's disease, accurate prediction of their longitudinal trajectories of cognitive decline can facilitate appropriate prognostic clinical action. Increasing evidence has shown that longitudinal brain imaging data can aid in the prediction of cognitive trajectories. However, in many cases, only a single (baseline) measurement from imaging is available for prediction. We propose a novel model for predicting the trajectory of cognition, using only a baseline measurement, by leveraging the temporal dependence in cognition. On both a synthetic dataset and a real-world dataset, we demonstrate that our model is superior to prior approaches in predicting cognition trajectory over the next five years. We show that the model's ability to capture nonlinear interaction between features leads to improved performance. Further, the proposed model achieved significantly improved trajectory prediction in subjects at higher risk of cognitive decline (those with genetic risk and worse clinical profiles at baseline), highlighting its clinical utility.
|
|
10:00-10:15, Paper TuAaO1.5 | Add to My Program |
Improving Diagnosis of Autism Spectrum Disorder and Disentangling Its Heterogeneous Functional Connectivity Patterns Using Capsule Networks |
|
Jiao, Zhicheng | Perelman School of Medicine at University of Pennsylvania |
Li, Hongming | University of Pennsylvania |
Fan, Yong | University of Pennsylvania |
Keywords: fMRI analysis, Computer-aided detection and diagnosis (CAD)
Abstract: Functional connectivity (FC) analysis is an appealing tool to aid diagnosis and elucidate the neurophysiological underpinnings of autism spectrum disorder (ASD). Many machine learning methods have been developed to distinguish ASD patients from healthy controls based on FC measures and identify abnormal FC patterns of ASD. Particularly, several studies have demonstrated that deep learning models could achieve better performance for ASD diagnosis than conventional machine learning methods. Although promising classification performance has been achieved by the existing machine learning methods, they do not explicitly model heterogeneity of ASD, incapable of disentangling heterogeneous FC patterns of ASD. To achieve an improved diagnosis and a better understanding of ASD, we adopt capsule networks (CapsNets) to build classifiers for distinguishing ASD patients from healthy controls based on FC measures and stratify ASD patients into groups with distinct FC patterns. Evaluation results based on a large multi-site dataset have demonstrated that our method not only obtained better classification performance than state-of-the-art alternative machine learning methods, but also identified clinically meaningful subgroups of ASD patients based on their vectorized classification outputs of the CapsNets classification model.
|
|
10:15-10:30, Paper TuAaO1.6 | Add to My Program |
Deep Learning of Cortical Surface Features Using Graph-Convolution Predicts Neonatal Brain Age and Neurodevelopmental Outcome |
|
Liu, Mengting | University of Southern California |
Duffy, Ben | University of Southern California |
Sun, Zhe | University of Southern California |
Toga, Arthur | University of Southern California |
Barkovich, James | UCSF |
Xu, Duan | University of California, San Francisco |
Kim, Hosung | University of Southern California |
Keywords: Machine learning, Modeling - Knowledge, Brain
Abstract: We investigated the ability of graph convolutional network (GCN) that takes into account the mesh topology as a sparse graph to predict brain age for preterm neonates using cortical surface morphometrics, i.e. cortical thickness and sulcal depth. Compared to machine learning and deep learning methods that did not use the surface topological information, the GCN better predicted the ages for preterm neonates with none/mild perinatal brain injuries (NMI). We then tested the GCN trained using NMI brains to predict the age of neonates with severe brain injuries (SI). Results also displayed good accuracy (MAE=1.43 weeks), while the analysis of the interaction term (true age × group) showed that the slope of the predicted brain age relative to the true age for the SI group was significantly less steep than the NMI group (p<0.0001), indicating that SI can decelerate early postnatal growth. To understand regional contributions to age prediction, we applied GCNs separately to the vertices within each cortical parcellation. The middle cingulate cortex that is known to be one of the thickest cortical regions in the neonatal period showed the best accuracy in age prediction (MAE = 1.24 weeks). Furthermore, we found that the regional brain ages computed using GCN models in several frontal cortices significantly correlated with cognitive abilities at 3 years of age. Furthermore, the brain predicted age in part of the superior temporal cortex, which is the auditory and language processing locus, was related to language functional scores at 3 years. Our results demonstrate the potential of the GCN models for predicting brain age as well as localizing brain regions contributing to the prediction of age and future cognitive outcome.
|
|
TuAaO2 Oral Session, Oakdale III |
Add to My Program |
Computer-Aided Detection and Diagnosis |
|
|
Chair: Unay, Devrim | Izmir University of Economics |
|
09:00-09:15, Paper TuAaO2.1 | Add to My Program |
Unsupervised Task Design to Meta-Train Medical Image Classifiers |
|
Maicas Suso, Gabriel | The University of Adelaide |
Nguyen, Cuong | University of Adelaide |
Taghizadeh Motlagh, Farbod | University of Adelaide |
Nascimento, Jacinto | Instituto Superior Técnico |
Carneiro, Gustavo | University of Adelaide |
Keywords: Computer-aided detection and diagnosis (CAD), Breast, Classification
Abstract: Meta-training has been empirically demonstrated to be the most effective pre-training method for few-shot learning of medical image classifiers (i.e., classifiers modeled with small training sets). However, the effectiveness of meta-training relies on the availability of a reasonable number of hand-designed classification tasks, which are costly to obtain, and consequently rarely available. In this paper, we propose a new method to unsupervisedly design a large number of classification tasks to meta-train medical image classifiers. We evaluate our method on a breast dynamically contrast enhanced magnetic resonance imaging (DCE-MRI) data set that has been used to benchmark few-shot training methods of medical image classifiers. Our results show that the proposed unsupervised task design to meta-train medical image classifiers builds a pre-trained model that, after fine-tuning, produces better classification results than other unsupervised and supervised pre-training methods, and competitive results with respect to meta-training that relies on hand-designed classification tasks.
|
|
09:15-09:30, Paper TuAaO2.2 | Add to My Program |
Uni and Multi-Modal Radiomic Features for the Predicting Prostate Cancer Aggressiveness |
|
Jung, Julip | Seoul Women's University |
Hong, Helen | Seoul Women's University |
Lee, Hansang | KAIST |
Hwang, Sung Il | Seoul National Unveristy College of Medicine, Department of Radio |
Lee, Hak Jong | Seoul National Unveristy College of Medicine, Department of Radio |
Keywords: Prostate, Classification, Magnetic resonance imaging (MRI)
Abstract: The use of quantitative radiomic features of MRI to predict the aggressiveness of prostate cancer has attracted increasing amounts of attention due to its potential as a non-invasive biomarker for prostate cancer. In this study, to predict prostate cancer aggressiveness, we investigate the usefulness of multi-modal radiomic features according to combination method such as concatenation or averaging and compare multi-modal radiomic features to uni-modal radiomic features. To define the prostate cancer region of T2wMR based on ground truth pathology, a radiologist manually segmented prostate cancer referring to a fusion result of registration of histopathology image and T2wMR. The prostate cancer region of the ADC is then defined as the same region as the T2wMR through registration of the ADC on the T2wMR. To extract radiomic features to predict prostate cancer aggressiveness, total 68 features are calculated for each region of T2wMR and ADC. To predict the aggressiveness of prostate cancer, a random forest classifier is trained for each region in T2wMR and ADC. The prostate cancer regions were categorized as Low GS Group (GS <= 3+4) and High GS Group (GS >= 4+3). As results, the sensitivity of combined features was the highest at 82.0% which is higher 2.4%, 2.7% and 4.8% than ADC, T2wMR, and average combined features. Experiment results showed that the possibility of determining the aggressiveness of prostate cancer through the multi-modal radiomic features of T2wMR and ADC.
|
|
09:30-09:45, Paper TuAaO2.3 | Add to My Program |
Computer-Aided Diagnosis of Congenital Abnormalities of the Kidney and Urinary Tract in Children Using a Multi-Instance Deep Learning Method Based on Ultrasound Imaging Data |
|
Yin, Shi | Huazhong University of Science and Technology |
Peng, Qinmu | Huazhong University of Science and Technology |
Li, Hongming | University of Pennsylvania |
Zhang, Zhengqiang | Huazhong University of Science and Technology |
You, Xinge | Huazhong University of Science and Technology |
Katherine, Fischer | The Children's Hospital of Philadelphia |
Furth, Susan | University of Pennsylvania |
Tasian, Gregory | The Children's Hospital of Philadelphia |
Fan, Yong | University of Pennsylvania |
Keywords: Ultrasound, Kidney, Computer-aided detection and diagnosis (CAD)
Abstract: Ultrasound images are widely used for diagnosis of congenital abnormalities of the kidney and urinary tract (CAKUT). Since a typical clinical ultrasound image captures 2D information of a specific view plan of the kidney and images of the same kidney on different planes have varied appearances, it is challenging to develop a computer aided diagnosis tool robust to ultrasound images in different views. To overcome this problem, we develop a multi-instance deep learning method for distinguishing children with CAKUT from controls based on their clinical ultrasound images, aiming to automatic diagnose the CAKUT in children based on ultrasound imaging data. Particularly, a multi-instance deep learning method was developed to build a robust pattern classifier to distinguish children with CAKUT from controls based on their ultrasound images in sagittal and transverse views obtained during routine clinical care. The classifier was built on imaging features derived using transfer learning from a pre-trained deep learning model with a mean pooling operator for fusing instance-level classification results. Experimental results have demonstrated that the multi-instance deep learning classifier performed better than classifiers built on either individual sagittal slices or individual transverse slices.
|
|
09:45-10:00, Paper TuAaO2.4 | Add to My Program |
Machine-Learning on Liver Ultrasound to Stratify Multiple Diseases Via Blood-Vessels and Perfusion Characteristics |
|
Bayet, Jules | ITMAT Data Science Group, Imperial College London |
Hoogenboom, Tim | Imperial College Londonn |
Sharma, Rohini | Imperial College London |
Angelini, Elsa | Imperial NIHR BRC, Imperial College London |
Keywords: Ultrasound, Liver, Machine learning
Abstract: Liver vessels can be visualized at sub-millimetre scale with contrast-enhanced ultrasound. In this work we exploit a co- hort of 97 subjects (healthy volunteers and 4 liver disease types), exploiting multiple videos acquired at locations within the liver hand-picked by the sonographer to perform the diag- nostic task. Annotation was performed at subject-level (dis- ease subtype or healthy), along with scoring of image quality. We propose an original approach exploiting the abstraction capabilities of maximum intensity projections (MIPs) to feed a deep-learning classifier. Two architectures were tested for which we compared performance with different scenarios re- garding the exploitation of transfer learning and the number of input MIPs per subjects. Our results show over 88% accu- racy for a 2-class task (healthy versus disease), and 70% for a 3-class task (healthy versus 2 disease sub-types). We demon- strate, for the first time, that deep learning with minimal su- pervision and no pre-filtering can accurately classify liver dis- eases based on vascular ultrasound imaging acquired in a clin- ical setting. We also report findings on specific misclassica- tion patterns which will guide further studies, augmentation of the cohort and subject annotation.
|
|
10:00-10:15, Paper TuAaO2.5 | Add to My Program |
False Positive Reduction Using Multiscale Contextual Features for Prostate Cancer Detection in Multi-Parametric MRI Scans |
|
Yu, Xin | Siemens Healthineers |
Lou, Bin | Siemens Healthineers |
Shi, Bibo | Ohio University |
Winkel, David | Siemens Healthineers |
Arrahmane, Nacim | Siemens Healthineers |
Diallo, Mamadou | Siemens Corporate Technology |
Meng, Tongbai | Siemens Healthineers |
von Busch, Heinrich | Siemens Healthineers |
Grimm, Robert | Siemens Healthineers |
Kiefer, Berthold | Siemens Healthineers |
Comaniciu, Dorin | Siemens Corporate Research |
Kamen, Ali | Siemens Corporation, Corporate Technology |
Huisman, Henkjan | Radboud University Medical Center |
Rosenkrantz, Andrew | New York University |
Penzkofer, Tobias | Charité |
Shabunin, Ivan | Patero Clinic |
Choi, Moon Hyung | Eunpyeong St. Mary’s Hospital |
Yang, Qingsong | Changhai Hospital of Shanghai |
Szolar, Dieter | Diagnostikum Graz Süd-West, |
Keywords: Computer-aided detection and diagnosis (CAD), Prostate, Magnetic resonance imaging (MRI)
Abstract: Prostate cancer (PCa) is the most prevalent and one of the leading causes of cancer death among men. Multi-parametric MRI (mp-MRI) is a prominent diagnostic scan, which could help in avoiding unnecessary biopsies for men screened for PCa. Artificial intelligence (AI) systems could help radiologists to be more accurate and consistent in diagnosing clinically significant cancer from mp-MRI scans. Lack of specificity has been identified recently as one of weak points of such assistance systems. In this paper, we propose a novel false positive reduction network to be added to the overall detection system to further analyze lesion candidates. The new network utilizes multiscale 2D image stacks of these candidates to discriminate between true and false positive detections. We trained and validated our network on a dataset with 2090 cases from seven different institutions and tested it on a separate independent dataset with 243 cases. With the proposed model, we achieved area under curve (AUC) of 0.876 on discriminating between true and false positive detected lesions and improved the AUC from 0.825 to 0.867 on overall identification of clinically significant cases.
|
|
10:15-10:30, Paper TuAaO2.6 | Add to My Program |
Polyp Detection in Colonoscopy Videos by Bootstrapping Via Temporal Consistency |
|
Ma, Yiting | University of Science and Technology of China |
Chen, Xuejin | University of Science and Technology of China |
Sun, Bin | Department of Gastroenterology. the First Affiliated Hospital Of |
Keywords: Computer-aided detection and diagnosis (CAD), Endoscopy, Gastrointestinal tract
Abstract: Computer-aided polyp detection during colonoscopy is beneficial to reduce the risk of colorectal cancers. Deep learning techniques have made significant process in natural object detection. However, when applying those fully supervised methods to polyp detection, the performance is greatly depressed by the deficiency of labeled data. In this paper, we propose a novel bootstrapping method for polyp detection in colonoscopy videos by augmenting training data with temporal consistency. For a detection network that is trained on a small set of annotated polyp images, we fine-tune it with new samples selected from the test video itself, in order to more effectively represent the polyp morphology of current video. A strategy of selecting new samples is proposed by considering temporal consistency in the test video. Evaluated on 11954 endoscopic frames of the CVC-ClinicVideoDB dataset, our method yields great improvement on polyp detection for several detection networks, and achieves state-of-the-art performance on the benchmark dataset.
|
|
TuAaO3 Oral Session, Oakdale IV-V |
Add to My Program |
Eye and Vessel Image Analysis |
|
|
Chair: Cheng, Li | University of Alberta, Canada |
Co-Chair: Anjos, Andre | Idiap Research Institute |
|
09:00-09:15, Paper TuAaO3.1 | Add to My Program |
ErrorNet: Learning Error Representations from Limited Data to Improve Vascular Segmentation |
|
Tajbakhsh, Nima | ASU |
Lai, Brian | UCLA |
Pundi Ananth, Shilpa | Voxelcloud, Inc |
Ding, Xiaowei | VOXELCLOUD INC |
Keywords: Vessels, Image segmentation, Machine learning
Abstract: Deep convolutional neural networks have proved effective in segmenting lesions and anatomies in various medical imaging modalities. However, in the presence of small sample size and domain shift problems, these models often produce masks with non-intuitive segmentation mistakes. In this paper, we propose a segmentation framework called ErrorNet, which learns to correct these segmentation mistakes through the repeated process of injecting systematic segmentation errors to the segmentation result based on a learned shape prior, followed by attempting to predict the injected error. During inference, ErrorNet corrects the segmentation mistakes by adding the predicted error map to the initial segmentation result. ErrorNet has advantages over alternatives based on domain adaptation or CRF-based post processing, because it requires neither domain-specific parameter tuning nor any data from the target domains. We have evaluated ErrorNet using five public datasets for the task of retinal vessel segmentation. The selected datasets differ in size and patient population, allowing us to evaluate the effectiveness of ErrorNet in handling small sample size and domain shift problems. Our experiments demonstrate that ErrorNet outperforms a base segmentation model, a CRF-based post processing scheme, and a domain adaptation method, with a greater performance gain in the presence of the aforementioned dataset limitations.
|
|
09:15-09:30, Paper TuAaO3.2 | Add to My Program |
Automated Hemorrhage Detection from Coarsely Annotated Fundus Images in Diabetic Retinopathy |
|
Huang, Yijin | Southern University of Science and Technology |
Lin, Li | School of Electronics and Information Technology, Sun Yat-Sen Un |
Li, Meng | State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Cent |
Wu, Jiewei | Sun Yat-Sen University |
Cheng, Pujin | Southern University of Science and Technology |
Wang, Kai | Sun Yat-Sen University |
Yuan, Jin | State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Cent |
Tang, Xiaoying | Southern University of Science and Technology |
Keywords: Retinal imaging, Machine learning, Computer-aided detection and diagnosis (CAD)
Abstract: In this paper, we proposed and validated a novel and effective pipeline for automatically detecting hemorrhage from coarsely-annotated fundus images in diabetic retinopathy. The proposed framework consisted of three parts: image preprocessing, training data refining, and object detection using a convolutional neural network with label smoothing. Contrast limited adaptive histogram equalization and adaptive gamma correction with weighting distribution were adopted to improve image quality by enhancing image contrast and correcting image illumination. To refine coarsely-annotated training data, we designed a bounding box refining network (BBR-net) to provide more accurate bounding box annotations. Combined with label smoothing, RetinaNet was implemented to alleviate mislabeling issues and automatically detect hemorrhages. The proposed method was trained and evaluated on a publicly available IDRiD dataset and also one of our private datasets. Experimental results showed that our BBR-net could effectively refine manually-delineated coarse hemorrhage annotations, with the average IoU being 0.8715 when compared with well-annotated bounding boxes. The proposed hemorrhage detection pipeline was compared to several alternatives and superior performance was observed.
|
|
09:30-09:45, Paper TuAaO3.3 | Add to My Program |
How to Extract More Information with Less Burden: Fundus Image Classification and Retinal Disease Localization with Ophthalmologist Intervention |
|
Meng, Qier | National Institute of Informatics |
Hashimoto, Yohei | The University of Tokyo |
Satoh, Shin'ichi | National Institute of Informatics |
Keywords: Retinal imaging, Eye, Pattern recognition and classification
Abstract: Image classification using deep convolutional neural networks (DCNN) has a competitive performance as compared to other state-of-the-art methods. Here, attention can be visualized as a heatmap to improve the explainability of DCNN. We generated the initial heatmaps by using gradient-based classification activation map (Grad-CAM). We first assume that these Grad-CAM heatmaps can reveal the lesion regions well, then apply the attention mining on these heatmaps. Another, we assume that these Grad-CAM heatmaps can't reveal the lesion regions well then apply the dissimilarity loss on these Grad-CAM heatmaps. In this study, we asked the ophthalmologists to select 30% of the heatmaps. Furthermore, we design knowledge preservation (KP) loss to minimize the discrepancy between heatmaps generated from the updated network and the selected heatmaps. Experiments revealed that our method improved accuracy from 90.1% to 96.2%. We also found that the attention regions are closer to the GT lesion regions.
|
|
09:45-10:00, Paper TuAaO3.4 | Add to My Program |
SUNet: A Lesion Regularized Model for Simultaneous Diabetic Retinopathy and Diabetic Macular Edema Grading |
|
Tu, Zhi | ShanghaiTech University |
Gao, Shenghua | ShanghaiTech University |
Zhou, Kang | ShanghaiTech University |
Chen, Xianing | ShanghaiTech University |
Fu, Huazhu | Inception Institute of Artificial Intelligence |
Gu, Zaiwang | Southern University of Science and Technology |
Cheng, Jun | Institute of Biomedical Engineering, Chinese Academy of Sciences |
Yu, Zehao | ShanghaiTech University |
Liu, Jiang | Southern University of Science and Technology |
Keywords: Classification, Computer-aided detection and diagnosis (CAD), Retinal imaging
Abstract: Diabetic retinopathy (DR), as a leading ocular disease, is often with a complication of diabetic macular edema (DME). However, most existing works only aim at DR grading but ignore the DME diagnosis, but doctors will do both tasks simultaneously. In this paper, motivated by the advantages of multi-task learning for image classification, and to mimic the behavior of clinicians in visual inspection for patients, we propose a feature Separation and Union Network (SUNet) for simultaneous DR and DME grading. Further, to improve the interpretability of the disease grading, a lesion regularizer is also imposed to regularize our network. Specifically, given an image, our SUNet first extracts a common feature for both DR and DME grading and lesion detection. Then a feature blending block is introduced which alternately uses feature separation and feature union for task-specific feature extraction,where feature separation learns task-specific features for lesion detection and DR and DME grading, and feature union aggregates features corresponding to lesion detection, DR and DME grading. In this way, we can distill the irrelevant features and leverage features of different but related tasks to improve the performance of each given task. Then the taskspecific features of the same task at different feature separation steps are concatenated for the prediction of each task. Extensive experiments on the very challenging IDRiD dataset demonstrate that our SUNet significantly outperforms existing methods for both DR and DME grading.
|
|
10:00-10:15, Paper TuAaO3.5 | Add to My Program |
Spatially Informed Cnn for Automated Cone Detection in Adaptive Optics Retinal Images |
|
Jin, Heng | Beihang University |
Morgan, Jessica | University of Pennsylvania |
Gee, James | University of Pennsylvania |
Chen, Min | University of Pennsylvania |
Keywords: Machine learning, Retinal imaging, Eye
Abstract: Adaptive optics (AO) scanning laser ophthalmoscopy offers cellular level in-vivo imaging of the human cone mosaic. Existing analysis of cone photoreceptor density in AO images require accurate identification of cone cells, which is a time and labor-intensive task. Recently, several methods have been introduced for automated cone detection in AO retinal images using convolutional neural networks (CNN). However, these approaches have been limited in their ability to correctly identify cones when applied to AO images originating from different locations in the retina, due to changes to the reflectance and arrangement of the cone mosaics with eccentricity. To address these limitations, we present an adapted CNN architecture that incorporates spatial information directly into the network. Our approach, inspired by conditional generative adversarial networks, embeds the retina location from which each AO image was acquired as part of the training. Using manual cone identification as ground truth, our evaluation shows general improvement over existing approaches when detecting cones in the middle and periphery regions of the retina, but decreased performance near the fovea.
|
|
10:15-10:30, Paper TuAaO3.6 | Add to My Program |
Automatic Angle-Closure Glaucoma Screening Based on the Localization of Scleral Spur in Anterior Segment Oct |
|
Li, Panming | Soochow University, School of Electronic and Information Enginee |
Geng, Le | Soochow University, School of Electronic and Information Enginee |
Zhu, Weifang | Soochow University |
Shi, Fei | Soochow University |
Chen, XinJian | Soochow University |
Keywords: Optical coherence tomography, Eye, Computer-aided detection and diagnosis (CAD)
Abstract: As one of the major types of glaucoma, closed-angle glaucoma is the leading cause of irreversible blindness in the world. The ability of Anterior Segment Optical Coherence Tomography (AS-OCT) to obtain high-resolution cross-sectional images of the entire anterior chamber in a single image makes it an important tool for glaucoma diagnosis. In this paper, we propose a practical and efficient system based on deep learning to accurately classify anterior chamber angle (ACA) closure by using the location of scleral spur (SS) points. First, the localization problem is reformulated as a pixel-wise regression task. A fully convolutional deep neural network is optimized to predict the probability that each pixel belongs to the SS points, and the numerical coordinates are obtained by the maximum likelihood estimation theory. Second, the ACA region centered on the detected SS is cropped as the input of the classification model. The single model applied for classification is SE-ResNet18 and optimized with focal loss. In the AGE Challenge 2019[1], our proposed method obtained superior performance for angle-closure glaucoma screening.
|
|
TuAbPo Poster Session, Oakdale Foyer Coral Foyer |
|
Tuesday Poster AM |
|
|
|
10:30-12:00, Subsession TuAbPo-01, Oakdale Foyer Coral Foyer | |
FMRI Analysis II Poster Session, 9 papers |
|
10:30-12:00, Subsession TuAbPo-02, Oakdale Foyer Coral Foyer | |
MRI Reconstruction Methods II Poster Session, 7 papers |
|
10:30-12:00, Subsession TuAbPo-03, Oakdale Foyer Coral Foyer | |
Computer-Aided Detection and Diagnosis II Poster Session, 7 papers |
|
10:30-12:00, Subsession TuAbPo-04, Oakdale Foyer Coral Foyer | |
DL/CNN Methods and Models II Poster Session, 8 papers |
|
10:30-12:00, Subsession TuAbPo-05, Oakdale Foyer Coral Foyer | |
Machine Learning, Pattern Recognition Methods Poster Session, 8 papers |
|
10:30-12:00, Subsession TuAbPo-06, Oakdale Foyer Coral Foyer | |
Optical Coherence Tomography I Poster Session, 6 papers |
|
10:30-12:00, Subsession TuAbPo-07, Oakdale Foyer Coral Foyer | |
Optical Microscopy and Analysis II Poster Session, 12 papers |
|
10:30-12:00, Subsession TuAbPo-08, Oakdale Foyer Coral Foyer | |
Videoscopy Processing Poster Session, 6 papers |
|
10:30-12:00, Subsession TuAbPo-09, Oakdale Foyer Coral Foyer | |
Abstract Posters: Medical Imaging and Analysis Poster Session, 11 papers |
|
10:30-12:00, Subsession TuAbPo-10, Oakdale Foyer Coral Foyer | |
Abstract Posters: Microscopy and OCT Poster Session, 4 papers |
|
TuAbPo-01 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
FMRI Analysis II |
|
|
Chair: Preti, Maria Giulia | EPFL / Université De Genève |
Co-Chair: Babajani-Feremi, Abbas | The University of Tennessee Health Science Center |
|
10:30-12:00, Paper TuAbPo-01.1 | Add to My Program |
Twin Classification in Resting-State Brain Connectivity |
|
Gritsenko, Andrey | Northeastern University |
Lindquist, Martin | Johns Hopkins Bloomberg School of Public Health |
Chung, Moo K. | University of Wisconsin-Madison |
Keywords: fMRI analysis, Classification, Machine learning
Abstract: Twin study is one of the major parts of human brain research that reveals the importance of environmental and genetic influences on different aspects of brain behavior and disorders. Accurate characterization of identical and fraternal twins allows us to inference on the genetic influence in a population. In this paper, we propose a novel pairwise classification pipeline to identify the zygosity of twin pairs using the resting state functional magnetic resonance images (rs-fMRI). The new feature representation is utilized to efficiently construct brain network for each subject. Specifically, we project the fMRI signal to a set of cosine series basis and use the projection coefficients as the compact and discriminative feature representation of noisy fMRI. The pairwise relation is encoded by a set of twinwise correlations between functional brain networks across brain regions. We further employ hill climbing variable selection to identify the most genetically affected brain regions. The proposed framework has been applied to 208 twin pairs in Human Connectome Project (HCP) and we achieved 92.23(±4.43)% classification accuracy.
|
|
10:30-12:00, Paper TuAbPo-01.2 | Add to My Program |
Estimating Reproducible Functional Networks Associated with Task Dynamics Using Unsupervised LSTMs |
|
Dvornek, Nicha | Yale School of Medicine |
Ventola, Pamela | Yale School of Medicine |
Duncan, James | Yale University |
Keywords: fMRI analysis, Functional imaging (e.g. fMRI), Brain
Abstract: We propose a method for estimating more reproducible functional networks that are more strongly associated with dynamic task activity by using recurrent neural networks with long short term memory (LSTMs). The LSTM model is trained in an unsupervised manner to learn to generate the functional magnetic resonance imaging (fMRI) time-series data in regions of interest. The learned functional networks can then be used for further analysis, e.g., correlation analysis to determine functional networks that are strongly associated with an fMRI task paradigm. We test our approach and compare to other methods for decomposing functional networks from fMRI activity on 2 related but separate datasets that employ a biological motion perception task. We demonstrate that the functional networks learned by the LSTM model are more strongly associated with the task activity and dynamics compared to other approaches. Furthermore, the patterns of network association are more closely replicated across subjects within the same dataset as well as across datasets. More reproducible functional networks are essential for better characterizing the neural correlates of a target task.
|
|
10:30-12:00, Paper TuAbPo-01.3 | Add to My Program |
Optimize Cnn Model for Fmri Signal Classification Via Adanet-Based Neural Architecture Search |
|
Dai, Haixing | University of Georgia |
Ge, Fangfei | Northwestern Polytechnical University |
Li, Qing | Beijing Normal University |
Zhang, Wei | University of Georgia |
Liu, Tianming | University of Georgia |
Keywords: Machine learning, fMRI analysis, Data Mining
Abstract: Recent studies showed that convolutional neural network (CNN) models possess remarkable capability of differentiating and characterizing fMRI signals from cortical gyri and sulci. In addition, visualization and analysis of the filters in the learned CNN models suggest that sulcal fMRI signals are more diverse and have higher frequency than gyral signals. However, it is not clear whether the gyral fMRI signals can be further divided into sub-populations, e.g., 3-hinge areas vs 2-hinge areas. It is also unclear whether the CNN models of two classes (gyral vs sulcal) classification can be further optimized for three classes (3-hinge gyral vs 2-hinge gyral vs sulcal) classification. To answer these questions, in this paper, we employed the AdaNet framework to design a neural architecture search (NAS) system for optimizing CNN models for three classes fMRI signal classification. The core idea is that AdaNet adaptively learns both the optimal structure of the CNN network and its weights so that the learnt CNN model can effectively extract discriminative features that maximize the classification accuracies of three classes of 3-hinge gyral, 2-hinge gyral and sulcal fMRI signals. We evaluated our framework on the Autism Brain Imaging Data Exchange (ABIDE) dataset, and experiments showed that our framework can obtained significantly better results, in terms of both classification accuracy and extracted features.
|
|
10:30-12:00, Paper TuAbPo-01.4 | Add to My Program |
A Novel Framework for Grading Autism Severity Using Task-Based Fmri |
|
Haweel, Reem | Ain Shamas University |
Dekhil, Omar | University of Louisville |
Shalaby, Ahmed | University of Louisville |
Mahmoud, Ali | University of Louisville |
Ghazal, Mohammed | Abu Dhabi University |
Khalil, Ashraf | Abu Dhabi University |
Keynton, Robert | Bioengineering Department, University of Louisville |
Barnes, Gregory | University of Louisville |
El-baz, Ayman | University of Louisville |
Keywords: Functional imaging (e.g. fMRI), Brain, Computer-aided detection and diagnosis (CAD)
Abstract: Autism is a developmental disorder associated with difficulties in communication and social interaction. Currently, the gold standard in autism diagnosis is the autism diagnostic observation schedule (ADOS) interviews that assign a score indicating the level of severity for each individual. However, current researchers investigate developing objective technologies to diagnose autism employing brain image modalities. One of such image modalities is task-based functional MRI which exhibits alterations in functional activity that is believed to be important in explaining autism causative factors. Although autism is defined over a wide spectrum, previous diagnosis approaches only divide subjects into normal or autistic. In this paper, a novel framework for grading the severity level of autistic subjects using task-based fMRI data is presented. A speech experiment is used to obtain local features related to the functional activity of the brain. According to ADOS reports, the adopted dataset of 39 subjects is classified to three groups (13 subjects per group): mild, moderate and severe. Individual analysis with the general linear model (GLM) is used for feature extraction for each 246 brain areas according to the Brainnetome atlas (BNT). Our classification results are obtained by random forest classifier after recursive feature elimination (RFE) with 72% accuracy. Finally, we validate our selected features by applying higher-level group analysis to prove how informative they are and to infer the significant statistical differences between groups
|
|
10:30-12:00, Paper TuAbPo-01.5 | Add to My Program |
Gradient Artifact Correction for Simultaneous Eeg-Fmri Using Denoising Autoencoders |
|
Duffy, Ben | University of Southern California |
Toga, Arthur | University of Southern California |
Kim, Hosung | University of Southern California |
Keywords: Image enhancement/restoration(noise and artifact reduction), EEG & MEG, Functional imaging (e.g. fMRI)
Abstract: EEG recorded during MRI acquisition suffers from severe artifacts due to the imaging gradients. Here, we explore the possibility of using denoising autoencoders for correcting for these artifacts. After hyperparameter optimization, the performance of the algorithm was compared against PCA on two different synthesized datasets. The first dataset was created by adding a template artifact to clean EEG data and randomly shifting it in time to simulate aliasing. While the second dataset was formed by filtering out the EEG frequencies and adding a known ground-truth clean EEG signal. The performance of each method was assessed by the RMSE relative to the clean EEG signal. In addition, the correlation coefficient compared to the artifact signal was used to measure the residual artifact level. On the second synthesized dataset, denoising autoencoders outperformed PCA by 4.3% in terms of RMSE, meaning they were able to better preserve the original signal while at the same time the correlation with the underlying artifact was reduced by 40%. These preliminary results merit further investigation on a larger dataset.
|
|
10:30-12:00, Paper TuAbPo-01.6 | Add to My Program |
Volumetric Registration of Brain Cortical Regions by Automatic Landmark Matching and Large Deformation Diffeomorphisms |
|
He, Hengda | Columbia University |
Razlighi, Qolamreza | Department of Radiology, Weill Cornell Medicine |
Keywords: Image registration, Functional imaging (e.g. fMRI), Brain
Abstract: A well-known challenge in fMRI data analysis is the excessive variability in the MR signal and the high level of random and structured noise. A common solution to deal with such high variability/noice is to recruit a large number of subjects to enhance the statistical power to detect any scientific effect. To achieve this, the morphologies of the sample brains are required to be warped into a standard space. However, human's cerebral cortices are highly convoluted, with large inter-subject morphological variability that renders the task of registration challenging. Currently, the state-of-the-art non-linear registration methods perform poorly on brains' cortical regions particularly on aging and clinical populations. To alleviate this issue, we propose a landmark-guided and region-based image registration method. We have evaluated our method by warping the brain cortical regions of both young and older participants into the standard space. Compared with the state-of-the-art method, we showed our method significantly (t = 117; p = 0) improved the overlap of the cortical regions (Dice increased by 57%). We concluded our method can significantly improve the registration accuracy of brain cortical regions.
|
|
10:30-12:00, Paper TuAbPo-01.7 | Add to My Program |
A Novel Spatio-Temporal Hub Identification Method for Dynamic Functional Networks |
|
Chen, Anqi | Hangzhou Dianzi University |
Yang, Defu | Hangzhou Dianzi University |
Yan, Chenggang | Hangzhou Dianzi University |
Peng, Ziwen | Shenzhen Kangning Hospital, Shenzhen Mental Health Center |
Kim, Minjeong | University of North Carolina at Greensboro |
Laurienti, Paul | Wake Forest University Health Sciences |
Wu, Guorong | University of North Carolina at Chapel Hill |
Keywords: fMRI analysis, Brain, Functional imaging (e.g. fMRI)
Abstract: Functional connectivity (FC) has been widely investigated to understand the cognition and behavior that emerge from human brain. Recently, there is overwhelming evidence showing that quantifying temporal changes in FC may provide greater insight into fundamental properties of brain network. However, scant attentions has been given to characterize the functional dynamics of network organization. To address this challenge, we propose a novel spatio-temporal hub identification method for functional brain networks by simultaneously identifying hub nodes in each static sliding window and maintaining the reasonable dynamics across the sliding windows, which allows us to further characterize the full-spectrum evolution of hub nodes along with the subject-specific functional dynamics. We have evaluated our spatio-temporal hub identification method on resting-state functional resonance imaging (fMRI) data from an obsessive-compulsive disease (OCD) study, where our new functional hub detection method outperforms current methods (without considering functional dynamics) in terms of accuracy and consistency. Index Terms— Dynamic functional network, brain network, graph spectrum, hub node
|
|
10:30-12:00, Paper TuAbPo-01.8 | Add to My Program |
Task Fmri Guided Fiber Clustering Via a Deep Clustering Method |
|
Wang, Huan | Shaanxi Normal University |
Dong, Qinglin | University of Georgia |
Qiang, Ning | Shaanxi Normal University |
Zhang, Xin | Northwestern Polytechnical University |
Liu, Tianming | University of Georgia |
Ge, Bao | Shaanxi Normal University |
Keywords: Computational Imaging, Functional imaging (e.g. fMRI), Diffusion weighted imaging
Abstract: Fiber clustering is a prerequisite step towards tract-based analysis for human brain, and it is very important to explain brain structure and function relationship. Over the last decade, it has been an open and challenging question as to what a reasonable clustering of fibers is. Specifically, the purpose of fiber clustering is to cluster the whole brain’s white matter fibers extracted from tractography into similar and meaningful fiber bundles, thus how to definite the “similar and meaningful” metric decides the performance and possible application of a fiber clustering method. In the past, researchers typically divided the fibers into anatomical or structural similar bundles, but rarely divided them according to functional meanings. In this work, we proposed a novel fiber clustering method by adopting the functional and structural information and combined them into the input of a deep convolutional autoencoder with embedded clustering, which can better extract and use the features within the data. The experimental results show that the proposed method can cluster the whole brain’s fibers into functionally and structurally meaningful bundles.
|
|
10:30-12:00, Paper TuAbPo-01.9 | Add to My Program |
INTERPRETING AGE EFFECTS of HUMAN FETAL BRAIN from SPONTANEOUS fMRI USING DEEP 3D CONVOLUTIONAL NEURAL NETWORKS |
|
Li, Xiangrui | Wayne State University |
Jasmine Hect, Jasmine Hect | Wayne State University |
Thomason, Moriah | Wayne State University |
Zhu, Dongxiao | Wayne State University |
Keywords: Fetus, Magnetic resonance imaging (MRI), Machine learning
Abstract: Understanding human fetal neurodevelopment is of great clinical importance as abnormal development is linked to adverse neuropsychiatric outcomes after birth. With the advances in functional Magnetic Resonance Imaging (fMRI), recent stud- ies focus on brain functional connectivity and have provided new insight into development of the human brain before birth. Deep Convolutional Neural Networks (CNN) have achieved remarkable success on learning directly from image data, yet have not been applied on fetal fMRI for understanding fetal neurodevelopment. Here, we bridge this gap by applying a novel application of 3D CNN to fetal blood oxygen-level dependence (BOLD) resting-state fMRI data. We build supervised CNN to isolate variation in fMRI signals that relate to younger v.s. older fetal age groups. Sensitivity analysis is then performed to identify brain regions in which changes in BOLD signal are strongly associated with fetal brain age. Based on the analysis, we discovered that regions that most strongly differentiate groups are largely bilateral, share similar distribution in older and younger age groups, and are areas of heightened metabolic activity in early human development.
|
|
TuAbPo-02 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
MRI Reconstruction Methods II |
|
|
Chair: Ongie, Greg | University of Chicago |
|
10:30-12:00, Paper TuAbPo-02.1 | Add to My Program |
Calibrationless Parallel Mri Using Model Based Deep Learning (c-Modl) |
|
Pramanik, Aniket | University of Iowa |
Aggarwal, Hemant Kumar | University of Iowa |
Jacob, Mathews | University of Iowa |
Keywords: Magnetic resonance imaging (MRI), Brain, Machine learning
Abstract: We introduce a fast model based deep learning approach for calibrationless parallel MRI reconstruction. The proposed scheme is a non-linear generalization of structured low rank (SLR) methods that self learn linear annihilation filters from the same subject; the proposed scheme pre-learns the nonlinear annihilation relations in the Fourier domain from exemplar data. The pre-learning strategy significantly reduces the computational complexity, making the proposed scheme three orders of magnitude faster than SLR schemes. The proposed framework also allows the use of a complementary spatial domain prior; the hybrid regularization scheme offers improved performance over calibrated image domain MoDL approach.The calibrationless strategy minimizes potential mismatches between calibration data and main scan, while eliminating the need for a fully sampled calibration region.
|
|
10:30-12:00, Paper TuAbPo-02.2 | Add to My Program |
Multi-Contrast MR Reconstruction with Enhanced Denoising Autoencoder Prior Learning |
|
Liu, Xiangshun | Nanchang University |
Zhang, Minghui | Nanchang University |
Liu, Qiegen | Department of Electronic Information Engineering, Nanchang Unive |
Xiao, Taohui | Paul C. Lauterbur Research Center for Biomedical Imaging, SIAT, |
Zheng, Hairong | Shenzhen Inst of Advanced Tech |
Ying, Leslie | The State University of New York at Buffalo |
Wang, Shanshan | Shenzhen Institutes of Advanced Technology |
Keywords: Magnetic resonance imaging (MRI), Brain
Abstract: This paper proposes an enhanced denoising autoencoder prior (EDAEP) learning framework for accurate multi-contrast MR image reconstruction. A multi-model structure with various noise levels is designed to capture features of different scales from different contrast images. Furthermore, a weighted aggregation strategy is proposed to balance the impact of different model outputs, making the performance of the proposed model more robust and stable while facing noise attacks. The model was trained to handle three different sampling patterns and different acceleration factors on two public datasets. Results demonstrate that our proposed method can improve the quality of reconstructed images and outperform the previous state-of-the-art approaches. The code is available at https://github.com/yqx7150.
|
|
10:30-12:00, Paper TuAbPo-02.3 | Add to My Program |
An Evaluation of Regularization Strategies for Subsampled Single-Shell Diffusion MRI |
|
Liu, Yunsong | University of Southern California |
Liao, Congyu | Massachusetts General Hospital, Harvard Medical School |
Setsompop, Kawin | Harvard Medical School |
Haldar, Justin | University of Southern California |
Keywords: Diffusion weighted imaging, Compressive sensing & sampling, Magnetic resonance imaging (MRI)
Abstract: Conventional single-shell diffusion MRI experiments acquire sampled values of the diffusion signal from the surface of a sphere in q-space. However, to reduce data acquisition time, there has been recent interest in using regularization to enable q-space undersampling. Although different regularization strategies have been proposed for this purpose (i.e., sparsity-promoting of the spherical ridgelet representation and Laplace-Beltrami Tikhonov regularization), there has not been a systematic evaluation of the strengths, weaknesses, and potential synergies of the different regularizers. In this work, we use real diffusion MRI data to systematically evaluate the performance characteristics of these different approaches and determine whether one approach is fundamentally more powerful than the other. Results from retrospective subsampling experiments suggest that both regularization strategies offer largely similar reconstruction performance (though with different levels of computational complexity) with some degree of synergy (albeit, relatively minor).
|
|
10:30-12:00, Paper TuAbPo-02.4 | Add to My Program |
Benchmarking Deep Nets MRI Reconstruction Models on the FastMRI Publicly Available Dataset |
|
Ramzi, Zaccharie | CEA |
Ciuciu, Philippe | CEA |
Starck, Jean-Luc | CEA, IRFU/SEDI/LCS |
Keywords: Magnetic resonance imaging (MRI), Image reconstruction - analytical & iterative methods, Machine learning
Abstract: The MRI reconstruction field lacked a proper data set that allowed for reproducible results on real raw data (i.e. complex-valued), especially when it comes to deep learning methods as this kind of methods require much more data than classical Compressed Sensing reconstruction. This lack is now filled by the fastMRI data set, and it is needed to evaluate recent deep learning models on this benchmark. Besides, these networks are written in different frameworks, in different repositories (if publicly available), it is therefore needed to have a common tool, publicly available, allowing a reproducible benchmark of the different methods and ease of building new models. We provide such a tool that allows the benchmark of different reconstruction deep learning models.
|
|
10:30-12:00, Paper TuAbPo-02.5 | Add to My Program |
Fast High Dynamic Range MRI by Contrast Enhancement Networks |
|
Marques, Matthew | University of Queensland |
Engstrom, Craig | University of Queensland |
Fripp, Jurgen | CSIRO |
Crozier, Stuart | The University of Queensland |
Chandra, Shekhar | University of Queensland |
Keywords: Machine learning, Magnetic resonance imaging (MRI), Other-method
Abstract: HDR-MRI is a sophisticated non-linear image fusion technique for MRI which enhances image quality by fusing multiple contrast types into a single composite image. It offers improved outcomes in automatic segmentation and potentially in diagnostic power, but the existing technique is slow and requires accurate image co-registration in order to function reliably. In this work, a lightweight fully convolutional neural network architecture is developed with the goal of approximating HDR-MRI images in real-time. The resulting Contrast Enhancement Network (CEN) is capable of performing near-perfect (SSIM = 0.98) 2D approximations of HDR-MRI in 10ms and full 3D approximations in 1s, running two orders of magnitude faster than the original implementation. It is also able to perform the approximation (SSIM = 0.93) with only two of the three contrasts required to generate the original HDR-MRI image, while requiring no image co-registration.
|
|
10:30-12:00, Paper TuAbPo-02.6 | Add to My Program |
Arterial Input Function and Tracer Kinetic Model Driven Network for Rapid Inference of Kinetic Maps in Dynamic Contrast Enhanced MRI (AIF-TK-Net) |
|
Kettelkamp, Joseph | University of Iowa |
Lingala, Sajan Goud | The University of Iowa |
Keywords: Magnetic resonance imaging (MRI), Modeling - Anatomical, physiological and pathological, Brain
Abstract: We propose a patient-specific arterial input function (AIF) and tracer kinetic (TK) model-driven network to rapidly estimate the extended Tofts-Kety kinetic model parameters in DCE-MRI. We term our network as AIF-TK-net, which maps an input comprising of an image patch of the DCE-time series and the patient-specific AIF to the output image patch of the TK parameters. We leverage the open-source NEURO-RIDER database of brain tumor DCE-MRI scans to train our network. Once trained, our model rapidly infers the TK maps of unseen DCE-MRI images on the order of a 0.34 sec/slice for a 256x256x65 time series data on a NVIDIA GeForce GTX 1080 Ti GPU. We show its utility on high time resolution DCE-MRI datasets where significant variability in AIFs across patients exists. We demonstrate that the proposed AIF-TK net considerably improves the TK parameter estimation accuracy in comparison to a network, which does not utilize the patient AIF.
|
|
10:30-12:00, Paper TuAbPo-02.7 | Add to My Program |
Mr Imaging and Spectroscopy for Biomarker Characterization in Golden Retriever Muscular Dystrophy Tissue Samples |
|
Del Bosque, Romina | Vanderbilt University |
Valle, Edith | Texas A&M University |
Wilcox, Matthew | Texas A&M University |
Carrell, Travis | Texas A&M Universiy |
Nghiem, Peter | Texas A&M University |
Wright, Steven M. | Texas A&M University |
McDougall, Mary | Texas A&M University |
Keywords: Magnetic resonance imaging (MRI), Magnetic resonance spectroscopy, Muscle
Abstract: Custom double-tuned birdcage coils were constructed to enable concurrent evaluation of a number of NMR indices in the golden retriever muscular dystrophy (GRMD) model of Duchenne muscular dystrophy (DMD). Seven rectus femoris muscle samples from dogs with ages ranging from 3 to 30 months were studied. 1H T1-weighted (T1w) and T2-weighted (T2w) images, 23Na images, and 31P spectra were acquired for each sample. 1H T1w and T2w images showed a decrease in T2w/T1w signal ratio for the four older (≥12 months) samples when compared to younger samples. Other NMR indices unexpectedly showed no significant correlation with age. The collection time of samples and varying levels of disease severity may have attributed to these results. Regardless, the associated custom coils and positioner developed to enable multi-nuclear studies will enable future work to investigate NMR-based biomarkers in the numerous GRMD samples available to our group.
|
|
TuAbPo-03 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Computer-Aided Detection and Diagnosis II |
|
|
Chair: de Bruijne, Marleen | Erasmus MC - University Medical Center Rotterdam |
Co-Chair: Yang, Yongyi | Illinois Institute of Technology |
|
10:30-12:00, Paper TuAbPo-03.1 | Add to My Program |
DeepMRS: An End-To-End Deep Neural Network for Dementia Disease Detection Using MRS Data |
|
Ben Ahmed, Olfa | University of Poitiers |
Fezzani, Seifeddine | XLIM |
Guillevin, Carole | University of Poitiers |
Fezai, Lobna | XLIM |
Naudin, Mathieu | University of Poitiers |
Gianelli, Benoit | University of Poitiers |
Fernandez-Maloigne, Christine | University of Poitiers |
Keywords: Computer-aided detection and diagnosis (CAD), Magnetic resonance spectroscopy, Brain
Abstract: Alzheimer’s disease (AD) is the most common form of dementia. Neuroimaging data is an integral part of the clinical assessment providing a way for clinicians to detect brain abnormalities for AD diagnosis. Anatomical MRI has been widely used to assess structural brain atrophy for AD detectionand prediction. In addition to structural changes, metabolic changes in some brain regions such as the Posterior Cingulate Cortex (PCC) could be a good bio-marker for an early AD detection. Recently, proton Magnetic Resonance Spectroscopy (1H-MRS) have been proved to be effective to reveal a wealth of brain metabolic information. In this paper, we propose an end-to-end deep leaning Network for early AD and Normal Control (NC) subjects classification using 1H-MRS raw data from the PCC area. This work is the first investigation of 1H-MRS data with deep-learning technique for early AD detection. Data of 135 subjects, collected in Poitiers university hospital, are used to learn the proposed DeepMRS network. Our classification of patients with early AD versus NC subjects achieves an AUC of 94,74%, a sensitivity of 100% and a specificity of 89,47% demonstrating a promising early dementia detection performance.
|
|
10:30-12:00, Paper TuAbPo-03.2 | Add to My Program |
Efficient Detection of EMVI in Rectal Cancer Via Richer Context Information and Feature Fusion |
|
Li, Shuai | Beihang University |
Zhang, Zhengdong | Beihang University |
Lu, Yun | Qingdao University |
Keywords: Computer-aided detection and diagnosis (CAD), Gastrointestinal tract, Magnetic resonance imaging (MRI)
Abstract: It is vital to automatically detect the Extramural Vascular Invasion (EMVI) in rectal cancer before surgery, which facilitates to guide the patient's treatment planning. Nevertheless, there are few studies about EMVI detection through magnetic resonance imaging (MRI). Moreover, since EMVI has three main characteristics: highly-variable appearances, relatively-small sizes and similar shapes with surrounding tissues, current deep learning based methods can not be directly used. In this paper, we propose a novel and efficient EMVI detection framework, which gives rise to three main contributions. Firstly, we introduce a self-attention module to capture dependencies ranging from local to global. Secondly, we design a parallel atrous convolution (PAC) block and a global pyramid pooling (GPP) module to encode richer context information at multiple scales. Thirdly, we fuse the whole-scene and local-region information together to improve the feature representation ability. Experimental results show that our framework can significantly improve the detection accuracy and outperform other state-of-the-art methods.
|
|
10:30-12:00, Paper TuAbPo-03.3 | Add to My Program |
Stan: Small Tumor-Aware Network for Breast Ultrasound Image Segmentation |
|
Shareef, Bryar | University of Idaho |
Xian, Min | University of Idaho |
Vakanski, Aleksandar | University of Idaho |
Keywords: Ultrasound, Breast, Image segmentation
Abstract: Breast tumor segmentation provides accurate tumor boundary, and serves as a key step toward further cancer quantification. Although deep learning-based approaches have been proposed and achieved promising results, existing approaches have difficulty in detecting small breast tumors. The capacity to detecting small tumors is particular-ly important in finding early stage cancers using computer-aided diagnosis (CAD) systems. In this paper, we propose a novel deep learning architecture called Small Tumor-Aware Network (STAN), to improve the performance of segmenting tumors with different size. The new architecture integrates both rich context information and high-resolution image features. We validate the proposed approach using seven quantitative metrics on two public breast ultrasound datasets. The proposed approach outperformed the state-of-the-art approaches in segmenting small breast tumors.
|
|
10:30-12:00, Paper TuAbPo-03.4 | Add to My Program |
Deep Learning Based Detection of Acute Aortic Syndrome in Contrast CT Images |
|
Yellapragada, Manikanta Srikar | New York University |
Xie, Yiting | Cornell University |
Graf, Benedikt | IBM Watson Health Imaging |
Richmond, David | IBM Watson Health |
Krishnan, Arun | IBM Watson Health |
Sitek, Arkadiusz | IBM Watson Health |
Keywords: Computed tomography (CT), Machine learning
Abstract: Acute aortic syndrome (AAS) is a group of life threatening conditions of the aorta. We have developed an end-to-end automatic approach to detect AAS in computed tomography (CT) images. Our approach consists of two steps. At first, we extract N cross sections along the segmented aorta centerline for each CT scan. These cross sections are stacked together to form a new volume which is then classified using two different classifiers, a 3D convolutional neural network (3D CNN) and a multiple instance learning (MIL). We trained, validated, and compared two models on 2291 contrast CT volumes. We tested on a set aside cohort of 230 normal and 50 positive CT volumes. Our models detected AAS with an Area under Receiver Operating Characteristic curve (AUC) of 0.965 and 0.985 using 3DCNN and MIL, respectively.
|
|
10:30-12:00, Paper TuAbPo-03.5 | Add to My Program |
Semi-Supervised Multi-Domain Multi-Task Training for Metastatic Colon Lymph Node Diagnosis from Abdominal CT |
|
Glaser, Saskia | University of Adelaide |
Maicas Suso, Gabriel | The University of Adelaide |
Bedrikovetski, Sergei | University of Adelaide |
Sammour, Tarik | University of Adelaide |
Carneiro, Gustavo | University of Adelaide |
Keywords: Computer-aided detection and diagnosis (CAD), Machine learning, Abdomen
Abstract: The diagnosis of the presence of metastatic lymph nodes from abdominal computed tomography (CT) scans is an essential task performed by radiologists to guide radiation and chemotherapy treatment. State-of-the-art deep learning classifiers trained for this task usually rely on a training set containing CT volumes and their respective image-level (i.e., global) annotation. However, the lack of annotations for the localisation of the regions of interest (ROIs) containing lymph nodes can limit classification accuracy due to the small size of the relevant ROIs in this problem. The use of lymph node ROIs together with global annotations in a multi-task training process has the potential to improve classification accuracy, but the high cost involved in obtaining the ROI annotation for the same samples that have global annotations is a roadblock for this alternative. We address this limitation by introducing a new training strategy from two data sets: one containing the global annotations, and another (publicly available) containing only the lymph node ROI localisation. We term our new strategy semi-supervised multi-domain multi-task training, where the goal is to improve the diagnosis accuracy on the globally annotated data set by incorporating the ROI annotations from a different domain. Using a private data set containing global annotations and a public data set containing lymph node ROI localisation, we show that our proposed training mechanism improves the area under the ROC curve for the classification task compared to several training method baselines.
|
|
10:30-12:00, Paper TuAbPo-03.6 | Add to My Program |
Computer Aided Diagnosis of Clinically Significant Prostate Cancer in Low-Risk Patients on Multi-Parametric Mr Images Using Deep Learning |
|
Arif, Muhammad | Erasmus MC, Rotterdam |
Schoots, Ivo | Erasmus Medical Center |
Castillo T, Jose M. | Erasmus MC - University Medical Center Rotterdam |
Robool, Monique | Erasmus MC |
Niessen, Wiro | Erasmus MC, University Medical Center Rotterdam |
Veenland, Jifke F. | Erasmus MC - University Medical Center Rotterdam |
Keywords: Computer-aided detection and diagnosis (CAD), Magnetic resonance imaging (MRI), Prostate
Abstract: The purpose of this study was to develop a quantitative method for detection and segmentation of clinically significant (ISUP grade ≥ 2) prostate cancer (PCa) in low-risk patient. A consecutive cohort of 356 patients (active surveillance) was selected and divided in two groups: 1) MRI and targeted-biopsy positive PCa, 2) MRI and standard-biopsy negative PCa. A 3D convolutional neural network was trained in three-fold cross validation with MRI and targeted-biopsy positive patient’s data using two mp-MRI sequences (T2-weighted, DWI-b800) and ADC map as input. After training, the model was tested on separate positive and negative patients to evaluate the performance. The model achieved an average area under the curve (AUC) of the receiver operating characteristics is 0.78 (sensitivity = 85%, specificity = 72%). The diagnostic performance of the proposed method in segmenting significant PCa and to conform non-significant PCa in low-risk patients is characterized by a good AUC and negative-predictive-value.
|
|
10:30-12:00, Paper TuAbPo-03.7 | Add to My Program |
Deep Learning Features for Modeling Perceptual Similarity in Microcalcification Lesion Retrieval |
|
Wang, Juan | Illinois Institute of Technology |
Lei, Liang | Chongqing University of Science and Technology |
Yang, Yongyi | Illinois Institute of Technology |
Keywords: Computer-aided detection and diagnosis (CAD), Breast, X-ray imaging
Abstract: Retrieving cases with similar image features has been found to be effective for improving the diagnostic accuracy of microcalcification (MC) lesions in mammograms. However, a major challenge in such an image-retrieval approach is how to determine a retrieved lesion image has diagnostically similar features to that of a query case. We investigate the feasibility of modeling perceptually similar MC lesions by using deep learning features extracted from two types of deep neural networks, of which one is a supervised-learning network developed for the task of MC detection and the other is a denoising autoencoder network. In the experiments, the deep learning features were compared against the perceptual similarity scores collected from a reader study on 1,000 MC lesion image pairs. The results indicate that the deep learning features can potentially be more effective for modelling the notion of perceptual similarity of MC lesions than traditional handcrafted texture features.
|
|
TuAbPo-04 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
DL/CNN Methods and Models II |
|
|
Chair: Acton, Scott | University of Virginia |
Co-Chair: Wernick, Miles | Illinois Institute of Technology |
|
10:30-12:00, Paper TuAbPo-04.1 | Add to My Program |
Medical Data Inquiry Using a Question Answering Model |
|
Liao, Zhibin | University of Adelaide |
Liu, Lingqiao | Australian Institute for Machine Learning, University of Adelaid |
Wu, Qi | Australian Institude for Machine Learning, University of Adelaid |
Teney, Damien | Australian Institute for Machine Learning, University of Adelaid |
Shen, Chunhua | Australian Institute for Machine Learning, University of Adelaid |
Hengel, Anton van | University of Adelaide |
Verjans, Johan | Australian Institute for Machine Learning |
Keywords: Machine learning, Modeling - Knowledge, Other-method
Abstract: Access to hospital data is commonly a difficult, costly and time-consuming process requiring extensive interaction with network administrators. This leads to possible delays in obtaining insights from data, such as diagnosis or other clinical outcomes. Healthcare administrators, medical practitioners, researchers and patients could benefit from a system that could extract relevant information from healthcare data in real-time. In this paper, we present a question answering system that allows health professionals to interact with a large-scale database by asking questions in natural language. This system is built upon the BERT and SQLOVA models, which translate a user's request into an SQL query, which is then passed to the data server to retrieve relevant information. We also propose a deep bilinear similarity model to improve the generated SQL queries by better matching terms in the user's query with the database schema and contents. This system was trained with only 75 real questions and 455 back-translated questions, and was evaluated over 75 additional real questions about a real health information database, achieving a retrieval accuracy of 78%.
|
|
10:30-12:00, Paper TuAbPo-04.2 | Add to My Program |
Unsupervised Adversarial Correction of Rigid MR Motion Artifacts |
|
Armanious, Karim | University of Stuttgart |
Tanwar, Aastha | University of Stuttgart |
Abdulatif, Sherif | University of Stuttgart |
Küstner, Thomas | University of Stuttgart, Germany |
Gatidis, Sergios | University of Tübingen |
Yang, Bin | Institute of Signal Processing and System Theory, University Of |
Keywords: Magnetic resonance imaging (MRI), Machine learning, Motion compensation and analysis
Abstract: Motion is one of the main sources for artifacts in magnetic resonance (MR) images. It can have significant consequences on the diagnostic quality of the resultant scans. Previously, supervised adversarial approaches have been suggested for the correction of MR motion artifacts. However, these approaches suffer from the limitation of required paired co-registered datasets for training which are often hard or impossible to acquire. Building upon our previous work, we introduce a new adversarial framework with a new generator architecture and loss function for the unsupervised correction of severe rigid motion artifacts in the brain region. Quantitative and qualitative comparisons with other supervised and unsupervised translation approaches showcase the enhanced performance of the introduced framework.
|
|
10:30-12:00, Paper TuAbPo-04.3 | Add to My Program |
Transforming Intensity Distribution of Brain Lesions Via Conditional GANs for Segmentation |
|
Hamghalam, Mohammad | Department of Electrical, Biomedical and Mechatronics Engineerin |
Wang, Tianfu | Shenzhen University |
Qin, Jing | Center for Smart Health, School of Nursing, the Hong Kong Polyte |
Lei, Baiying | Shenzhen University |
Keywords: Image segmentation, Brain, Magnetic resonance imaging (MRI)
Abstract: Brain lesion segmentation is crucial for diagnosis, surgical planning, and analysis. Owing to the fact that pixel values of brain lesions in magnetic resonance (MR) scans are distributed over the wide intensity range, there is always a considerable overlap between the class-conditional densities of lesions. Hence, an accurate automatic brain lesion segmentation is still a challenging task. We present a novel architecture based on conditional generative adversarial networks (cGANs) to improve the lesion contrast for segmentation. To this end, we propose a novel generator adaptively calibrating the input pixel values, and a Markovian discriminator to estimate the distribution of tumors. We further propose the Enhancement and Segmentation GAN (Enh-Seg-GAN) which effectively incorporates the classifier loss into the adversarial one during training to predict the central labels of the sliding input patches. Particularly, the generated synthetic MR images are a substitute for the real ones to maximize lesion contrast while suppressing the background. The potential of proposed frameworks is confirmed by quantitative evaluation compared to the state-of-the-art methods on BraTS'13 dataset.
|
|
10:30-12:00, Paper TuAbPo-04.4 | Add to My Program |
AF-SEG: An Annotation-Free Approach for Image Segmentation by Self-Supervision and Generative Adversarial Network |
|
Yu, Fei | Peking University |
Dong, Hexin | Peking University |
Zhang, Mo | Peking University |
Zhao, Jie | Peking University |
Dong, Bin | Peking University |
Li, Quanzheng | Harvard Medical School, Massachusetts General Hospital |
Zhang, Li | Peking University |
Keywords: Image segmentation, Image synthesis, Vessels
Abstract: Traditional segmentation methods are annotation-free but usually produce unsatisfactory results. The latest leading deep learning methods improve the results but require expensive and time-consuming pixel-level manual annotations. In this work, we propose a novel method based on self-supervision and generative adversarial network (GAN), which has high performance and requires no manual annotations. First, we perform traditional segmentation methods to obtain coarse segmentation. Then, we use GAN to generate a synthetic image, on which the image foreground is pixel-to-pixel corresponding to the coarse segmentation. Finally, we train the segmentation model with the data pairs of synthetic images and coarse segmentations. We evaluate our method on two types of segmentation tasks, including red blood cell (RBC) segmentation on microscope images and vessel segmentation on digital subtraction angiographies (DSA). The results show that our annotation-free method provides a considerable improvement over the traditional methods and achieves comparable accuracies with fully supervised methods.
|
|
10:30-12:00, Paper TuAbPo-04.5 | Add to My Program |
MixModule: Mixed CNN Kernel Module for Medical Image Segmentation |
|
Yu, Heng | Tsinghua University |
Feng, Xue | University of San Francisco |
Wang, Ziwen | Boston University |
Sun, Hao | University of Southern California |
Keywords: Image segmentation
Abstract: Convolutional neural networks (CNNs) have been successfully applied to medical image classification, segmentation, and related tasks. Among the many CNNs architectures, U-Net and its improved versions based are widely used and achieve state-of-the-art performance these years. These improved architectures focus on structural improvements and the size of the convolution kernel is generally fixed. In this paper, we propose a module that combines the benefits of multiple kernel sizes and apply it to U-Net its variants. We test our module on three segmentation benchmark datasets and experimental results show significant improvement.
|
|
10:30-12:00, Paper TuAbPo-04.6 | Add to My Program |
Image Segmentation Using Hybrid Representations |
|
Desai, Alakh | International Institute of Information Technology, Hyderabad |
Chauhan, Ruchi | International Institute of Information Technology, Hyderabad |
Sivaswamy, Jayanthi | International Institute of Information Technology-Hyderabad |
Keywords: Image segmentation, Ultrasound, Eye
Abstract: This work explores a hybrid approach to segmentation as an alternative to a purely data driven approach. We introduce an end-to-end U-Net based network called DU-Net, which uses additional frequency preserving features, namely the Scattering Coefficients (SC) for medical image segmentation. SC are translation invariant and Lipschitz continuous to deformations which help DU-Net outperform other conventional CNN counterparts on four datasets and two segmentation tasks: Optic Disc and Optic Cup in color fundus images and fetal Head in ultrasound images. The proposed method shows remarkable improvement over the basic U-Net with performance competitive to state-of-the-art methods. The results indicate that it is possible to use a lighter network trained with fewer images (without any augmentation) to attain good segmentation results.
|
|
10:30-12:00, Paper TuAbPo-04.7 | Add to My Program |
Mitigating Adversarial Attacks on Medical Image Understanding Systems |
|
Paul, Rahul | University of South Florida , Tampa |
Schabath, Matthew | H.L.Moffitt Cancer Center & Research Institute, Tampa, Florida |
Gillies, Robert | Departments of Diagnostic Radiology and Imaging Research, H. Lee |
Hall, Lawrence | University of South Florida |
Goldgof, Dmitry | University of South Florida |
Keywords: Computer-aided detection and diagnosis (CAD), Classification, Computed tomography (CT)
Abstract: Deep learning systems are now being widely used to analyze lung cancer. However, recent work has shown a deep learning system can be easily fooled by intentionally adding some noise in the image. This is called as Adversarial attack. This paper presents an adversarial attack for malignancy prediction of lung nodules. We found that the adversarial attack can cause significant changes in lung nodule malignancy prediction accuracy. An ensemble-based defense strategy was developed to reduce the effect of an adversarial attack. A multi-initialization based CNN ensemble was utilized. We also explored adding adversarial images in the training set, which eventually reduced the rate of mis-classification and made the CNN models more robust to an adversarial attack. A subset of cases from the National Lung Screening Trial (NLST) dataset were used in our study. Initially, 75.1%, 75.5% and 76% classification accuracy were obtained from the three CNNs on original images (without an adversarial attack). Fast Gradient Sign Method (FGSM) and one-pixel attacks were analyzed. After the FGSM attack, 46.4%, 39.24%, and 39.71% accuracy was obtained from the 3 CNNs. Whereas, after a one pixel attack 72.15%, 73%, and 73% classification accuracy was achieved. FGSM caused much more damaged to CNN prediction. With a multi-initialization based ensemble and including adversarial images in the training set, 82.27% and 81.43% classification accuracy were attained after FGSM and one-pixel attacks respectively.
|
|
10:30-12:00, Paper TuAbPo-04.8 | Add to My Program |
CSAF-CNN: Cross-Layer Spatial Attention Map Fusion Network for Organ-At-Risk Segmentation in Head and Neck CT Images |
|
Liu, Zuhao | University of Electronic Science and Technology of China |
Wang, Huan | University of Electronic Science and Technology of China, Chengd |
Lei, Wenhui | University of Electronic Science and Technology of China |
Wang, Guotai | University of Electronic Science and Engineering of China (UESTC |
Keywords: Image segmentation, Machine learning, Computed tomography (CT)
Abstract: Accurate segmentation of organ at risk (OARs) in head and neck CT images is critical for planning of radiotherapy of the nasopharynx cancer. In segmentation tasks, fully convolutional networks (FCNs) are widely used. Recently, as a kind of attention module, concurrent squeeze and excitation (scSE) blocks in FCNs are proved to have good performance. However, the attention feature maps generated by scSE blocks are isolated from each other, which doesn’t help network notice the similarities among different feature maps. Consequently, we propose cross-layer spatial attention map fusion network (CSAF-CNN) to fuse different spatial attention maps to solve this problem. In addition, we introduce a top-k exponential logarithmic dice loss (TELD-Loss) in OARs segmentation, which effectively alleviates the serious sample imbalance problem of this task. We evaluate our framework in the head & neck CT scans of nasopharynx cancer patients in StructSeg 2019 challenge. We validate the effectiveness of the proposed method through ablation study, and achieve very competitive results.
|
|
TuAbPo-05 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Machine Learning, Pattern Recognition Methods |
|
|
Chair: Amini, Amir | University of Louisville |
|
10:30-12:00, Paper TuAbPo-05.1 | Add to My Program |
Using Transfer Learning and Class Activation Maps Supporting Detection and Localization of Femoral Fractures on Anteroposterior Radiographs |
|
Gupta, Vikash | The Ohio State University |
Demirer, Mutlu | The Ohio State University |
Bigelow, Matthew | Ohio State University |
Yu, Sarah | The Ohio State University |
Yu, Joseph | The Ohio State University |
Prevedello, Luciano | The Ohio State University |
White, Richard D | Ohio State University Wexner Medical Center |
Erdal, Barbaros | Department of Radiology, the Wexner Medical Center, the Ohio Sta |
Keywords: X-ray imaging, Bone, Machine learning
Abstract: Acute Proximal Femoral Fractures are a growing health concern among the aging population. These fractures are often associated with significant morbidity and mortality as well as reduced quality of life. Furthermore, with the increasing life expectancy owing to advances in healthcare, the number of proximal femoral fractures may increase by a factor of 2 to 3, since the majority of fractures occur in patients over the age of 65. In this paper, we show that by using transfer learning and leveraging pre-trained models, we can achieve very high accuracy in detecting fractures and that they can be localized utilizing class activation maps.
|
|
10:30-12:00, Paper TuAbPo-05.2 | Add to My Program |
Knowledge Transfer between Datasets for Learning-Based Tissue Microstructure Estimation |
|
Qin, Yu | Beijing Institute of Technology |
Li, Yuxing | Beijing Institute of Technology |
Liu, Zhiwen | Beijing Institute of Technology |
Ye, Chuyang | Beijing Institute of Technology |
Keywords: Diffusion weighted imaging, Brain, Machine learning
Abstract: Learning-based approaches, especially those based on deep networks, have enabled high-quality estimation of tissue microstructure from low-quality diffusion magnetic resonance imaging (dMRI) scans, which are acquired with a limited number of diffusion gradients and a relatively poor spatial resolution. These learning-based approaches to tissue microstructure estimation require acquisitions of training dMRI scans with high-quality diffusion signals, which are densely sampled in the q-space and have a high spatial resolution. However, the acquisition of training scans may not be available for all datasets. Therefore, we explore knowledge transfer between different dMRI datasets so that learning-based tissue microstructure estimation can be applied for datasets where training scans are not acquired. Specifically, for a target dataset of interest, where only low-quality diffusion signals are acquired without training scans, we exploit the information in a source dMRI dataset acquired with high-quality diffusion signals. We interpolate the diffusion signals in the source dataset in the q-space using a dictionary-based signal representation, so that the interpolated signals match the acquisition scheme of the target dataset. Then, the interpolated signals are used together with the high-quality tissue microstructure computed from the source dataset to train deep networks that perform tissue microstructure estimation for the target dataset. Experiments were performed on brain dMRI scans with low-quality diffusion signals, where the benefit of the proposed strategy is demonstrated.
|
|
10:30-12:00, Paper TuAbPo-05.3 | Add to My Program |
Deep Learning Models to Study the Early Stages of Parkinson’s Disease |
|
Munoz Ramirez, Veronica | Université Grenoble-Alpes |
Kmetzsch, Virgilio | Inria |
Forbes, Florence | INRIA Jean Kuntzman Laboratory , Grenoble University |
Dojat, Michel | INSERM U1216 |
Keywords: Pattern recognition and classification, Magnetic resonance imaging (MRI), Brain
Abstract: Current physio-pathological data suggest that Parkinson's Disease (PD) symptoms are related to important alterations in subcortical brain structures. However, structural changes in these small structures remain difficult to detect for neuro-radiologists, in particular, at the early stages of the disease ('de novo' PD patients). The absence of a reliable ground truth at the voxel level prevents the application of traditional supervised deep learning techniques. In this work, we consider instead an anomaly detection approach and show that auto-encoders (AE) could provide an efficient anomaly scoring to discriminate 'de novo' PD patients using quantitative Magnetic Resonance Imaging (MRI) data.
|
|
10:30-12:00, Paper TuAbPo-05.4 | Add to My Program |
Liver Segmentation in CT with MRI Data: Zero-Shot Domain Adaptation by Contour Extraction and Shape Priors |
|
Pham, Duc Duy | University of Duisburg-Essen |
Dovletov, Gurbandurdy | University of Duisburg-Essen |
Pauli, Josef | Duisburg-Essen, Intelligente Systeme |
Keywords: Image segmentation, Liver
Abstract: In this work we address the problem of domain adaptation for segmentation tasks with deep convolutional neural networks. We focus on managing the domain shift from MRI to CT volumes on the example of 3D liver segmentation. Domain adaptation between modalities is particularly of practical importance, as different hospital departments usually tend to use different imaging modalities and protocols in their clinical routine. Thus, training a model with source data from one department may not be sufficient for application in another institution. Most adaptation strategies make use of target domain samples and often additionally incorporate the corresponding ground truths from the target domain during the training process. In contrast to these approaches, we investigate the possibility of training our model solely on source domain data sets, i.e. we apply zero-shot domain adaptation. To compensate the missing target domain data, we use prior knowledge about both modalities to steer the model towards more general features during the training process. We particularly make use of fixed Sobel kernels to enhance contour information and apply anatomical priors, learned separately by a convolutional autoencoder. Although we completely discard including the target domain in the training process, our proposed approach improves a vanilla U-Net implementation drastically and yields promising segmentation results.
|
|
10:30-12:00, Paper TuAbPo-05.5 | Add to My Program |
Deep Random Forests for Small Sample Size Prediction with Medical Imaging Data |
|
Katzmann, Alexander | Siemens Healthcare GmbH |
Mühlberg, Alexander | Siemens Healthcare GmbH |
Suehling, Michael | Siemens AG |
Noerenberg, Dominik | University Hospital Großhadern, Ludwig-Maximilians-University Mu |
Holch, Julian Walter | University Hospital Grohadern, Ludwig-Maximilians-University Mün |
Gross, Horst-Michael | University of Technology Ilmenau |
Keywords: Machine learning, Pattern recognition and classification, Computed tomography (CT)
Abstract: Deep neural networks represent the state of the art for computer-aided medical imaging assessment, e.g. lesion detection, organ segmentation and disease classification. While for large datasets their superior performance is a clear argument, medical imaging data is often small and highly heterogeneous. In combination with the typical parameter amount in deep neural networks, this often leads to overfitting and results in a low level of generalization performance. We propose a straight-forward combination of random forests and deep neural networks for superior performance on medical imaging datasets with only small data, and provide an extensive evaluation of survival prediction for metastatic colorectal cancer patients using computed tomography imaging data, with our proposed method clearly outperforming other approaches.
|
|
10:30-12:00, Paper TuAbPo-05.6 | Add to My Program |
Modeling Heterogeneity in Feature Selection for MCI Classification |
|
Zhu, Wei | University of Rochester |
Shi, Feng | Cedars Sinai Medical Center |
Luo, Jiebo | University of Rochester |
Keywords: Dimensionality reduction, Machine learning, fMRI analysis
Abstract: Conventional methods designed for Mild Cognitive Impairment (MCI) classification usually assume that the MCI subjects are homogeneous. However, recent discoveries indicate that MCI has heterogeneous neuropathological origins which may contribute to the sub-optimal performance of conventional methods. To compensate for the limitations of existing methods, we propose Maximum Margin Heterogeneous Feature Selection (MMHFS) by explicitly considering the heterogeneous distribution of MCI data. More specifically, the proposed method simultaneously performs unsupervised clustering discovery on MCI data and conducts discriminant feature selection to help classify MCI from Normal Control (NC). It is worth noting that these two processes can benefit from each other, thus enabling the proposed method to achieve better performance.
|
|
10:30-12:00, Paper TuAbPo-05.7 | Add to My Program |
Training Liver Vessel Segmentation Deep Neural Networks on Noisy Labels from Contrast CT Imaging |
|
Xu, Minfeng | Alibaba |
Wang, Yu | Alibaba |
Chi, Ying | Alibaba Group |
Hua, Xian-Sheng | Alibaba Group |
Keywords: Image segmentation, Liver, Computed tomography (CT)
Abstract: Liver vessel segmentation from contrast CT images is critical in liver surgical planning and navigation. Due to the complex vessel systems, manual segmentation of liver vessel is laborious and error-prone. In this work we propose liver vessel segmentation deep neural networks which are able to perform the segmentation automatically. Dense image labelling incurred by normal deep learning based segmentation makes it impractical for vessel segmentation. On the contrary, our method only requires a few of initial voxel-level labels, and thus tremendously reduces the workload of manual annotating. A small number of liver vessels are firstly annotated and used to train a sparse dictionary and logistic regressor to get the preliminary vessel predictions. Then the proposed deep neural network is trained based on bootstrapping technique where the training target is a convex combination of the model predictions and those preliminary vessel predictions. Followed by the post-processing step consisting of region connection and noisy removal, the liver vessel tree is finally built from model predictions. Experimental results of3DIRCADb dataset show that the proposed method can effectively extract liver vessel trees from contrast CT images with minimum annotations.The state-of-art results have been achieved on this small dataset with the average dice and sensitivity 0.687±0.041 and 0.786±0.105 respectively.
|
|
10:30-12:00, Paper TuAbPo-05.8 | Add to My Program |
Super-Resolution and Self-Attention with Generative Adversarial Network for Improving Malignancy Characterization of Hepatocellular Carcinoma |
|
Li, Yunling | Guangzhou University of Chinese Medicine |
Huang, Hui | Guangzhou University of Chinese Medicine |
Zhang, Lijuan | Shenzhen Institute of Advanced Technology |
Wang, Guangyi | Guangdong General Hospital |
Zhang, Honglai | Guangzhou University of Chinese Medicine |
Zhou, Wu | Guangzhou University of Chinese Medicine |
Keywords: Computer-aided detection and diagnosis (CAD), Liver, Magnetic resonance imaging (MRI)
Abstract: The slice thickness of MR imaging may remarkably degrade the clarity of 3D lesion images within through-plane slices (coronal or sagittal views) so as to influence the performance of lesion characterization. To alleviate the problem, we propose an end-to-end super-resolution and self-attention framework based on Generative adversarial networks (GAN) for improving the malignancy characterization of hepatocellular carcinoma (HCC). Specifically, a super-resolution subnetwork is designed to enhance the low-resolution patches of coronal or sagittal views based on texture transferred from the high-resolution patches of the axial view, and then the enhanced patches are fed into the classification subnetwork for malignancy characterization. Furthermore, a self-attention mechanism is utilized to extract multiple discriminative features for better super-resolution and lesion characterization. Experimental results of clinical HCCs demonstrate the superior performance of the proposed method compared with conventional CNN-based methods and show the potential in clinical practice.
|
|
TuAbPo-06 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Optical Coherence Tomography I |
|
|
Chair: Marziliano, Pina | Ecole Polytechnique Federale De Lausanne |
|
10:30-12:00, Paper TuAbPo-06.1 | Add to My Program |
Oct Image Quality Evaluation Based on Deep and Shallow Features Fusion Network |
|
Wang, Rui | PingAn Technology (Shenzhen) Co., Ltd |
Fan, Dongyi | PingAn Technology(ShenZhen)Co., Ltd |
Wang, Lilong | PingAn Technology |
Lv, Bin | PingAn Technology (Shenzhen) Co., Ltd |
Wang, Min | Department of Ophthalmology, Eye and ENT Hospital of Fudan Unive |
Zhou, Qienyuan | Optovue, Inc. (Fremont, California, USA) |
Lv, Chuanfeng | PingAn Tech |
Xie, Guotong | PingAn Tech |
Keywords: Optical coherence tomography, Image quality assessment, Eye
Abstract: Optical coherence tomography (OCT) has become an important tool for the diagnosis of retinal diseases, and image quality assessment on OCT images has considerable clinical significance for guaranteeing the accuracy of diagnosis by ophthalmologists. Traditional OCT image quality assessment is usually based on hand-crafted features including signal strength index and signal to noise ratio. These features only reflect a part of image quality, but cannot be seen as a full representation on image quality. Especially, there is no detailed description of OCT image quality so far. In this paper, we firstly define OCT image quality as three grades (‘Good’, ‘Usable’ and ‘Poor’). Considering the diversity of image quality, we then propose a deep and shallow features fusion network (DSFF-Net) to conduct multiple label classification. The DSFF-Net combines deep and enhanced shallow features of OCT images to predict the image quality grade. The experimental results on a large OCT dataset show that our network obtains state-of-the-art performance, outperforming the other classical CNN networks.
|
|
10:30-12:00, Paper TuAbPo-06.2 | Add to My Program |
Noise Redistribution and 3D Shearlet Filtering for Speckle Reduction in Optical Coherence Tomography |
|
Hu, Yan | Southern University of Science and Technology |
Yang, Jianlong | Cixi Institute of Biomedical Engineering, Chinese Academy of Sci |
Cheng, Jun | Institute of Biomedical Engineering, Chinese Academy of Sciences |
Liu, Jiang | Southern University of Science and Technology |
Keywords: Image enhancement/restoration(noise and artifact reduction), Optical coherence tomography, Eye
Abstract: Optical coherence tomography (OCT) is a micrometer-resolution, cross-sectional imaging modality for biological tissue. It has been widely applied for retinal imaging in ophthalmology. However, the large speckle noise affects the analysis of OCT retinal images and their diagnostic utility. In this article, we present a new speckle reduction algorithm for 3D OCT images. The OCT speckle noise is approximated as Poisson distribution, which is difficult to be removed for its signal-dependent characteristic. Thus our algorithm is consisted by two steps: first, a variance-stabilizing trans-formation, named Anscombe transformation, is applied to redistribute the multiplicative speckle noise into an additive Gaussian noise; then the transformed data is decomposed and filtered in 3D Shearlet domain, which provides better representation of the edge information of the retinal layers than wavelet and curvelet. The proposed method is evaluated through the three parameters using high-definition B-scans as the ground truth. Quantitative experimental results show that our method gives out the best evaluation parameters, and highest edge contrast, compared with state-of-the-art OCT denoising algorithms.
|
|
10:30-12:00, Paper TuAbPo-06.3 | Add to My Program |
Unsupervised Domain Adaptation for Cross-Device Oct Lesion Detection Via Learning Adaptive Features |
|
Yang, Suhui | Ping an technology(Shenzhen) Co.Ltd., Shenzhen, China |
Zhou, Xia | Ping an Technology (Shenzhen) Co. Ltd., Shenzhen, China |
Jun, Wang | PingAn Techlonogy Co. Ltd |
Xie, Guotong | PingAn Tech |
Lv, Chuanfeng | PingAn Tech |
Gao, Peng | Ping an Technology Co., Ltd |
Lv, Bin | PingAn Technology (Shenzhen) Co., Ltd |
Keywords: Optical coherence tomography, Computer-aided detection and diagnosis (CAD), Eye
Abstract: Optical coherence tomography (OCT) is widely used in computer-aided medical diagnosis of retinal pathologies. Deep convolutional network has been successfully applied to detect lesions from OCT images. Different OCT imaging devices inevitably cause variation in the distribution between training phase and testing phase, which will lead to extremely reduction on model performance. Most existing unsupervised domain adaptation methods are mainly focused on lesion segmentation, there are few studies on lesion detection tasks especially for OCT images. In this paper, we propose a novel unsupervised domain adaptation framework adaptively learning feature representation to achieve cross-device lesion detection for OCT images. Firstly, we design global and local adversarial discriminators to force the networks to learn device-independent features. Secondly, we develop a non-parameter adaptive feature norm into global adversarial discriminator to stabilize the discrimination in target domain. Finally, we perform the validation experiment on lesion detection task across two OCT devices. The results exhibit that the proposed framework has promising performance compared with other unsupervised domain adaptation approaches.
|
|
10:30-12:00, Paper TuAbPo-06.4 | Add to My Program |
Macular GCIPL Thickness Map Prediction Via Time-Aware Convolutional LSTM |
|
Zhiqi, Chen | New York University |
Wang, Yao | Polytechnic Institute of New York University |
Wollstein, Gadi | Department of Ophthalmology, New York University |
Ramos-Cadena, Maria de los Angeles | Department of Ophthalmology, New York University |
Schuman, Joel S. | NYU Langone Health, NYU School of Medicine |
Ishikawa, Hiroshi | Department of Ophthalmology, New York University |
Keywords: Machine learning, Eye, Optical coherence tomography
Abstract: Macular ganglion cell inner plexiform layer (GCIPL) thickness is an important biomarker for clinical managements of glaucoma. Clinical analysis of GCIPL progression uses averaged thickness only, which easily washes out small changes and reveals no spatial patterns. This is the first work to predict the 2D GCIPL thickness map. We propose a novel Time-aware Convolutional Long Short-Term Memory (TC-LSTM) unit to decompose memories into the short-term and long-term memories and exploit time intervals to penalize the short-term memory. TC-LSTM unit is incorporated into an auto-encoder-decoder so that the end-to-end model can handle irregular sampling intervals of longitudinal GCIPL thickness map sequences and capture both spatial and temporal correlations. Experiments show the superiority of the proposed model over the traditional method.
|
|
10:30-12:00, Paper TuAbPo-06.5 | Add to My Program |
Hierarchy-Constrained Network for Corneal Tissue Segmentation Based on Anterior Segment Oct Images |
|
Liu, Yang | PingAn Technology (Shenzhen) Co., Ltd |
Li, Dongfang | QingDao Eye Hospital of Shandong First Medical University |
Guo, Yan | PingAn Technology (Shenzhen) Co., Ltd., Shenzhen, China |
Zhou, Xia | Ping an Technology (Shenzhen) Co. Ltd., Shenzhen, China |
Dong, Yanling | QingDao Eye Hospital of Shandong First Medical University |
Guo, Zhen | Qingdao Eye Hospital of Shandong First Medical University |
Xie, Guotong | PingAn Tech |
Lv, Chuanfeng | PingAn Tech |
Lv, Bin | PingAn Technology (Shenzhen) Co., Ltd |
Keywords: Optical coherence tomography, Eye, Image segmentation
Abstract: Anterior segment optical coherence tomography (AS-OCT) is widely used to observe the corneal tissue structures in clinical ophthalmology. Accurate segmentation of corneal tissue interfaces is essential for corneal diseases diagnosis and surgical planning. However, image scattered noise and keratopathy make corneal tissue interface fitting results of the existing methods deviate. In this paper, we propose a hierarchy-constrained network, which combines hierarchical features by using of an elegant progressive feature-extraction module and boundary constraint to overcome these challenges. In the meantime, multi-level prediction fusion module is integrated to the network that eventually enables the output node to sufficiently absorb features extracted from various levels. Extensive experimental results on two datasets containing cornea images with multiple lesions show that our proposed method distinctly improves the accuracy of corneal tissue interfaces segmentation and outperforms other existing methods.
|
|
10:30-12:00, Paper TuAbPo-06.6 | Add to My Program |
Deep Learning for High Speed Optical Coherence Elastography |
|
Neidhardt, Maximilian | Hamburg University of Technology |
Bengs, Marcel | Hamburg University of Technology |
Latus, Sarah | Hamburg University of Technology |
Schlüter, Matthias | Hamburg University of Technology |
Saathoff, Thore | Hamburg University of Technology |
Schlaefer, Alexander | Hamburg University of Technology |
Keywords: Optical coherence tomography, Machine learning, Elasticity measures
Abstract: Mechanical properties of tissue provide valuable information for identifying lesions. One approach to obtain quantitative estimates of elastic properties is shear wave elastography with optical coherence elastography (OCE). However, given the shear wave velocity, it is still difficult to estimate elastic properties. Hence, we propose deep learning to directly predict elastic tissue properties from OCE data. We acquire 2D images with a frame rate of 30 kHz and use convolutional neural networks to predict gelatin concentration, which we use as a surrogate for tissue elasticity. We compare our deep learning approach to predictions from conventional regression models, using the shear wave velocity as a feature. Mean absolut prediction errors for the conventional approaches range from 1.32+-0.98 p.p. to 1.57+-1.30 p.p. whereas we report an error of 0.90+-0.84 p.p. for the convolutional neural network with 3D spatio-temporal input. Our results indicate that deep learning on spatio-temporal data outperforms elastography based on explicit shear wave velocity estimation.
|
|
TuAbPo-07 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Optical Microscopy and Analysis II |
|
|
Co-Chair: Jug, Florian | MPI-CBG |
|
10:30-12:00, Paper TuAbPo-07.1 | Add to My Program |
Reservoir Computing for Jurkat T-Cell Segmentation in High Resolution Live Cell Ca2+ Fluorescence Microscopy |
|
Hadaeghi, Fatemeh | Institute of Computational Neuroscience, Universitätskliniku |
Diercks, Björn-Philipp | University Medical Center Hamburg-Eppendorf |
Wolf, Insa M. A. | University Medical Center Hamburg-Eppendorf |
Werner, René | University Medical Center Hamburg-Eppendorf |
Keywords: Microscopy - Light, Confocal, Fluorescence, In-vivo cellular and molecular imaging, Image segmentation
Abstract: The reservoir computing (RC) paradigm is exploited to detect Jurkat T cells and antibody-coated beads in fluorescence microscopy data. Recent progress in imaging of subcellular calcium (Ca 2+) signaling offers a high spatial and temporal resolution to characterize early signaling events in T cells. However, data acquisition with dual-wavelength Ca 2+ indicators, the photo-bleaching at high acquisition rate, low signal-to-noise ratio, and temporal fluctuations of image intensity entail corporation of post-processing techniques into Ca 2+ imaging systems. Besides, although continuous recording enables real-time Ca 2+ signal tracking in T cells, reliable automated algorithms must be developed to characterize the cells, and to extract the relevant information for conducting further statistical analyses. Here, we present a robust two-channel segmentation algorithm to detect Jurkat T lymphocytes as well as antibody-coated beads that are utilized to mimic cell-cell interaction and to activate the T cells in microscopy data. Our algorithm uses the reservoir computing framework to learn and recognize the cells -- taking the spatiotemporal correlations between pixels into account. A comparison of segmentation accuracy on testing data between our proposed method and the deep learning U-Net model confirms that the developed model provides accurate and computationally cheap solution to the cell segmentation problem.
|
|
10:30-12:00, Paper TuAbPo-07.2 | Add to My Program |
Enumeration of Ampicillin-Resistant E. Coli in Blood Using Droplet Microfluidics and High-Speed Image Processing |
|
Li, Yiyan | Fort Lewis College |
Cherukury, Hemanth | University of California - Irvine |
Zimak, Jan | University of California - Irvine |
Harrison, Jacob | Fort Lewis College |
Peterson, Ellena | University of California - Irvine |
Zhao, Weian | University of California - Irvine |
Keywords: Molecular and cellular screening, Microscopy - Light, Confocal, Fluorescence, Image compression
Abstract: Bacteria entering the bloodstream causes bloodstream infection (BSI). Without proper treatment, BSI can lead to sepsis which is a life-threatening condition. Detection of bacteria in blood at the early stages of BSI can effectively prevent the development of sepsis. Using microfluidic droplets for single bacterium encapsulation provides single-digit bacterial detection sensitivity. In this study, samples of ampicillin-resistant E. coli in human blood were partitioned into millions of 30 μm diameter microfluidic droplets and followed by 8-hour culturing. Thousands of fluorescent bacteria from a single colony filled up the positive droplets after the culturing process. A circle detection software based on Hough Transform was developed to count the number of positive droplets from fluorescence images. The period to process one image can be as short as 0.5 ms when the original image is pre-processed and binarized by the developed software.
|
|
10:30-12:00, Paper TuAbPo-07.3 | Add to My Program |
Single-Molecule Localization Microscopy Reconstruction Using Noise2Noise for Super-Resolution Imaging of Actin Filaments |
|
Lefebvre, Joël | University of Oxford |
Javer, Avelino | University of Oxford |
Dmitrieva, Mariia | University of Oxford |
Lewkow, Bohdan | University of Cambridge |
Allgeyer, Edward | University of Cambridge |
Sirinakis, George | University of Cambridge |
St. Johnston, Daniel | University of Cambridge |
Rittscher, Jens | University of Oxford |
Keywords: Image enhancement/restoration(noise and artifact reduction), Microscopy - Super-resolution, Cells & molecules
Abstract: Single-molecule localization microscopy (SMLM) is a super-resolution imaging technique developed to image structures smaller than the diffraction limit. This modality results in sparse and non-uniform sets of localized blinks that need to be reconstructed to obtain a super-resolution representation of a tissue. In this paper, we explore the use of the Noise2Noise (N2N) paradigm to reconstruct the SMLM images. Noise2Noise is an image denoising technique where a neural network is trained with only pairs of noisy realizations of the data instead of using pairs of noisy/clean images, as performed with Noise2Clean (N2C). Here we have adapted Noise2Noise to the 2D SMLM reconstruction problem, exploring different pair creation strategies (fixed and dynamic). The approach was applied to synthetic data and to real 2D SMLM data of actin filaments. This revealed that N2N can achieve reconstruction performances close to the Noise2Clean training strategy, without having access to the super-resolution images. This could open the way to further improvement in SMLM acquisition speed and reconstruction performance.
|
|
10:30-12:00, Paper TuAbPo-07.4 | Add to My Program |
Ising-GAN: Annotated Data Augmentation with a Spatially Constrained Generative Adversarial Network |
|
Dimitrakopoulos, Panagiotis | University of Ioannina |
Sfikas, Giorgos | University of Ioannina |
Nikou, Christophoros | University of Ioannina |
Keywords: Image synthesis, Cells & molecules, Image enhancement/restoration(noise and artifact reduction)
Abstract: Data augmentation is a popular technique with which new dataset samples are artificially synthesized to the end of aiding training of learning-based algorithms and avoiding overfitting. Methods based on Generative adversarial networks (GANs) have recently rekindled interest in research on new techinques for data augmentation. With the current paper we propose a new GAN-based model for data augmentation, comprising a suitable Markov Random Field-based spatial constraint that encourages synthesis of spatially smooth outputs. Oriented towards use with medical imaging sets where a localization/segmentation annotation is available, our model can simultaneously also produce artificial annotations. We gauge performance numerically by measuring performance of U-Net trained to detect cells on microscopy images, by taking into account the produced augmented dataset. Numerical trials, as well as qualitative results validate the usefulness of our model.
|
|
10:30-12:00, Paper TuAbPo-07.5 | Add to My Program |
ESCELL: Emergent Symbolic Cellular Language |
|
Chowdhury, Aritra | GE Research |
Kubricht, James | GE Research |
Sood Anup, Anup | GE Global Research |
Santamaria, Alberto | GE Global Research |
Tu, Peter | General Electric |
Keywords: Machine learning, Classification, Microscopy - Light, Confocal, Fluorescence
Abstract: We present ESCELL, a method for developing an emergent symbolic language of communication between multiple agents reasoning about cells. We show how agents are able to cooperate and communicate successfully in the form of symbols similar to human language to accomplish a task in the form of a referential game (Lewis’ signaling game). In one form of the game, a sender and a receiver observe a set of cells from 5 different cell phenotypes. The sender is told one cell is a target and is allowed to send one symbol to the receiver from a fixed arbitrary vocabulary size. The receiver relies on the information in the symbol to identify the target cell. We train the sender and receiver networks to develop an innate emergent language between themselves to accomplish this task. We observe that the networks are able to successfully identify cells from 5 different phenotypes with an accuracy of 93.2%. We also introduce a new form of the signaling game where the sender is shown one image instead of all the images that the receiver sees. The networks successfully develop an emergent language to get an identification accuracy of 77.8%.
|
|
10:30-12:00, Paper TuAbPo-07.6 | Add to My Program |
Image-Based Simulations of Tubular Network Formation |
|
Svoboda, David | Masaryk University |
Nečasová, Tereza | Masaryk University |
Keywords: Microscopy - Light, Confocal, Fluorescence, Cells & molecules, Image synthesis
Abstract: The image-based simulations in biomedicine play an important role as the real image data are difficult to be fully and precisely annotated. An increasing capability of contemporary computers allows to model and simulate reasonably complicated structures and in the last years also the dynamic processes. In this paper, we introduce a complex 3D model that describes the structure and dynamics of the population of endothelial cells. The model is based on standard cellular Potts model. It describes the formation process of a complex tubular network of endothelial cells fully in 3D together with the simulation of the cell death called apoptosis. The generated network imitates the structure and behavior that can be observed in real phase-contrast microscopy. The generated image data may serve as a benchmark dataset for newly designed detection or tracking algorithms.
|
|
10:30-12:00, Paper TuAbPo-07.7 | Add to My Program |
Confocal Imaging of Intercellular Calcium in HeLa Cells for Monitoring Drug-Response: Biophysical Framework for Visualization of the Time-Lapse Images |
|
Gare, Suman | Indian Institute of Technology Hyderabad |
Saxena, Abha | Indian Institute of Technology Hyderabad, |
Giri, Lopamudra | Indian Institute of Technology Hyderabad |
Keywords: Microscopy - Light, Confocal, Fluorescence, Visualization, Quantification and estimation
Abstract: Recent advancements in biomedical imaging focus on fluorescent imaging using laser scanning confocal microscopy. However, high-resolution imaging of cellular activity remains considerably expensive for both in vitro and in vivo model. In this context, integration of mathematical modeling and imaging data analysis to predict the cellular activity may aid understanding of cell signaling. Here we performed dynamic imaging using confocal microscopy and propose a model considering cell to cell connectivity that can predict the effect of drug on Ca2+ oscillations. The proposed model consists of large number of ordinary differential (ODE) equations and uses the concept of adjoint matrix containing coupling factors to capture the activity of cells with random arrangement. The results show that the cell-to-cell connection plays a crucial role in controlling the calcium oscillations through a diffusion-based mechanism. The present simulation tool can be used as generalized framework to generate and visualize the time-lapse videos required for in vitro drug testing for various drug doses.
|
|
10:30-12:00, Paper TuAbPo-07.8 | Add to My Program |
Estimation of Cell Cycle States of Human Melanoma Cells with Quantitative Phase Imaging and Deep Learning |
|
Henser-Brownhill, Tristan | University of Manchester |
Ju, Robert J. | The University of Queensland Institute for Molecular Bioscience, |
Haass, Nikolas K. | The University of Queensland |
Stehbens, Samantha J. | The University of Queensland Institute for Molecular Bioscience, |
Ballestrem, Christoph | Wellcome Trust Centre for Cell Matrix Research, School of Biolog |
Cootes, Timothy F. | Division of Informatics, Imaging & Data Sciences, School of Heal |
Keywords: Microscopy - Light, Confocal, Fluorescence, Single cell & molecule detection, Machine learning
Abstract: Visualization and classification of cell cycle stages in live cells requires the introduction of transient or stably expressing fluorescent markers. This is not feasible for all cell types, and can be time consuming to implement. Labelling of living cells also has the potential to perturb normal cellular function. Here we describe a computational strategy to estimate core cell cycle stages without markers by taking advantage of features extracted from information-rich ptychographic time-lapse movies. We show that a deep-learning approach can estimate the cell cycle trajectories of individual human melanoma cells from short 3-frame (~23 minute) snapshots, and can identify cell cycle arrest induced by chemotherapeutic agents targeting melanoma driver mutations.
|
|
10:30-12:00, Paper TuAbPo-07.9 | Add to My Program |
Cramer Rao Inequality, Cauchy-Binet Representation and Structural Optimization of Fluorescence Unmixing Experiment |
|
Goun, Alexei | Princeton University |
Keywords: Microscopy - Light, Confocal, Fluorescence, Deconvolution, Image acquisition
Abstract: A predictive theoretical model based on Cramer-Rao bound for the uncertainty in fluorescent protein mixture composition detection has been developed. A physically based representation of the experimental efficiency through the Cauchy-Binet identity is presented. This approach allows the optimal design of the experiments without the introduction of artificial figures of merit.
|
|
10:30-12:00, Paper TuAbPo-07.10 | Add to My Program |
Weakly-Supervised Prediction of Cell Migration Modes in Confocal Microscopy Images Using Bayesian Deep Learning |
|
Gupta, Anindya | Uppsala University, |
Larsson, Veronica Jennie | Karolinska Institutet |
Matuszewski, Damian J. | Uppsala University |
Strömblad, Staffan | Karolinska Institutet |
Wählby, Carolina | Centre for Image Analysis and Science for Life Laboratory, Uppsa |
Keywords: Microscopy - Light, Confocal, Fluorescence, Single cell & molecule detection, Pattern recognition and classification
Abstract: Cell migration is pivotal for their development, physiology and disease treatment. A single cell on a 2D surface can utilize continuous or discontinuous migration modes. To comprehend the cell migration, an adequate quantification for single cell-based analysis is crucial. An automatized approach could alleviate tedious manual analysis, facilitating large-scale drug screening. Supervised deep learning has shown promising outcomes in computerized microscopy image analysis. However, their implication is limited due to the scarcity of carefully annotated data and uncertain deterministic outputs. We compare three deep learning models to study the problem of learning discriminative morphological representations using weakly annotated data for predicting the cell migration modes. We also estimate Bayesian uncertainty to describe the confidence of the probabilistic predictions. Amongst three compared models, DenseNet yielded the best results with a sensitivity of 87.91% at a false negative rate of 1.26%.
|
|
10:30-12:00, Paper TuAbPo-07.11 | Add to My Program |
Transcriptome-Supervised Classification of Tissue Morphology Using Deep Learning |
|
Andersson, Axel | Uppsala University |
Partel, Gabriele | Uppsala University |
Solorzano Vargas, Leslie Evelyn | Uppsala University |
Wählby, Carolina | Centre for Image Analysis and Science for Life Laboratory, Uppsa |
Keywords: Classification, Tissue, Microscopy - Light, Confocal, Fluorescence
Abstract: Deep learning has proven to successfully learn variations in tissue and cell morphology. Training of such models typically relies on expensive manual annotations. Here we conjecture that spatially resolved gene expression, e.i., the transcriptome, can be used as an alternative to manual annotations. In particular, we trained five convolutional neural networks with patches of different size extracted from locations defined by spatially resolved gene expression. The network is trained to classify tissue morphology related to two different genes, general tissue, as well as background, on an image of fluorescence stained nuclei in a mouse brain coronal section. Performance is evaluated on an independent tissue section from a different mouse brain, reaching an average Dice score of 0.51. Results may indicate that novel techniques for spatially resolved transcriptomics together with deep learning may provide a unique and unbiased way to find genotype-phenotype relationships.
|
|
10:30-12:00, Paper TuAbPo-07.12 | Add to My Program |
Extracting Axial Depth and Trajectory Trend Using Astigmatism, Gaussian Fitting, and CNNs for Protein Tracking |
|
Delas Penas, Kristofer | University of Oxford |
Dmitrieva, Mariia | University of Oxford |
Lefebvre, Joël | University of Oxford |
Zenner, Helen | University of Cambridge |
Allgeyer, Edward | University of Cambridge |
Booth, Martin | University of Oxford |
St. Johnston, Daniel | University of Cambridge |
Rittscher, Jens | University of Oxford |
Keywords: Machine learning, Microscopy - Light, Confocal, Fluorescence, Quantification and estimation
Abstract: Accurate analysis of vesicle trafficking in live cells is challenging for a number of reasons: varying appearance, complex protein movement patterns, and imaging conditions. To allow fast image acquisition, we study how employing an astigmatism can be utilized for obtaining additional information that could make tracking more robust. We present two approaches for measuring the z position of individual vesicles.Firstly, Gaussian curve fitting with CNN-based denoising is applied to infer the absolute depth around the focal plane of each localized protein. We demonstrate that adding denoising yields more accurate estimation of depth while preserving the overall structure of the localized proteins. Secondly, we investigate if we can predict using a custom CNN architecture the axial trajectory trend. We demonstrate that this method performs well on calibration beads data without the need for denoising. By incorporating the obtained depth information into a trajectory analysis, we demonstrate the potential improvement in vesicle tracking.
|
|
TuAbPo-08 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Videoscopy Processing |
|
|
Chair: Sage, Daniel | Ecole Polytechnique Federale De Lausanne (EPFL) |
|
10:30-12:00, Paper TuAbPo-08.1 | Add to My Program |
Multi-Frame Ct-Video Registration for 3d Airway-Wall Analysis |
|
Byrnes, Patrick | Penn State Erie - the Behrend College |
Higgins, William | Penn State University |
Keywords: Endoscopy, Multi-modality fusion, Image registration
Abstract: Bronchoscopy and three-dimensional (3D) computed tomography (CT) are important complementary tools for managing lung diseases. Endobronchial video captured during bronchoscopy gives live views of the airway-tree interior with vivid detail of the airway mucosal surfaces, while the 3D CT images give considerable anatomical detail. Unfortunately, little effort has been made to link these rich data sources. This paper describes a rapid interactive multi-frame method for registering the video frames constituting a complete bronchoscopic video sequence onto their respective locations within the CT-based 3D airway tree. Registration results using both phantom and human cases show our method’s efficacy compared to ground-truth data, with a maximum position error = 8.5mm, orientation error of 17 degrees, and a minimum trajectory accuracy = 94.1%. We also apply our method to multimodal 3D airway-wall analysis within a comprehensive bronchoscopic video analysis system.
|
|
10:30-12:00, Paper TuAbPo-08.2 | Add to My Program |
Photoshopping Colonoscopy Video Frames |
|
LIu, Yuyuan | University of Adelaide |
Tian, Yu | University of Adelaide |
Maicas Suso, Gabriel | The University of Adelaide |
Pu, Leonardo | University of Adelaide |
Singh, Rajvinder | University of Adelaide |
Verjans, Johan | Australian Institute for Machine Learning |
Carneiro, Gustavo | University of Adelaide |
Keywords: Computer-aided detection and diagnosis (CAD), Endoscopy, Machine learning
Abstract: The automatic detection of frames containing polyps from a colonoscopy video sequence is an important first step for a fully automated colonoscopy analysis tool. Typically, such detection system is built using a large annotated data set of frames with and without polyps, which is expensive to be obtained. In this paper, we introduce a new system that detects frames containing polyps as anomalies from a distribution of frames from exams that do not contain any polyps. The system is trained using a one-class training set consisting of colonoscopy frames without polyps -- such training set is considerably less expensive to obtain, compared to the 2-class data set mentioned above. During inference, the system is only able to reconstruct frames without polyps, and when it tries to reconstruct a frame with polyp, it automatically removes (i.e., photoshop) it from the frame -- the difference between the input and reconstructed frames is used to detect frames with polyps. We name our proposed model as anomaly detection generative adversarial network (ADGAN), comprising a dual GAN with two generators and two discriminators. To test our framework, we use a new colonoscopy data set with 14317 images, split as a training set with 13350 images without polyps, and a testing set with 290 abnormal images containing polyps and 677 normal images without polyps. We show that our proposed approach achieves the state-of-the-art result on this data set, compared with recently proposed anomaly detection systems.
|
|
10:30-12:00, Paper TuAbPo-08.3 | Add to My Program |
A Deep Learning Approach to Video Fluoroscopic Swallowing Exam Classification |
|
Wilhelm, Patrick | University of Iowa |
Reinhardt, Joseph M. | The University of Iowa |
Van Daele, Douglas | Department of Otolaryngology, Carver College of Medicine |
Keywords: Machine learning
Abstract: Dysphagia, or difficulty swallowing, is a serious health problem that reduces the quality of life of those affected. The standard method to diagnose dysphagia is the x-ray video fluoroscopic swallowing exam (VFSE). In this paper we investigate the use of deep learning networks to classify VFSE as normal or abnormal. The proposed network is based on a long term recurrent convolutional network (LRCN). This network was trained and validated using 1154 VFSE. Using 10-fold cross-validation, the accuracy of classification was 85% and the area under the ROC curve was 0.89. This work shows the promise of using deep learning networks as a screening tool to detect dysphagia in VFSE.
|
|
10:30-12:00, Paper TuAbPo-08.4 | Add to My Program |
Recurrent Neural Networks for Compressive Video Reconstruction |
|
Lorente Mur, Antonio | INSA Lyon, CREATIS |
Peyrin, Francoise | Université De Lyon, CNRS UMR 5220, INSERM U1206, INSA Lyon |
Ducros, Nicolas | INSA Lyon, CREATIS |
Keywords: Computational Imaging, Image reconstruction - analytical & iterative methods, Machine learning
Abstract: Single-pixel imaging allows low cost cameras to be built for imaging modalities where a conventional camera would either be too expensive or too cumbersome. This is very attractive for biomedical imaging applications based on hyperspectral measurements, such as image-guided surgery, which requires the full spectrum of fluorescence. A single-pixel camera essentially measures the inner product of the scene and a set of patterns. An inverse problem has to be solved to recover the original image from the raw measurement. The challenge in single-pixel imaging is to reconstruct the video sequence in real time from under-sampled data. Previous approaches have focused on the reconstruction of each frame independently, which fails to exploit the natural temporal redundancy in a video sequence. In this study, we propose a fast deep-learning reconstructor that exploits the spatio-temporal features in a video. In particular, we consider convolutional gated recurrent units that have low memory requirements. Our simulation shows than the proposed recurrent network improves the reconstruction quality compared to static approaches that reconstruct the video frames independently.
|
|
10:30-12:00, Paper TuAbPo-08.5 | Add to My Program |
Reduce False-Positive Rate by Active Learning for Automatic Polyp Detection in Colonoscopy Videos |
|
Guo, Zhe | The University of Aizu |
Zhang, Ruiyao | The University of Aizu |
Li, Qin | The University of Aizu |
Liu, Xinkai | The University of Aizu |
Nemoto, Daiki | Aizu Medical Center, Fukushima Medical University |
Togashi, Kazutomo | Aizu Medical Center, Fukushima Medical University |
Niroshana S.M, Isuru | The University of Aizu |
Shi, Yuchen | The University of Aizu |
Zhu, Xin | The University of Aizu |
Keywords: Computer-aided detection and diagnosis (CAD), Machine learning, Gastrointestinal tract
Abstract: Automatic polyp detection is reported to have a high false-positive rate (FPR) because of various polyp-like structures and artifacts in complex colon environment. An efficient polyp’s computer-aided detection (CADe) system should have a high sensitivity and a low FPR (high specificity). Convolutional neural networks have been implemented in colonoscopy-based automatic polyp detection and achieved high performance in improving polyp detection rate. However, complex colon environments caused excessive false positives are going to prevent the clinical implementation of CADe system. To reduce false positive rate, we proposed an automatic polyp detection algorithm, combined with YOLOv3 architecture and active learning. This algorithm was trained with colonoscopy videos/ images from 283 subjects. Through testing with 100 short and 9 full colonoscopy videos, the proposed algorithm shown FPR of 2.8% and 1.5%, respectively, similar sensitivities of expert endoscopists.
|
|
10:30-12:00, Paper TuAbPo-08.6 | Add to My Program |
Screening for Barrett's Esophagus with Probe-Based Confocal Laser Endomicroscopy Videos |
|
Pulido, J. Vince | University of Virginia, |
Guleria, Shan | University of Virginia School of Medicine |
Ehsan, Lubaina | University of Virginia, School of Medicine, Department of Pediat |
Shah, Tilak | Hunter Holmes McGuire VA Medical Center |
Syed, Sana | University of Virginia, School of Medicine, Department of Pediat |
Brown, Donald | University of Virginia |
Keywords: Microscopy - Light, Confocal, Fluorescence, Gastrointestinal tract, Machine learning
Abstract: Histologic diagnosis of Barrett's esophagus and esophageal malignancy via probe-based confocal laser endomicroscopy (pCLE) allows for real-time examination of epithelial architecture and targeted biopsy sampling. Although pCLE has demonstrated high specificity, sensitivity remains low. This study employs deep learning architectures in order to improve the accuracy of pCLE in diagnosing esophageal cancer and its precursors. pCLE videos are curated and annotated as belonging to one of the three classes: squamous, Barrett's (intestinal metaplasia without dysplasia), or dysplasia. We introduce two novel video architectures, AttentionPooling and Multi-Module AttentionPooling deep networks, that outperform other models and demonstrate a high degree of explainability.
|
|
TuAbPo-09 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Abstract Posters: Medical Imaging and Analysis |
|
|
Chair: Aggarwal, Hemant Kumar | University of Iowa |
|
10:30-12:00, Paper TuAbPo-09.2 | Add to My Program |
HEALPix View-Order for 3D+time Radial Self-Navigated Motion-Corrected ZTE MRI |
|
Corum, Curtis Andrew | Champaign Imaging LLC |
Kruger, Stanley | University of Iowa |
Magnotta, Vincent Alfonso | University of Iowa |
Keywords: Magnetic resonance imaging (MRI), Brain, Image acquisition
Abstract: In MRI there has been no 3D+time radial view-order which
meets all the desired characteristics for simultaneous
dynamic/high-resolution imaging, such as for self-navigated
motion-corrected high resolution neuroimaging. In this work, we examine the use of Hierarchical Equal Area
iso-Latitude Pixelization (HEALPix) for generation of three
dimensional dynamic (3D+time) radial view-orders for MRI,
and compare to a selection of commonly used 3D view-orders. The resulting trajectories were evaluated through
simulation of the point spread function and slanted surface
object suitable for modulation transfer function, contrast
ratio, and SNR measurement. Results from the HEALPix
view-order were compared to Generalized Spiral, Golden
Means, and Random view-orders. We report the first use of the HEALPix view-order to
acquire in-vivo brain images.
|
|
10:30-12:00, Paper TuAbPo-09.3 | Add to My Program |
Phase Constrained Joint Deblurring and Water-Fat Separation for Mr Spiral Imaging |
|
Peng, Xi | Mayo Clinic |
Wang, Dinghui | University of Toronto |
Chao, Tzucheng | Mayo Clinic |
Pipe, James | Mayo Clinic |
Keywords: Magnetic resonance imaging (MRI), Deconvolution, Image enhancement/restoration(noise and artifact reduction)
Abstract: Spiral imaging has drawn increasing attention due to its
high SNR efficiency and low sensitivity to motion. One
major challenge in spiral imaging is the spatial blurring
and distortion caused by off resonance and chemical shift.
Previous joint deblurring and water-fat separation method
has shown significant improvement over sequential methods,
but could be very sensitive to phase errors introduced by
inaccurate B0 or flow artefacts. This work presents a novel
water-fat phase consistent constraint to improve the
robustness of the joint deblurring method to such potential
phase errors. In vivo experiments have been conducted to
validate the feasibility of the proposed approach.
|
|
10:30-12:00, Paper TuAbPo-09.4 | Add to My Program |
Gamma Kurtosis Model in Diffusion-Relaxometry Signal Prediction |
|
Bogusz, Fabian | AGH University of Science and Technology, Kraków |
Pieciak, Tomasz | AGH University of Science and Technology, Kraków |
Afzali, Maryam | Cardiff University Brain Research Imaging Center |
Pizzolato, Marco | École Polytechnique Fédérale De Lausanne |
Aja-Fernandez, Santiago | Universidad De Valladolid |
Jones, Derek | Cardiff University Brain Research Imaging Center |
Keywords: Magnetic resonance imaging (MRI), Diffusion weighted imaging, Brain
Abstract: Magnetic resonance imaging (MRI) is a powerful tool to study the microstructure of the tissue. Two important modalities are diffusion MRI that provides information on the microstructural level and relaxometry that extracts the sensitivity of the signal to the biochemical environment by transverse and longitudinal relaxation times. We propose a modification of the signal model extending the classical apparent diffusion coefficient (ADC) into gamma distributed diffusion with kurtosis term. The estimation of the model parameters was done via a non-linear Levenberg-Marquardt method using a various number of diffusion-weighting gradients. The results show that the kurtosis model allows for a better interpolation compared to a more conventional model based on ADC.
|
|
10:30-12:00, Paper TuAbPo-09.5 | Add to My Program |
Novel Application of Nonlinear Apodization for Medical Imaging |
|
Arndt, Jeffrey | Integrity Applications Incorporated |
Kight, Lauren | Centauri |
Calderon, Armando Medina | Centauri |
Lew, Jason | Centauri |
Keywords: Image enhancement/restoration(noise and artifact reduction), Ultrasound, Magnetic resonance imaging (MRI)
Abstract: Presented here is a nonlinear apodization (NLA) method for
processing magnetic resonance (MR) and ultrasound (US)
images, which has been modified from its original use in
processing radar imagery. This technique reduces Gibb’s
artifacts (ringing) while preserving the boundary edges and
the mainlobe width of the impulse response. This is done by
selecting, pixel-by-pixel, the specific signal-domain
windowing function (cosine-on-pedestal) that optimizes each
point throughout the image. The windows are chosen from an
infinite but bounded set, determined by weighting
coefficients for the cosine-on-pedestal equation and the
values of the pixels adjacent to the point of interest. By
using this method, total sidelobe suppression is achievable
without degrading the resolution of the mainlobe. In radar
applications, this nonlinear apodization technique has
shown to require fewer operations per pixel than other
traditional apodization techniques. The preliminary results
from applications on MR and US data are presented here.
|
|
10:30-12:00, Paper TuAbPo-09.6 | Add to My Program |
A Transmission-Less Attenuation Compensation Method for Brain Spect Imaging |
|
Yu, Zitong | Enter an Organization |
Rahman, Md Ashequr | Washington University in St. Louis |
Jha, Abhinav | Washington University in St. Louis |
Keywords: Nuclear imaging (e.g. PET, SPECT), Image reconstruction - analytical & iterative methods, Brain
Abstract: Attenuation compensation (AC) is a pre-requisite for
reliable quantification and beneficial for visual
interpretation tasks in SPECT imaging. Typical AC methods
requires the presence of an attenuation map, which is
obtained using a transmission scan, such as the CT scan.
This
has several disadvantages such as increased radiation dose,
higher costs, and possible misalignment between SPECT and
CT scans. Also, often a CT scan may be unavailable. In this
context, we and others are showing that scattered photons
in SPECT contain information to estimate the attenuation
distribution. To exploit this observation, we propose a
simple physics and learning-based
method that uses the SPECT emission data in the photopeak
and scatter windows to perform transmission-less ASC in
SPECT. The method was developed in the context of
quantitative
2-D dopamine-transporter (DaT)-scan SPECT imaging.
The proposed method uses data acquired in the scatter
window to reconstruct an initial estimate of the
attenuation
map using a physics-based approach. An auto-encoder is
then trained to segment this initial estimate into soft
tissue
and bone regions. Pre-defined attenuation coefficients are
assigned
to these regions, yielding the reconstructed attenuation
map. This is used to reconstruct the activity distribution
using
an ordered subsets expectation maximization (OSEM)-based
reconstruction approach.
We objectively evaluated the performance of this method
using highly realistic simulation studies, where the task
was
to quantify activity uptake in the caudate and putamen
regions
of the brain from the reconstructed activity images.
Normalized
root mean square error (RMSE) between the true and
estimated activity values were computed. We compared the
performance of the proposed method to reconstructed images
obtained using the true attenuation map, and to those
obtained
using the traditional Chang’s attenuation compensation
approach.
Our results showed no statistically significant differences
between the activity estimates obtained using the proposed
method and that with true attenuation map. Additionally,
the proposed method significantly outperformed the
Chang’s AC method. Overall, these results demonstrate
excellent potential of the proposed method to perform
transmission-less ASC and
motivate further evaluation to other SPECT applications and
using clinical data.
|
|
10:30-12:00, Paper TuAbPo-09.7 | Add to My Program |
State Estimation in Dynamic Radial Golden Angle MRI |
|
Wettenhovi, Ville-Veikko | University of Eastern Finland |
Kolehmainen, Ville | University of Kuopio |
Kettunen, Mikko | University of Eastern Finland |
Grohn, Olli | University of Eastern Finland |
Vauhkonen, Marko | University of Kuopio Kuopio |
Keywords: Magnetic resonance imaging (MRI), Image reconstruction - analytical & iterative methods, Inverse methods
Abstract: We present a state estimation formulation for time-varying
magnetic resonance imaging (MRI) utilizing data-driven a
priori information. In state estimation, we utilize
separate state evolution and observation models to model
the time dependent image reconstruction problem. In this
paper we compute the state estimates by using the Kalman
filter (KF) and steady state Kalman smoother (KS). KF
includes separate matrix for the process noise covariance
that gives a priori information to the filter regarding the
strength of the changes and the location in the image
domain where the changes are expected to happen. In this
work, we utilize a data-driven approach to compute this
process noise covariance matrix, allowing for more accurate
estimates in regions of activity and less noise in inactive
regions. We construct this data-driven covariance matrix
from the conventional sliding window (SW) estimates. We evaluate the method by using golden angle sampled radial
MRI, with both simulated and experimentally measured data.
The simulated data corresponds to a functional MRI (fMRI)
examination while the measured data is dynamic
contrast-enhanced MRI measurement from a rat brain. In the
KF estimates, only a single radial spoke of data was used
to update the estimate at each time step. As such, a new
estimate was formed after each new spoke, leading to faster
frame rates when compared to the conventional sliding
window. The results show that the state estimation approach
with the data-driven process noise covariance can improve
both spatial and temporal resolution.
|
|
10:30-12:00, Paper TuAbPo-09.8 | Add to My Program |
Double-View Global 2D-3D Registration on Cerebral Angiograms |
|
Jin, Pan | The Chinese University of Hong Kong |
Min, Zhe | Chinese University of Hong Kong |
Meng, Max Q.-H. | The Chinese University of Hong Kong |
Keywords: Surgical guidance/navigation, X-ray imaging
Abstract: In minimally invasive surgery, the clinician relies on image guidance to diagnose, plan and navigate. In order to update the live information during surgery, 2D X-ray images and pre-operatively acquired 3D CT images need to be registered. In this work, we propose a novel global double-view registration method based on the Branch and Bound algorithm to register them.
|
|
10:30-12:00, Paper TuAbPo-09.9 | Add to My Program |
Automated Instance Segmentation and Keypoint Detection for Spine Imaging Analysis |
|
Suri, Abhinav | University of Pennsylvania School of Medicine |
Beyrer, Patrick | University of Pennsylvania |
Jankelovits, Amanda | University of Pennsylvania |
Golden, Jacqueline | University of Pennsylvania School of Medicine |
Baoer, Li | University of Pennsylvania |
Rajapakse, Chamith | University of Pennsylvania |
Keywords: Machine learning, Spine, Magnetic resonance imaging (MRI)
Abstract: 1.INTRODUCTION
Individuals diagnosed with degenerative bone diseases such
as osteoporosis are more susceptible to vertebral fractures
which comprise almost 50% of all osteoporotic fractures in
the United States per year. Thoracolumbar vertebral body
fractures can be classified as wedge, biconcave, or crush,
depending on the anterior (Ha), middle (Hm), and posterior
(Hp) heights of each vertebral body. However, determining
these height measurements in clinical workflow is
time-consuming and resource intensive. Instance
segmentation and keypoint detection network designs offer
the ability to determine Ha, Hm, and Hp, in order to
classify deformities according to the semi- or fully
quantitative method. We investigated the accuracy of such
algorithms for analyzing sagittal spine CT and MR images. 2.MATERIALS AND METHODS
Sagittal spine MRI (998) and CT scans (35) were split into
training and testing data. The training set was augmented
(±15°rotation, ±30% contrast and brightness, random
cropping) to a final size of 5667 vertebrae (1269 CT & 4398
MR). A testing set of 238 MR and 15 CT scans was used to
evaluate the neural network. Mask RCNN (architecture for
basic instance segmentation) was modified to include a 2D-
UNet head (for better segmentation) along with a Keypoint
RCNN network to detect 6 relevant vertebral keypoints
(network design in Figure 1 w/one network per imaging
modality). The effectiveness of the neural network was
measured using two parameters: Dice score (ranges from 0 to
1 where 1=predicted overlay is manually segmented ground
truth) and keypoint error distance (distance of predicted
key-point location compared to manually labeled reference
point). 3.RESULTS
The neural network achieved an overall Dice coefficient of
0.968 and key-point error distance of 0.984 millimeters on
the testing dataset. Mean percent error in Ha, Hm, and Hp
height calculations (based on keypoints) was 0.13%.The
neural network was able to process each scan slice with a
mean time of 1.492 seconds. 4.CONCLUSIONS
The neural network was able to determine morphometric
measurements for detecting spinal fractures with high
accuracy on sagittal MR and CT images. This approach could
simplify the screening, detection of changes, and surgical
planning in patients with vertebral deformities and
fractures by reducing the burden on radiologists who have
to do measurements manually.
|
|
10:30-12:00, Paper TuAbPo-09.10 | Add to My Program |
Automatic Segmentation of Enlarged Perivascular Spaces Using T-Test Loss in Mr Images |
|
Yang, Ehwa | Samsung Medical Center / Sungkyunkwan University School of Medic |
Moon, Won-Jin | Konkuk University |
Kim, Jae-Hun | Samsung Medical Center |
Keywords: Machine learning, Brain, Magnetic resonance imaging (MRI)
Abstract: In this study, we used T-test loss for segmenting enlarged
perivascular spaces (EPVS) area in the brain MRI. The
segmentation model of EPVS is learned with T-test loss and
combination of T1-weighted, T2-weighted, and the FLAIR
brain MR image is used as input to effectively distinguish
the EPVS. Our results showed that the cascaded U-Net with
T-test loss (0.7002) showed the higher score than that with
dice loss (0.6811) for segmentation of EVPS in the brain
MRI.
|
|
10:30-12:00, Paper TuAbPo-09.11 | Add to My Program |
An Estimation-Based Method for 3D Segmentation of DaT-Scan SPECT Images |
|
Sol Moon, Hae | Washington University in St. Louis |
Liu, Ziping | Washington University in St. Louis |
Ponisio, Maria | Washington University in St. Louis |
Laforest, Richard | Washington University in St. Louis |
Jha, Abhinav | Washington University in St. Louis |
|
|
10:30-12:00, Paper TuAbPo-09.12 | Add to My Program |
Journal Paper: Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks |
|
Dar, Salman Ul Hassan | Bilkent University |
Yurt, Mahmut | Bilkent University |
Karacan, Levent | Hacettepe University |
Erdem, Aykut | Hacettepe University |
Erdem, Erkut | Hacettepe University |
Cukur, Tolga | Bilkent University |
Keywords: Magnetic resonance imaging (MRI), Brain, Image synthesis
Abstract: Image synthesis in multi-contrast MRI can be achieved via an intensity transformation between source and target contrasts. Data-driven methods typically learn this transformation via L2 or L1 loss terms, reducing sensitivity to high spatial frequencies. To address this limitation, we proposed a novel approach based on conditional generative adversarial networks that synergistically combines adversarial, pixel-wise and perceptual losses.
|
|
TuAbPo-10 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Abstract Posters: Microscopy and OCT |
|
|
Chair: Park, Hyoungjun | Korea Advanced Institute of Science and Technology |
|
10:30-12:00, Paper TuAbPo-10.1 | Add to My Program |
Cell Detection from Brain Histology Using Artificial Neural Network |
|
Mladinov, Mihovil | University of California San Francisco |
Grinberg, Lea T. | University of California San Francisco |
Miramontes-Lizarraga, Silvia | University of California Berkeley |
Ushizima, Daniela | Lawrence Berkeley National Laboratory |
|
|
10:30-12:00, Paper TuAbPo-10.2 | Add to My Program |
Detection of Micro-Fractures in Intravascular Optical Coherence Tomography (ivoct) Images after Treating Coronary Arteries with Shockwave Intravascular Lithotripsy (ivl) |
|
Gharaibeh, Yazan | Case Western Reserve University |
Dong, Pengfei | University of Nebraska Lincoln |
Lee, Juhwan | Case Western Reserve University |
Zimin, Vladislav | University Hospitals Cleveland Medical Center |
Dallan, Luis Augusto | University Hospitals Cleveland Medical Center - Case Western Res |
Illindala, Uday | Shockwave Medical Inc |
Bezerra, Hiram | University Hospitals |
Gu, Linxia | Florida Institute of Technology |
Wilson, David | Case Western Reserve University |
Keywords: Optical coherence tomography, Heart, Modeling - Anatomical, physiological and pathological
Abstract: Intravascular lithotripsy (IVL) is a plaque modification
technique that delivers pressure waves to pre-treat heavily
calcified vascular calcifications to aid successful stent
deployment. IVL causes micro-fractures that can develop
into macro-fractures which enable successful vessel
expansion. Intravascular optical coherence tomography
(IVOCT) has the penetration, resolution, and contrast to
characterize coronary calcifications. We detected the
presence of micro-fractures by comparing textures before
and after IVL treatment (p = 0.0039). In addition, we used
finite element model (FEM) to success-fully predict the
location of macro-fracture. Results suggest that we can use
our methods to understand and possibly clinically monitor
IVL treatment.
|
|
10:30-12:00, Paper TuAbPo-10.3 | Add to My Program |
Deep Learning in Image Classification: Disentangling Biological Signal from Experimental Noise in Cellular Microscopy Data Using Control Delta Matrix |
|
Bae, Hye Ryeong | Stanford University |
Kim, Jonathan | Stanford University |
Kwon, Yong Nam | Stanford University |
Keywords: Microscopy - Light, Confocal, Fluorescence, Machine learning, Classification
Abstract: This study focuses on using deep image recognition to
improve classification of microscopy images of cells. One
of the main challenges of applying deep learning to
microscopy data is that it is difficult to distinguish
biological variations from technical noise. This is
especially problematic in cellular imaging, where
environmental and experimental conditions cause batch
effects that are often more visually salient than the
phenotypic variations of interest. We examine the Recursion
Cellular Image Classification (CellSignal) Kaggle Challenge
(Jul.-Sep., 2019). The evaluation metric of the challenge
is the classification accuracy of small interfering RNA
(siRNA), which corresponds to the classification accuracy
of genetic perturbations. We introduce the concept of a
“Control Delta Matrix,” which uses negative control images
(images of cells with no siRNA exposure) to normalize input
images. The input and control images are put through a deep
convolutional pipeline to produce latent embeddings. Then,
the embedding of the control is subtracted from that of the
input to obtain the control delta matrix. Based on the
intuition that the embedding of a negative control image is
a representation of the batch’s inherent characteristics
without siRNA influence, we hypothesize that its removal
from the input image’s representation would isolate the
siRNA’s effect and enable easier classification. Our
preliminary results using the Control Delta Matrix in a
DenseNet based model show steady improvement in both
training accuracy (defined as siRNA classification
accuracy) and training loss (defined as a weighted average
of ArcFace and Softmax cross-entropy losses).
|
|
10:30-12:00, Paper TuAbPo-10.5 | Add to My Program |
Advanced Computational Methods Play Pivotal Role to Answer Fundamental Biological Questions |
|
Hossain, M. Julius | European Molecular Biology Laboratory |
Ellenberg, Jan | European Molecular Biology Laboratory |
Keywords: Microscopy - Light, Confocal, Fluorescence, Image segmentation, Image registration
Abstract: The European Molecular Biology Laboratory (EMBL) is one of the world’s leading research institutions for the life sciences conducting multidisciplinary research to continuously advance our understanding of the fundamental mechanisms of life. The Ellenberg Group at EMBL performs state-of-the-art microscopy across scales and produces huge volume of data from different imaging modalities capturing various events inside living organisms, cells or organelles. Automated analysis of this data is important to quantify these events and connect the results from different experiments to understand how cells and their molecular machines are constructed and dynamically work together to carry out the essential functions of life. Automated analysis involves substantial development of sophisticated computational frameworks in order to deal with complexity and heterogeneity of image data and detect interesting events. It also enables scientists to observe the structures and dynamics of different sub-cellular components which are not possible to do experimentally. This presentation will address different fundamental biological questions to demonstrate that computational pipelines play key role to study them successfully. It will also demonstrate why image analysis frameworks are so important and how they make significant impact in achieving overall research goals in a multi-disciplinary research environment.
|
|
TuPaO1 Oral Session, Oakdale I-II |
Add to My Program |
Brain Connectivity |
|
|
Chair: Riklin Raviv, Tammy | Ben-Gurion University |
|
14:30-14:45, Paper TuPaO1.1 | Add to My Program |
Prediction of Language Impairments in Children Using Deep Relational Reasoning with DWI Data |
|
Banerjee, Soumyanil | Wayne State University |
Dong, Ming | Wayne State University |
Lee, Min-Hee | Wayne State University School of Medicine |
O'Hara, Nolan | Wayne State University |
Asano, Eishi | Departments of Pediatrics and Neurology, Wayne State University |
Jeong, Jeong-Won | Wayne State University School of Medicine |
Keywords: Machine learning, Diffusion weighted imaging, Brain
Abstract: This paper proposes a new deep learning model using relational reasoning with diffusion-weighted imaging (DWI) data. We investigate how effectively and comprehensively DWI tractography-based connectome predicts the impairment of expressive and receptive language ability in individual children with focal epilepsy (FE). The proposed model constitutes a combination of a dilated convolutional neural network (CNN) and a relation network (RN), with the latter being applied to the dependencies of axonal connections across cortical regions in the whole brain. The presented results from 51 FE children demonstrate that the proposed model outperforms other existing state-of-the-art algorithms to predict language abilities without depending on connectome densities, with average improvement of up to 96.2% and 83.8% in expressive and receptive language prediction, respectively.
|
|
14:45-15:00, Paper TuPaO1.2 | Add to My Program |
Enriching Statistical Inferences on Brain Connectivity for Alzheimer's Disease Analysis Via Latent Space Graph Embedding |
|
Ma, Xin | The University of Texas at Arlington |
Wu, Guorong | University of North Carolina at Chapel Hill |
Kim, Won Hwa | University of Texas at Arlington |
Keywords: Probabilistic and statistical models & methods, Brain, Connectivity analysis
Abstract: We develop a graph node embedding Deep Neural Network that leverage on statistical outcome measure and graph structure given in the data. The objective is to identify regions of interests (ROIs) in the brain that are affected by topological changes of brain connectivity due to specific neurodegenerative diseases by enriching statistical group analysis. We tackle this problem by learning a latent space where statistical inference can be made more effectively. Our experiments on a large-scale Alzheimer's Disease dataset show promising result identifying ROIs that show statistically significant group differences separating even early and late Mild Cognitive Impairment (MCI) groups whose effect sizes are very subtle.
|
|
15:00-15:15, Paper TuPaO1.3 | Add to My Program |
Mapping Cerebral Connectivity Changes after Mild Traumatic Brain Injury in Older Adults Using Diffusion Tensor Imaging and Riemannian Matching of Elastic Curves |
|
Irimia, Andrei | University of Southern California |
Fan, Di | University of Southern California |
Chaudhari, Nikhil | University of Southern California |
Ngo, Van | University of Southern California |
Zhang, Fan | Harvard Medical School |
Joshi, Shantanu | Ahmanson-Lovelace Brain Mapping Center, Department of Neurology, |
O'Donnell, Lauren | BWH |
Keywords: Brain, Diffusion weighted imaging, Connectivity analysis
Abstract: Although diffusion tensor imaging (DTI) can identify white matter (WM) changes due to mild traumatic brain injury (mTBI), the task of within-subject longitudinal matching of DTI streamlines remains challenging in this condition. Here we combine (A) automatic, atlas-informed labeling of WM streamline clusters with (B) streamline prototyping and (C) Riemannian matching of elastic curves to quantify within-subject changes in WM structure properties, focusing on the arcuate fasciculus. The approach is demonstrated in a group of geriatric mTBI patients imaged acutely and ~6 months post-injury. Results highlight the utility of differen-tial geometry approaches when quantifying brain connectivity alterations due to mTBI.
|
|
15:15-15:30, Paper TuPaO1.4 | Add to My Program |
Analysis of Consistency in Structural and Functional Connectivity of Human Brain |
|
Osmanlioglu, Yusuf | University of Pennsylvania |
Antony Alappatt, Jacob | University of Pennsylvania |
Parker, Drew | University of Pennsylvania |
Verma, Ragini | University of Pennsylvania |
Keywords: Connectivity analysis, Diffusion weighted imaging, Functional imaging (e.g. fMRI)
Abstract: Analysis of structural and functional connectivity of brain has become a fundamental approach in neuroscientific research. Despite several studies reporting consistent similarities as well as differences for structural and resting state (rs) functional connectomes, a comparative investigation of connectomic consistency between the two modalities is still lacking. Nonetheless, connectomic analysis comprising both connectivity types necessitate extra attention as consistency of connectivity differs across modalities, possibly affecting the interpretation of the results. In this study, we present a comprehensive analysis of consistency in structural and rs-functional connectomes obtained from longitudinal diffusion MRI and rs-fMRI data of a single healthy subject. We contrast consistency of deterministic and probabilistic tracking with that of full, positive, and negative functional connectivities across various connectome generation schemes, using correlation as a measure of consistency.
|
|
15:30-15:45, Paper TuPaO1.5 | Add to My Program |
Functional Multi-Connectivity: A Novel Approach to Assess Multi-Way Entanglement between Networks and Voxels |
|
Iraji, Armin | Georgia State University |
Lewis, Noah | MIND Institute |
Faghiri, Ashkan | University of New Mexico |
Fu, Zening | University of Hongkong |
DeRamus, Thomas | Tri-Institutional Center for Translational Research in Neuroimag |
Abrol, Anees | Georgia State University, the Mind Research Network |
Qi, Shile | Brainnetome Center & National Laboratory of Pattern Recognition, |
Calhoun, Vince | The Mind Research Network/University of New Mexico |
Keywords: Connectivity analysis, fMRI analysis
Abstract: The interactions among brain entities, commonly computed through pair-wise functional connectivity, are assumed to be manifestations of information processing which drive function. However, this focus on large-scale networks and their pair-wise temporal interactions is likely missing important information contained within fMRI data. We propose leveraging multi-connected features at both the voxel- and network-level to capture “multi-way entanglement” between networks and voxels, providing improved resolution of interconnected brain functional hierarchy. Entanglement refers to each brain network being heavily enmeshed with the activity of other networks. Under our multi-connectivity assumption, elements of a system simultaneously communicate and interact with each other through multiple pathways. As such we move beyond the typical pair-wise temporal partial or full correlation. We propose a framework to estimate functional multi-connectivity (FMC) by computing the relationship between system-wide connections of intrinsic connectivity networks (ICNs). Results show that FMC obtains information which is different from standard pair-wise analyses.
|
|
15:45-16:00, Paper TuPaO1.6 | Add to My Program |
Agglomerative Region-Based Analysis |
|
Higger, Matt | Harvard Medical School |
Wassermann, Demian | Inria |
Shenton, Martha | Brigham and Women's Hosptial, Harvard Medical School |
Bouix, Sylvain | Psychiatry Neuroimaging Laboratory |
Keywords: Image segmentation, Machine learning, Diffusion weighted imaging
Abstract: A fundamental problem in brain imaging is the identification of volumes whose features distinguish two populations. One popular solution, Voxel-Based Analyses (VBA), glues together contiguous voxels with significant intra-voxel population differences. VBA's output regions may not be spatially consistent: each voxel may show a unique population effect. We introduce Agglomerative Region-Based Analysis (ARBA), which mitigates this issue to increase sensitivity. ARBA is an Agglomerative Clustering procedure, like Ward's method, which segments image sets in a common space to greedily maximize a likelihood function. The resulting regions are pared down to a set of disjoint regions that show statistically significant population differences via Permutation Testing. ARBA is shown to increase sensitivity over VBA in a detection task on multivariate Diffusion MRI brain images.
|
|
TuPaO2 Oral Session, Oakdale III |
Add to My Program |
Machine Learning and Pattern Recognition Methods |
|
|
Chair: Moradi, Mehdi | IBM Research |
Co-Chair: Duan, Qi | NIH |
|
14:30-14:45, Paper TuPaO2.1 | Add to My Program |
Class-Center Involved Triplet Loss for Skin Disease Classification on Imbalanced Data |
|
Lei, Weixian | Sun Yat-Sen University |
Zhang, Rong | Sun Yat-Sen University |
Yang, Yang | Sun Yat-Sen University |
Wang, Ruixuan | Sun Yat-Sen University |
Zheng, Wei-Shi | School of Data and Computer Science, Sun Yat-Sen University |
Keywords: Skin, Classification
Abstract: It is ideal to develop intelligent systems to accurately di- agnose diseases as human specialists. However, due to the highly imbalanced data problem between common and rare diseases, it is still an open problem for the systems to ef- fectively learn to recognize both common and rare diseases. We propose utilizing triplet modelling to overcome the data imbalance issue for the rare diseases. Moreover, we further develop a class-center based triplet loss in order to make the triplet-based learning more stable. Extensive evaluation on two skin image classification tasks shows that the triplet- based approach is very effective and outperforms the widely used methods for solving the imbalance problem, including oversampling, class weighting, and using focal loss.
|
|
14:45-15:00, Paper TuPaO2.2 | Add to My Program |
Discovering Salient Anatomical Landmarks by Predicting Human Gaze |
|
Droste, Richard | University of Oxford |
Chatelain, Pierre | University of Oxford |
Drukker, Lior | Nuffield Department of Women’s and Reproductive Health, Universi |
Sharma, Harshita | University of Oxford |
Papageorghiou, Aris | Nuffield Department of Obstetrics and Gynaecology, John Ra |
Noble, J Alison | University of Oxford |
Keywords: Machine learning, Pattern recognition and classification, Ultrasound
Abstract: Anatomical landmarks are a crucial prerequisite for many medical imaging tasks. Usually, the set of landmarks for a given task is predefined by experts. The landmark locations for a given image are then annotated manually or via machine learning methods trained on manual annotations. In this paper, in contrast, we present a method to automatically discover and localize anatomical landmarks in medical images. Specifically, we consider landmarks that attract the visual attention of humans, which we term visually salient landmarks. We illustrate the method for fetal neurosonographic images. First, full-length clinical fetal ultrasound scans are recorded with live sonographer gaze-tracking. Next, a convolutional neural network (CNN) is trained to predict the gaze point distribution (saliency map) of the sonographers on scan video frames. The CNN is then used to predict saliency maps of unseen fetal neurosonographic images, and the landmarks are extracted as the local maxima of these saliency maps. Finally, the landmarks are matched across images by clustering the landmark CNN features. We show that the discovered landmarks can be used within affine image registration, with average landmark alignment errors between 4.1% and 10.9% of the fetal head long axis length.
|
|
15:00-15:15, Paper TuPaO2.3 | Add to My Program |
Earthmover-Based Manifold Learning for Analyzing Molecular Conformation Spaces |
|
Zelesko, Nathan | Brown University |
Moscovich, Amit | Princeton University |
Kileel, Joe | Princeton University |
Singer, Amit | Princeton University |
Keywords: Dimensionality reduction, Shape analysis, Machine learning
Abstract: In this paper, we propose a novel approach for manifold learning that combines the Earthmover's distance (EMD) with the diffusion maps method for dimensionality reduction. We demonstrate the potential benefits of this approach for learning shape spaces of proteins and other flexible macromolecules using a simulated dataset of 3-D density maps that mimic the non-uniform rotary motion of ATP synthase. Our results show that EMD-based diffusion maps require far fewer samples to recover the intrinsic geometry than the standard diffusion maps algorithm that is based on the Euclidean distance. To reduce the computational burden of calculating the EMD for all volume pairs, we employ a wavelet-based approximation to the EMD which reduces the computation of the pairwise EMDs to a computation of pairwise weighted-l1 distances between wavelet coefficient vectors.
|
|
15:15-15:30, Paper TuPaO2.4 | Add to My Program |
Semi-Supervised Cervical Dysplasia Classification with Learnable Graph Convolutional Network |
|
Ou, Yanglan | Penn State University |
Xue, Yuan | Penn State University |
Yuan, Ye | Carnegie Mellon University |
Xu, Tao | Lehigh University |
Pisztora, Vincent | Pennsylvania State University |
Li, Jia | The Pennsylvania State University |
Huang, Xiaolei | The Pennsylvania State University |
Keywords: Pattern recognition and classification, Cervix, Graphical models & methods
Abstract: Cervical cancer is the second most prevalent cancer affecting women today. As the early detection of cervical carcinoma relies heavily upon screening and pre-clinical testing, digital cervicography has great potential as a primary or auxiliary screening tool, especially in low-resource regions due to its low cost and easy access. Although an automated cervical dysplasia detection system has been desirable, traditional fully-supervised training of such systems requires large amounts of annotated data which are often labor-intensive to collect. To alleviate the need for much manual annotation, we propose a novel graph convolutional network (GCN) based semi-supervised classification model that can be trained with fewer annotations. In existing GCNs, graphs are constructed with fixed features and can not be updated during the learning process. This limits their ability to exploit new features learned during graph convolution. In this paper, we propose a novel and more flexible GCN model with a feature encoder that adaptively updates the adjacency matrix during learning and demonstrate that this model design leads to improved performance. Our experimental results on a cervical dysplasia classification dataset show that the proposed framework outperforms previous methods under a semi-supervised setting, especially when the labeled samples are scarce.
|
|
15:30-15:45, Paper TuPaO2.5 | Add to My Program |
Separation of Metabolite and Macromolecule Signals for 1H-MRSI Using Learned Nonlinear Models |
|
Li, Yahang | University of Illinois Urbana-Champaign |
Wang, Zepeng | University of Illinois at Urbana-Champaign |
Lam, Fan | University of Illinois at Urbana Champaign |
Keywords: Magnetic resonance spectroscopy, Machine learning, Inverse methods
Abstract: This paper presents a novel method to reconstruct and separate metabolite and macromolecule (MM) signals in 1H magnetic resonance spectroscopic imaging (MRSI) data using learned nonlinear models. Specifically, deep autoencoder (DAE) networks were constructed and trained to learn the nonlinear low-dimensional manifolds, where the metabolite and MM signals reside individually. A regularized reconstruction formulation is proposed to integrate the learned models with signal encoding model to reconstruct and separate the metabolite and MM components. An efficient algorithm was developed to solve the associated optimization problem. The performance of the proposed method has been evaluated using simulation and experimental 1H-MRSI data. Efficient low-dimensional signal representation of the learned models and improved metabolite/MM separation over the standard parametric fitting based approach have been demonstrated.
|
|
15:45-16:00, Paper TuPaO2.6 | Add to My Program |
The Ladder Algorithm: Finding Repetitive Structures in Medical Images by Induction |
|
Windsor, Rhydian | University of Oxford |
Jamaludin, Amir | Unversity of Oxford |
Keywords: Machine learning, Spine
Abstract: In this paper we introduce the Ladder Algorithm; a novel recurrent algorithm to detect repetitive structures in natural images with high accuracy using little training data. We then demonstrate the algorithm on the task of extracting vertebrae from whole spine magnetic resonance scans with only lumbar MR scans for training data. It is shown to achieve high performance with 99.8% precision and recall, exceeding current state of the art approaches for lumbar vertebrae detection in T1 and T2 weighted scans. It also generalises to whole spine images with minimal drop in accuracy, achieving a detection rate of 99.4%.
|
|
TuPaO3 Oral Session, Oakdale IV-V |
Add to My Program |
Heart Imaging and Segmentation |
|
|
Chair: Ledesma-Carbayo, Maria J. | Universidad Politécnica De Madrid |
Co-Chair: Metaxas, Dimitris | Rutgers University |
|
14:30-14:45, Paper TuPaO3.1 | Add to My Program |
A Semi-Supervised Joint Learning Approach to Left Ventricular Segmentation and Motion Tracking in Echocardiography |
|
Ta, Kevinminh | Yale University |
Ahn, Shawn | Yale University |
Lu, Allen | Yale University |
Stendahl, John | Yale University |
Sinusas, Albert | Yale University |
Duncan, James | Yale University |
Keywords: Machine learning, Ultrasound, Heart
Abstract: Accurate interpretation and analysis of echocardiography is important in assessing cardiovascular health. However, motion tracking often relies on accurate segmentation of the myocardium, which can be difficult to obtain due to inherent ultrasound properties. In order to address this limitation, we propose a semi-supervised joint learning network that exploits overlapping features in motion tracking and segmentation. The network simultaneously trains two branches: one for motion tracking and one for segmentation. Each branch learns to extract features relevant to their respective tasks and shares them with the other. Learned motion estimations propagate a manually segmented mask through time, which is used to guide future segmentation predictions. Physiological constraints are introduced to enforce realistic cardiac behavior. Experimental results on synthetic and in vivo canine 2D+t echocardiographic sequences outperform some competing methods in both tasks.
|
|
14:45-15:00, Paper TuPaO3.2 | Add to My Program |
Efficient Aortic Valve Multilabel Segmentation Using a Spatial Transformer Network |
|
Pak, Daniel Hyungseok | Yale University |
Caballero, Andres | Georgia Institute of Technology |
Sun, Wei | Georgia Institute of Technology |
Duncan, James | Yale University |
Keywords: Image segmentation, Machine learning, Heart
Abstract: Automated segmentation of aortic valve components using pre-operative CT scans would help provide quantitative metrics for better treatment planning of valve replacement procedures and create inputs for simulations such as finite element analysis. U-net has been used extensively for segmentation in medical imaging, but naive application of this model onto large 3D images leads to memory issues and drop in accuracy. Hence, we propose an architecture sequentially combining it with a Spatial Transformer Network (STN), which effectively transforms the original image to a consistent subregion containing the aortic valve. The addition of STN improves segmentation performance while significantly decreasing training time. Training is performed end-to-end, with no additional supervision for the STN. This framework may be useful in other medical imaging applications where the entity of interest is sparse, has a fixed number of instances, and exhibits shape regularity.
|
|
15:00-15:15, Paper TuPaO3.3 | Add to My Program |
Coronary Wall Segmentation in CCTA Scans Via a Hybrid Net with Contours Regularization |
|
Huang, Kaikai | The University of Tokyo |
Tejero-de-Pablos, Antonio | The University of Tokyo |
Yamane, Hiroaki | The University of Tokyo |
Kurose, Yusuke | The University of Tokyo |
Iho, Junichi | Sakurabashi Watanabe Hospital |
Tokunaga, Youji | Sakurabashi Watanabe Hospital |
Horie, Makoto | Sakurabashi Watanabe Hospital |
Nishizawa, Keisuke | Sakurabashi Watanabe Hospital |
Hayashi, Yusaku | Sakurabashi Watanabe Hospital |
Koyama, Yasushi | Sakurabashi Watanabe Hospital |
Harada, Tatsuya | The University of Tokyo |
Keywords: Image segmentation, Heart, Computed tomography (CT)
Abstract: Providing closed and well-connected boundaries of coronary artery is essential to assist cardiologists in the diagnosis of coronary artery disease (CAD). Recently, several deep learning-based methods have been proposed for boundary detection and segmentation in a medical image. However, when applied to coronary wall detection, they tend to produce disconnected and inaccurate boundaries. In this paper, we propose a novel boundary detection method for coronary arteries that focuses on the continuity and connectivity of the boundaries. In order to model the spatial continuity of consecutive images, our hybrid architecture takes a volume (i.e., a segment of the coronary artery) as input and detects the boundary of the target slice (i.e., the central slice of the segment). Then, to ensure closed boundaries, we propose a contour-constrained weighted Hausdorff distance loss. We evaluate our method on a dataset of 34 patients of coronary CT angiography scans with curved planar reconstruction (CCTA-CPR) of the arteries (i.e., cross-sections). Experiment results show that our method can produce smooth closed boundaries outperforming the state-of-the-art accuracy.
|
|
15:15-15:30, Paper TuPaO3.4 | Add to My Program |
Free-Breathing Cardiovascular MRI Using a Plug-And-Play Method with Learned Denoiser |
|
Liu, Sizhuo | The Ohio State University |
Reehorst, Edward | Ohio State University |
Schniter, Philip | The Ohio State University |
Ahmad, Rizwan | Ohio State University |
Keywords: Magnetic resonance imaging (MRI), Image reconstruction - analytical & iterative methods, Machine learning
Abstract: Cardiac magnetic resonance imaging (CMR) is a noninvasive imaging modality that provides a comprehensive evaluation of the cardiovascular system. The clinical utility of CMR is hampered by long acquisition times, however. In this work, we propose and validate a plug-and-play (PnP) method for CMR reconstruction from undersampled multi-coil data. To fully exploit the rich image structure inherent in CMR, we pair the PnP framework with a deep learning (DL)-based denoiser that is trained using spatiotemporal patches from high-quality, breath-held cardiac cine images. The resulting "PnP-DL" method iterates over data consistency and denoising subroutines. We compare the reconstruction performance of PnP-DL to that of compressed sensing (CS) using eight breath-held and ten real-time (RT) free-breathing cardiac cine datasets. We find that, for breath-held datasets, PnP-DL offers more than one dB advantage over commonly used CS methods. For RT free-breathing datasets, where ground truth is not available, PnP-DL receives higher scores in qualitative evaluation. The results highlight the potential of PnP-DL to accelerate RT CMR.
|
|
15:30-15:45, Paper TuPaO3.5 | Add to My Program |
Soft-Label Guided Semi-Supervised Learning for Bi-Ventricle Segmentation in Cardiac Cine Mri |
|
Chang, Qi | Rutgers University |
Yan, Zhennan | Rutgers, the State University of New Jersey |
Lou, Yixuan | Rutgers University |
Axel, Leon | NYU Medical Center |
Metaxas, Dimitris | Rutgers University |
Keywords: Image segmentation, Machine learning, Magnetic resonance imaging (MRI)
Abstract: Deep convolutional neural networks have been applied to medical image segmentation tasks successfully in recent years by taking advantage of a large amount of training data with golden standard annotations. However, it is difficult and expensive to obtain good-quality annotations in practice. This work aims to propose a novel semi-supervised learning framework to improve the ventricle segmentation from 2D cine MR images. Our method is efficient and effective by computing soft labels dynamically for the unlabeled data. Specifically, we obtain the soft labels, rather than hard labels, from a teacher model in every learning iteration. The uncertainty of the target label of unlabeled data is intrinsically encoded in the soft label. The soft label can be improved towards the ideal target in training. We use a separate loss to regularize the unlabeled data to produce similar probability distribution as the soft labels in each iteration. Experiments show that our method outperforms a state-of-the-art semi-supervised method.
|
|
15:45-16:00, Paper TuPaO3.6 | Add to My Program |
Automated Left Atrial Segmentation from Magnetic Resonance Image Sequences Using Deep Convolutional Neural Network with Autoencoder |
|
Ghosh, Shrimanti | University of Alberta, Canada |
Ray, Nilanjan | University of Alberta |
Boulanger, Pierre | University of Alberta |
Punithakumar, Kumaradevan | University of Alberta |
Noga, Michelle | University of Alberta |
Keywords: Magnetic resonance imaging (MRI), Image segmentation, Machine learning
Abstract: This study presents a novel automated algorithm to segment the left atrium (LA) from 2, 3 and 4-chamber long-axis cardiac cine magnetic resonance image (MRI) sequences using deep convolutional neural network (CNN). The objective of the segmentation process is to delineate the boundary between myocardium and endocardium and exclude the mitral valve so that the results could be used for generating clinical measurements such as strain and strain rate. As such, the segmentation needs to be performed using open contours, a more challenging problem than the pixel-wise semantic segmentation performed by existing machine learning-based approaches such as U-net. The proposed neural net is built based on pre-trained CNN Inception V4 architecture, and it predicts a compressed vector by applying a multi-layer autoencoder, which is then back-projected into the segmentation contour of the LA to perform the delineation using open contours. Quantitative evaluations were performed to compare the performances of the proposed method and the current state-of-the-art U-net method. Both methods were trained using 6195 images acquired from 80 patients and evaluated using 1515 images acquired from 20 patients where the datasets were obtained retrospectively, and ground truth manual segmentation was provided by an expert radiologist. The proposed method yielded an average Dice score of 93.1 % and Hausdorff distance of 4.2 mm, whereas the U-net yielded 91.6 % and 11.9 mm for Dice score and Hausdorff distance metrics, respectively. The quantitative evaluations demonstrated that the proposed method performed significantly better than U-net in terms of Hausdorff distance in addition to providing open contour-based segmentation for the LA.
|
|
TuPbPo Poster Session, Oakdale Foyer Coral Foyer |
|
Tuesday Poster PM |
|
|
|
16:00-17:30, Subsession TuPbPo-01, Oakdale Foyer Coral Foyer | |
Image Synthesis Poster Session, 11 papers |
|
16:00-17:30, Subsession TuPbPo-02, Oakdale Foyer Coral Foyer | |
Ultrasound Imaging and Analysis II Poster Session, 9 papers |
|
16:00-17:30, Subsession TuPbPo-03, Oakdale Foyer Coral Foyer | |
Lung, Chest, and Airways Image Analysis II Poster Session, 10 papers |
|
16:00-17:30, Subsession TuPbPo-04, Oakdale Foyer Coral Foyer | |
Machine Learning for Brain Studies II Poster Session, 9 papers |
|
16:00-17:30, Subsession TuPbPo-05, Oakdale Foyer Coral Foyer | |
Heart Imaging and Analysis II Poster Session, 7 papers |
|
16:00-17:30, Subsession TuPbPo-06, Oakdale Foyer Coral Foyer | |
Optical Coherence Tomography II Poster Session, 6 papers |
|
16:00-17:30, Subsession TuPbPo-07, Oakdale Foyer Coral Foyer | |
Skin Imaging & Analysis Poster Session, 7 papers |
|
16:00-17:30, Subsession TuPbPo-08, Oakdale Foyer Coral Foyer | |
Abstract Posters: Machine Learning Methods Poster Session, 11 papers |
|
TuPbPo-01 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Image Synthesis |
|
|
Chair: Goldberger, Jacob | Bar-Ilan University |
Co-Chair: Sheet, Debdoot | Indian Institute of Technology Kharagpur |
|
16:00-17:30, Paper TuPbPo-01.1 | Add to My Program |
Generating Controllable Ultrasound Images of the Fetal Head |
|
Lok Hin, Lee | University of Oxford |
Noble, J Alison | University of Oxford |
Keywords: Ultrasound, Fetus, Image synthesis
Abstract: Synthesis of anatomically realistic ultrasound images could be potentially valuable in sonographer training and to provide training images for algorithms, but is a challenging technical problem. Generating examples where different image attributes can be controlled may also be useful for tasks such as semi-supervised classification and regression to augment costly human annotation. In this paper, we propose using an information maximizing generative adversarial network with a least-squares loss function to generate new examples of fetal brain ultrasound images from clinically acquired healthy subject twenty-week anatomy scans. The unsupervised network succeeds in disentangling natural clinical variations in anatomical visibility and image acquisition parameters, which allows for user-control in image generation. To evaluate our method, we also introduce an additional synthetic fetal ultrasound specific image quality metric called the Frechet SonoNet Distance (FSD) to quantitatively evaluate synthesis quality. To the best of our knowledge, this is the first work that generates ultrasound images with a generator network trained on clinical acquisitions where governing parameters can be controlled in a visually interpretable manner.
|
|
16:00-17:30, Paper TuPbPo-01.2 | Add to My Program |
Learning a Self-Inverse Network for Bidirectional MRI Image Synthesis |
|
Shen, Zengming | University of Illinois at Urbana Champaign |
Chen, Yifan | Zhejiang University |
Zhou, Shaohua Kevin | Siemens Corporate Research |
Georgescu, Bogdan | Siemens Corporation, Corporate Technology |
Liu, Xuqi | University of Miami |
Huang, Thomas | UIUC |
Keywords: Image synthesis, Magnetic resonance imaging (MRI)
Abstract: The one-to-one mapping is necessary for MRI image synthesis as MRI images are unique to the patient. State-of-the-art approaches for image synthesis from domain X to domain Y learn a convolutional neural network that meticulously maps between the domains. A different network is typically implemented to map along the opposite direction, from Y to X. In this paper, we explore the possibility of only wielding one network for bi-directional image synthesis. In other words, such an autonomous learning network implements a self-inverse function. A self-inverse network shares several distinct advantages: only one network instead of two, better generalization and more restricted parameter space. Most importantly, a self-inverse function guarantees a one-to-one mapping, a property that cannot be guaranteed by earlier approaches that are not self-inverse. The experiments on MRI T1 and T2 images show that, compared with the baseline approaches that use two separate models for the image synthesis along with two directions, our self-inverse network achieves better synthesis results in terms of standard metrics. Finally, our sensitivity analysis confirms the feasibility of learning a one-to-one mapping function for MRI image synthesis.
|
|
16:00-17:30, Paper TuPbPo-01.3 | Add to My Program |
Virtual Staining for Mitosis Detection in Breast Histopathology |
|
Mercan, Caner | Radboud University Medical Center |
Mooij, Germonda | Radboud University Medical Center, Radboud University |
Tellez Martin, David | Radboud University Medical Center |
Lotz, Johannes | Fraunhofer MEVIS |
Weiss, Nick | Fraunhofer MEVIS |
van Gerven, Marcel | Radboud University Nijmegen |
Ciompi, Francesco | Radboud University Medical Center |
Keywords: Histopathology imaging (e.g. whole slide imaging), Breast, Image synthesis
Abstract: We propose a virtual staining methodology based on Generative Adversarial Networks to map histopathology images of breast cancer tissue from H&E stain to PHH3 and vice versa. We use the resulting synthetic images to build Convolutional Neural Networks (CNN) for automatic detection of mitotic figures, a strong prognostic biomarker used in routine breast cancer diagnosis and grading. We propose several scenarios, in which CNN trained with synthetically generated histopathology images perform on par with or even better than the same baseline model trained with real images. We discuss the potential of this application to scale the number of training samples without the need for manual annotations.
|
|
16:00-17:30, Paper TuPbPo-01.4 | Add to My Program |
3D Conditional Adversarial Learning for Synthesizing Microscopic Neuron Image Using Skeleton-To-Neuron Translation |
|
Tang, Zihao | University of Sydney |
Zhang, Donghao | University of Sydney |
Song, Yang | University of New South Wales |
Wang, Heng | The University of Sydney |
Liu, Dongnan | The University of Sydney |
Zhang, Chaoyi | The University of Sydney |
Liu, Siqi | Siemens Healthineers |
Peng, Hanchuan | Allen Institute for Brain Science |
Cai, Weidong | University of Sydney |
Keywords: Microscopy - Light, Confocal, Fluorescence, Image synthesis, Machine learning
Abstract: The automatic reconstruction of single neuron cells from microscopic images is essential to enabling large-scale data-driven investigations in neuron morphology research. However, the performances of single neuron reconstruction algorithms are constrained by both the quantity and the quality of the annotated 3D microscopic images since the annotating single neuron models is highly labour intensive. We propose a framework for synthesizing microscopy-realistic 3D neuron images from simulated single neuron skeletons using conditional Generative Adversarial Networks (cGAN). We build the generator network with multi-resolution sub-modules to improve the output fidelity. We evaluate our framework on Janelia-Fly dataset from the BigNeuron project. With both qualitative and quantitative analysis, we show that the proposed framework outperforms the other state-of-the-art methods regarding the quality of the synthetic neuron images. We also show that combining the real neuron images and the synthetic images generated from our framework can improve the performance of neuron segmentation.
|
|
16:00-17:30, Paper TuPbPo-01.5 | Add to My Program |
Zero-Shot Adaptation to Simulate 3D Ultrasound Volume by Learning a Multilinear Separable 2D Convolutional Neural Network |
|
Mooga, Anand | Indian Institute of Technology Kharagpur, India |
Sethuraman, Ramanathan | Intel |
Sheet, Debdoot | Indian Institute of Technology Kharagpur |
Keywords: Image synthesis, Machine learning, Ultrasound
Abstract: Ultrasound imaging relies on sensing of waves returned after interaction with scattering media present in biological tissues. An acoustic pulse transmitted by a single element transducer dilates along the direction of propagation, and is observed as 1D point spread function (PSF) in A-mode imaging. In 2D B-mode imaging, a 1D array of transducer elements is used and dilation of pulse is also observed along the direction of these elements, manifesting a 2D PSF. In 3D B-mode imaging using a 2D matrix of transducer elements, a 3D PSF is observed. Fast simulation of a 3D B-mode volume by way of convolutional transformer networks to learn the PSF family would require a training dataset of true 3D volumes which are not readily available. Here we start in Stage 0 with a simple physics based simulator in 3D to generate speckles from a tissue echogenicity map. Next in Stage 1, we learn a multilinear separable 2D convolutional neural network using 1D convolutions to model PSF family along direction of ultrasound propagation and orthogonal to it. This is adversarially trained using a visual Turing test on 2D ultrasound images. The PSF being circularly symmetric about an axis parallel to the direction of wave propagation, we simulate full 3D volume, by way of alternating the direction of 1D convolution along 2 axes that are mutually orthogonal to the direction of wave propagation. We validate performance using visual Turing test with experts and distribution similarity measures.
|
|
16:00-17:30, Paper TuPbPo-01.6 | Add to My Program |
MRI to CT Synthesis of the Lumbar Spine from a Pseudo-3D Cycle Gan |
|
Oulbacha, Reda | Polytechnique Montreal |
Kadoury, Samuel | Polytechnique Montreal |
Keywords: Spine, Image synthesis, Machine learning
Abstract: In this paper, we introduce a fully unsupervised approach for the synthesis of CT images of the lumbar spine, used for image-guided surgical procedures, from a T2-weighted MRI acquired for diagnostic purposes. Our approach makes use of a trainable pre-processing pipeline using a low-capacity fully convolutional network, to normalize the input MRI data, in cascade with FC-ResNets, to segment the vertebral bodies and pedicles. A pseudo-3D Cycle GAN architecture is proposed to include neighboring slices in the synthesis process, along with a cyclic loss function ensuring consistency between MRI and CT synthesis. Clinical experiments were performed on the SpineWeb dataset, totalling 18 patients with both MRI and CT. Quantitative comparison to expert CT segmentations yields an average Dice score of 83 +/- 1.6 on synthetic CTs, while a comparison to CT annotations yielded a landmark localization error of 2.2 +/- 1.4mm. Intensity distributions and mean absolute errors in Hounsfield units also show promising results, illustrating the strong potential and versatility of the pipeline by achieving clinically viable CT scans which can be used for surgical guidance.
|
|
16:00-17:30, Paper TuPbPo-01.7 | Add to My Program |
Open-Set Oct Image Recognition with Synthetic Learning |
|
Xiao, Yuting | ShanghaiTech University |
Gao, Shenghua | ShanghaiTech University |
Chai, Zhenjie | Shanghaitech University |
Zhou, Kang | ShanghaiTech University |
Zhang, Tianyang | Cixi Institute of Biomedical Engineering, Ningbo Institute of In |
Zhao, Yitian | Chinese Academy of Sciences |
Cheng, Jun | Institute of Biomedical Engineering, Chinese Academy of Sciences |
Liu, Jiang | Southern University of Science and Technology |
Keywords: Classification, Retinal imaging, Image synthesis
Abstract: Due to new eye diseases discovered every year, doctors may encounter some rare or unknown diseases. Similarly, in medical image recognition field, many practical medical classification tasks may encounter the case where some testing samples belong to some rare or unknown classes that have never been observed or included in the training set, which is termed as an open-set problem. As rare diseases samples are difficult to be obtained and included in the training set, it is reasonable to design an algorithm that recognizes both known and unknown diseases. Towards this end, this paper leverages a novel generative adversarial network (GAN) based synthetic learning for open-set retinal optical coherence tomography (OCT) image recognition. Specifically, we first train an auto-encoder GAN and a classifier to reconstruct and classify the observed images, respectively. Then a subspace-constrained synthesis loss is introduced to generate images that locate near the boundaries of the subspace of images corresponding to each observed disease, meanwhile, these images cannot be classified by the pre-trained classifier. In other words, these synthesized images are categorized into an unknown class. In this way, we can generate images belonging to the unknown class, and add them into the original dataset to retrain the classifier for the unknown disease discovery
|
|
16:00-17:30, Paper TuPbPo-01.8 | Add to My Program |
Synthesis and Edition of Ultrasound Images Via Sketch Guided Progressive Growing GANs |
|
Liang, Jiamin | Shenzhen University |
Yang, Xin | The Chinese University of Hong Kong |
Li, Haoming | SHENZHEN University |
Wang, Yi | Shenzhen University |
Manh, The Van | Shenzhen University |
Dou, Haoran | Shenzhen University |
Chen, Chaoyu | Shenzhen University |
Fang, Jinghui | Guangzhou Medical University |
Liang, Xiaowen | Guangzhou Medical University |
Mai, Zixin | Guangzhou Medical University |
Zhu, Guowen | SHENZHEN University |
Chen, Zhiyi | Guangzhou Medical University |
Ni, Dong | Shenzhen University |
Keywords: Image synthesis, Ultrasound
Abstract: Ultrasound (US) is widely accepted in clinic for anatomical structure inspection. However, lacking in resources to practice US scan, novices often struggle to learn the operation skills. Also, in the deep learning era, automated US image analysis is limited by the lack of annotated samples. Efficiently synthesizing realistic, editable and high resolution US images can solve the problems. The task is challenging and previous methods can only partially complete it. In this paper, we devise a new framework for US image synthesis. Particularly, we firstly adopt a Sgan to introduce background sketch upon object mask in a conditioned generative adversarial network. With enriched sketch cues, Sgan can generate realistic US images with editable and fine-grained structure details. Although effective, Sgan is hard to generate high resolution US images. To achieve this, we further implant the Sgan into a progressive growing scheme (PGSgan). By smoothly growing both generator and discriminator, PGSgan can gradually synthesize US images from low to high resolution. By synthesizing ovary and follicle US images, our extensive perceptual evaluation, user study and segmentation results prove the promising efficacy and efficiency of the proposed PGSgan.
|
|
16:00-17:30, Paper TuPbPo-01.9 | Add to My Program |
Controllable Skin Lesion Synthesis Using Texture Patches, Bezier Curves and Conditional GANs |
|
Borges Oliveira, Dario Augusto | IBM Research |
Keywords: Image synthesis, Skin, Image segmentation
Abstract: Data synthesis is an important tool for improving data availability in cases where data is hard to capture or annotate. In the context of skin lesions data, data synthesis has been used for data augmentation in automated classification methods or for supporting training of dermoscopic images visual inspection. In this paper, we propose a simple yet effective approach for diverse skin lesion image synthesis using conditional generative adversarial networks. Our pipeline takes as input a random Bezier curve representing the lesion mask, and two texture patches: one for skin, and one for lesion; and synthesizes a new dermoscopic image. Our method generates images where lesions and skin reproduce the corresponding provided texture patches, and the lesion conforms to the provided Bezier mask. Our results report realistic controllable synthesis and improved performance for skin lesion segmentation task considering different semantic segmentation networks in a public challenge in comparison to classic data augmentation.
|
|
16:00-17:30, Paper TuPbPo-01.10 | Add to My Program |
Multi-Modality Generative Adversarial Networks with Tumor Consistency Loss for Brain Mr Image Synthesis |
|
Xin, Bingyu | Tsinghua University |
Hu, Yifan | Tencent Youtu Lab |
Zheng, Yefeng | Tencent Youtu Lab |
Liao, Hongen | Tsinghua University; |
Keywords: Image synthesis, Magnetic resonance imaging (MRI), Brain
Abstract: Magnetic Resonance (MR) images of different modalities can provide complementary information for clinical diagnosis, but whole modalities are often costly to access. Most existing methods only focus on synthesizing missing images between two modalities, which limits their robustness and efficiency when multiple modalities are missing. To address this problem, we propose a multi-modality generative adversarial network (MGAN) to synthesize three high-quality MR modalities (FLAIR, T1 and T1ce) from one MR modality T2 simultaneously. The experimental results show that the quality of the synthesized images by our proposed methods is better than the one synthesized by the baseline model, pix2pix. Besides, for MR brain image synthesis, it is important to preserve the critical tumor information in the generated modalities, so we further introduce a multi-modality tumor consistency loss to MGAN, called TC-MGAN. We use the synthesized modalities by TC-MGAN to boost the tumor segmentation accuracy, and the results demonstrate its effectiveness.
|
|
16:00-17:30, Paper TuPbPo-01.11 | Add to My Program |
3D Ultrasound Generation from Partial 2D Observations Using Fully Convolutional and Spatial Transformation Networks |
|
Mezheritsky, Tal | Polytechnique Montreal |
Vazquez Romaguera, Liset | Polytechnique Montreal |
Kadoury, Samuel | Polytechnique Montreal |
Keywords: Ultrasound, Liver, Image synthesis
Abstract: External beam radiation therapy (EBRT) is a therapeutic modality often used for the treatment of various types of cancer. EBRT’s efficiency highly depends on accurate tracking of the target to be treated and therefore requires the use of real-time imaging modalities such as ultrasound (US) during treatment. While US is cost effective and non-ionizing, 2D US is not well suited to track targets that displace in 3D, while 3D US is challenging to integrate in real-time due to insufficient temporal frequency. In this work, we present a 3D inference model based on fully convolutional networks combined with a spatial transformative network (STN) layer, which given a 2D US image and a baseline 3D US volume as inputs, can predict the deformation of the baseline volume to generate an up-to-date 3D US volume in real-time. We train our model using 20 4D liver US sequences taken from the CLUST15 3D tracking challenge, testing the model on image tracking sequences. The proposed model achieves a normalized cross-correlation of 0.56 in an ablation study and a mean landmark location error of 2.92 ± 1.67mm for target anatomy tracking. These promising results demonstrate the potential of generative STN models for predicting 3D motion fields during EBRT.
|
|
TuPbPo-02 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Ultrasound Imaging and Analysis II |
|
|
Chair: Lavarello, Roberto | Pontificia Universidad Catolica Del Peru |
Co-Chair: Noble, J Alison | University of Oxford |
|
16:00-17:30, Paper TuPbPo-02.1 | Add to My Program |
Transformation Elastography: Converting Anisotropy to Isotropy |
|
Guidetti, Martina | University of Illinois at Chicago |
Klatt, Dieter | The University of Illinois at Chicago |
Royston, Thomas | University of Illinois at Chicago |
Keywords: Elastography imaging, Viscoelasticity imaging, Inverse methods
Abstract: Elastography refers to mapping mechanical properties in a material based on measuring wave motion in it using noninvasive optical, acoustic or magnetic resonance imaging methods. For example, increased stiffness will increase wavelength. Stiffness and viscosity can depend on both location and direction. A material with aligned fibers or layers may have different stiffness and viscosity values along the fibers or layers versus across them. Converting wave measurements into a mechanical property map or image is known as reconstruction. To make the reconstruction problem analytically tractable, isotropy and homogeneity are often assumed, and the effects of finite boundaries are ignored. But, infinite isotropic homogeneity is not the situation in most cases of interest, when there are pathological conditions, material faults or hidden anomalies that are not uniformly distributed in fibrous or layered structures of finite dimension. Introduction of anisotropy, inhomogeneity and finite boundaries complicates the analysis forcing the abandonment of analytically-driven strategies, in favor of numerical approximations that may be computationally expensive and yield less physical insight. A new strategy, Transformation Elastography (TE), is proposed that involves spatial distortion in order to make an anisotropic problem become isotropic. The fundamental underpinnings of TE have been proven in forward simulation problems. In the present paper a TE approach to inversion and reconstruction is introduced and validated based on numerical finite element simulations.
|
|
16:00-17:30, Paper TuPbPo-02.2 | Add to My Program |
CEUS-Net: Lesion Segmentation in Dynamic Contrast-Enhanced Ultrasound with Feature-Reweighted Attention Mechanism |
|
Wan, Peng | Nanjing University of Aeronautics and Astronautics |
Chen, Fang | Nanjing University of Aeronautics and Astronautics |
Zhu, Xiaowei | Nanjing University of Aeronautics and Astronautics |
Liu, Chunrui | Department of Ultrasound, Drum Tower Hospital, the Affiliated Ho |
Zhang, Yidan | Department of Ultrasound, Nanjing Drum Tower Hospital, the Affilia |
Kong, Wentao | Drumtower Hospital, Medical College of Nanjing University |
Zhang, Daoqiang | Nanjing University of Aeronautics and Astronautics |
Keywords: Perfusion imaging, Ultrasound, Image segmentation
Abstract: Contrast-enhanced ultrasound (CEUS) has been a popular clinical imaging technique for the dynamic visualization of the tumor microvasculature. Due to the heterogeneous intratumor vessel distribution and ambiguous lesion boundary, automatic tumor segmentation in the CEUS sequence is challenging. To overcome these difficulties, we propose a novel network, CEUS-Net, which is a novel U-net network infused with our designed feature-reweighted dense blocks. Specifically, CEUS-Net incorporates the dynamic channel-wise feature re-weighting into the Dense block for adapting the importance of learned lesion-relevant features. Besides, in order to efficiently utilize dynamic characteristics of CEUS modality, our model attempts to learn spatial-temporal features encoded in diverse enhancement patterns using a multichannel convolutional module. The CEUS-Net has been tested on tumor segmentation tasks of CEUS images from breast and thyroid lesions. It results in the dice index of 0.84, and 0.78 for CEUS segmentation of breast and thyroid respectively.
|
|
16:00-17:30, Paper TuPbPo-02.3 | Add to My Program |
H-Scan Format for Classification of Ultrasound Scatterers and Matched Comparison to Histology Measurements |
|
Khairalseed, Mawia | University of Texas at Dallas |
Rijal, Girdhari | University of Texas at Dallas |
Hoyt, Kenneth | University of Texas at Dallas |
Keywords: Ultrasound, Tissue, Classification
Abstract: H-scan imaging is a new ultrasound (US) technique used to visualize the relative size of acoustic scatterers. The purpose of this study was to evaluate the sensitivity of H-scan US imaging to scatterer size and comparison to histological sections of tumor tissue. Image data was acquired using a programmable US scanner (Vantage 256, Verasonics Inc) equipped with a 256-element L22-8v capacitive micromachined ultrasonic transducer (CMUT, Kolo Medical). To generate the H-scan US image, three parallel convolution filters were applied to the radiofrequency (RF) data sequences to measure the relative strength of the backscattered US signals. H-scan US imaging was used to image a gelatin-based heterogenous phantom and breast tumor-bearing mice (N = 4). Excised tumor tissue underwent histologic processing and the cells were segmented to compute physical size measurements at the cellular level followed by spatial correlation with H-scan US image features. The in vitro results show that there was an improvement in the contrast-to-noise ratio (CNR) of 44.1% for H-scan compared to B-scan US imaging. Preliminary animal studies revealed there was a statistically significant relationship between H-scan US and physical size measures at the cell level (R2 > 0.95, p < 0.02). Overall, this study details the first experimental evidence that H-scan US image findings are directly related to physical cell size of the underlying bulk tumor tissue.
|
|
16:00-17:30, Paper TuPbPo-02.4 | Add to My Program |
Remove Appearance Shift for Ultrasound Image Segmentation Via Fast and Universal Style Transfer |
|
Liu, Zhendong | Shenzhen University |
Yang, Xin | The Chinese University of Hong Kong |
Liu, Shengfeng | Shenzhen University |
Gao, Rui | Shenzhen University |
Dou, Haoran | Shenzhen University |
He, Shuangchi | School of Biomedical Engineering, Shenzhen University |
Huang, Yuhao | Shenzhen University |
Huang, Yankai | Shenzhen Luohu Hospital Group Luohu People's Hospital, the Thir |
Zhang, Yuanji | Shenzhen Luohu Group Luohu People's Hospital,The Third Af |
Luo, Huanjia | The Second Clinical Medical College of Jinan University, Shenzhe |
Xiong, Yi | Shenzhen Luohu People's Hospital, the Third Affiliated Hospital, S |
Ni, Dong | Shenzhen University |
Keywords: Machine learning, Image segmentation, Ultrasound
Abstract: Deep Neural Networks (DNNs) suffer from the performance degradation when image appearance shift occurs, especially in ultrasound (US) image segmentation. In this paper, we propose a novel and intuitive framework to remove the appearance shift, and hence improve the generalization ability of DNNs. Our work has three highlights. First, we follow the spirit of universal style transfer to remove appearance shifts, which was not explored before for US images. Without sacrificing image structure details, it enables the arbitrary style-content transfer. Second, accelerated with Adaptive Instance Normalization block, our framework achieved real-time speed required in the clinical US scanning. Third, an efficient and effective style image selection strategy is proposed to ensure the target-style US image and testing content US image properly match each other. Experiments on two large US datasets demonstrate that our methods are superior to state-of-the-art methods on making DNNs robust against various appearance shifts.
|
|
16:00-17:30, Paper TuPbPo-02.5 | Add to My Program |
Region Proposal Network with IoU-Balance Loss and Graph Prior for Landmark Detection in 3D Ultrasound |
|
Chen, Chaoyu | Shenzhen University |
Yang, Xin | The Chinese University of Hong Kong |
Huang, Ruobing | Shenzhen University |
Shi, Wenlong | Shenzhen University |
Liu, Shengfeng | Shenzhen University |
Lin, Mingrong | Shenzhen Uniwersity |
Huang, Yuhao | Shenzhen University |
Yang, Yong | Shenzhen University |
Zhang, Yuanji | Shenzhen Luohu Group Luohu People's Hospital,The Third Af |
Luo, Huanjia | The Second Clinical Medical College of Jinan University, Shenzhe |
Huang, Yankai | Shenzhen Luohu Hospital Group Luohu People's Hospital, the Thir |
Xiong, Yi | Shenzhen Luohu People's Hospital, the Third Affiliated Hospital, S |
Ni, Dong | Shenzhen University |
Keywords: Ultrasound, Fetus, Machine learning
Abstract: 3D ultrasound (US) can improve the prenatal examinations for fetal growth monitoring. Detecting anatomical landmarks of fetus in 3D US has plenty of applications. Classical methods directly regress the coordinates or gaussian heatmaps of landmarks. However, these methods tend to show drawbacks when facing with the large volume and poor image quality of 3D US images. Different from previous methodology, in this work, we propose a successful and first investigation about exploiting object detection framework for landmark detection in 3D US. By regressing multiple parameters of the landmark-centered bounding box (B-box) with strict criteria, object detection framework presents potentials in outperforming previous landmark detection methods. Specifically, we choose the region proposal network (RPN) with localization and classification branches as our backbone for detection efficiency. Based on 3D RPN, we propose to adopt an IoU-balance loss to enhance the communication between two branches and promote the landmark localization. Furthermore, we build a distance based graph prior to regularize the landmark localization and therefore reduce false positives. We validate our method on the challenging task of detection for five fetal facial landmarks. Regarding the landmark localization and classification criteria, our method outperforms the state-of-the-art methods in efficacy and efficiency.
|
|
16:00-17:30, Paper TuPbPo-02.6 | Add to My Program |
Breast Lesion Segmentation in Ultrasound Images with Limited Annotated Data |
|
Behboodi, Bahareh | Concordia University |
Amiri, Mina | Concordia University |
Brooks, Rupert | Nuance Communications and Concordia University |
Rivaz, Hassan | Concordia University |
Keywords: Ultrasound, Machine learning, Image segmentation
Abstract: Ultrasound (US) is one of the most commonly used imaging modalities in both diagnosis and surgical interventions due to its low-cost, safety, and non-invasive characteristic. US image segmentation is currently a unique challenge because of the presence of speckle noise. As manual segmentation requires considerable efforts and time, the development of automatic segmentation algorithms has attracted researchers’ attention. Although recent methodologies based on convolutional neural networks have shown promising performances, their success relies on the availability of a large number of training data, which is prohibitively difficult for many applications. There- fore, in this study we propose the use of simulated US images and natural images as auxiliary datasets in order to pre-train our segmentation network, and then to fine-tune with limited in vivo data. We show that with as little as 19 in vivo images, fine-tuning the pre-trained network improves the dice score by 21% compared to training from scratch. We also demonstrate that if the same number of natural and simulation US images is available, pre-training on simulation data is preferable.
|
|
16:00-17:30, Paper TuPbPo-02.7 | Add to My Program |
Three-Dimensional Voxel-Level Classification of Ultrasound Scattering |
|
Tai, Haowei | University of Texas at Dallas |
Dolui, Swapnil | University of Texas at Dallas |
Khairalseed, Mawia | University of Texas at Dallas |
Hoyt, Kenneth | University of Texas at Dallas |
Keywords: Ultrasound
Abstract: Three-dimensional (3D) H-scan ultrasound (US) is a new high-resolution imaging technology for voxel-level tissue classification. For the purpose of validation, a simulated H-scan US imaging system was developed to comprehensively study the sensitivity to scatterer size in volume space. A programmable research US system (Vantage 256, Verasonics Inc, Kirkland, WA) equipped with a custom volumetric imaging transducer (4DL7, Vermon, Tours, France) was used for US data acquisition and comparison to simulated findings. Preliminary studies were conducted using homogeneous phantoms embedded with acoustic scatterers of varying sizes (15, 30, 40 or 250 μm). Both simulation and experimental results indicate that the H-scan US imaging method is more sensitive than B-mode US in differentiating US scatterers of varying size. Overall, this study proved useful for evaluating H-scan US imaging of tissue scatterer patterns and will inform future technology research and development.
|
|
16:00-17:30, Paper TuPbPo-02.8 | Add to My Program |
Automated Meshing of Anatomical Shapes for Deformable Medial Modeling: Application to the Placenta in 3d Ultrasound |
|
Pouch, Alison | University of Pennsylvania |
Yushkevich, Paul | University of Pennsylvania |
Aly, Abdullah | University of Pennsylvania |
Woltersom, Alexander | University of Pennsylvania |
Okon, Edidiong | University of Pennsylvania |
Aly, Ahmed | University of Pennsylvania |
Yushkevich, Natalie | University of Pennsylvania |
Parameshwaran, Shobhana | University of Pennsylvania |
Wang, Jiancong | PICSL Lab, University of Pennsylvannia |
Oguz, Baris | University of Pennsylvania |
Gee, James | University of Pennsylvania |
Oguz, Ipek | Vanderbilt University |
Schwartz, Nadav | University of Pennsylvania |
Keywords: Shape analysis, Ultrasound, Modeling - Anatomical, physiological and pathological
Abstract: Deformable medial modeling is an approach to extracting clinically useful features of the morphological skeleton of anatomical structures in medical images. Similar to any deformable modeling technique, it requires a pre-defined model, or synthetic skeleton, of a class of shapes before modeling new instances of that class. The creation of synthetic skeletons often requires manual interaction, and the deformation of the synthetic skeleton to new target geometries is prone to registration errors if not well initialized. This work presents a fully automated method for creating synthetic skeletons (i.e., 3D boundary meshes with medial links) for flat, oblong shapes that are homeomorphic to a sphere. The method rotationally cross-sections the 3D shape, approximates a 2D medial model in each cross-section, and then defines edges between nodes of neighboring slices to create a regularly sampled 3D boundary mesh. In this study, we demonstrate the method on 62 segmentations of placentas in first-trimester 3D ultrasound images and evaluate its compatibility and representational accuracy with an existing deformable modeling method. The method may lead to extraction of new clinically meaningful features of placenta geometry, as well as facilitate other applications of deformable medial modeling in medical image analysis.
|
|
16:00-17:30, Paper TuPbPo-02.9 | Add to My Program |
Self-Supervised Representation Learning for Ultrasound Video |
|
Jiao, Jianbo | University of Oxford |
Droste, Richard | University of Oxford |
Drukker, Lior | Nuffield Department of Women’s and Reproductive Health, Universi |
Papageorghiou, Aris | Nuffield Department of Obstetrics and Gynaecology, John Ra |
Noble, J Alison | University of Oxford |
Keywords: Ultrasound, Fetus, Machine learning
Abstract: Recent advances in deep learning have achieved promising performance for medical image analysis, while in most cases ground-truth annotations from human experts are necessary to train the deep model. In practice, such annotations are expensive to collect and can be scarce for medical imaging applications. Therefore, there is significant interest in learning representations from unlabelled raw data. In this paper, we propose a self-supervised learning approach to learn meaningful and transferable representations from medical imaging video without any type of human annotation. We assume that in order to learn such a representation, the model should identify anatomical structures from the unlabelled data. Therefore we force the model to address anatomy-aware tasks with free supervision from the data itself. Specifically, the model is designed to correct the order of a reshuffled video clip and at the same time predict the geometric transformation applied to the video clip. Experiments on fetal ultrasound video show that the proposed approach can effectively learn meaningful and strong representations, which transfer well to downstream tasks like standard plane detection and saliency prediction.
|
|
TuPbPo-03 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Lung, Chest, and Airways Image Analysis II |
|
|
|
16:00-17:30, Paper TuPbPo-03.1 | Add to My Program |
A Robust Network Architecture to Detect Normal Chest X-Ray Radiographs |
|
Wong, Ken C. L. | IBM Research - Almaden Research Center |
Moradi, Mehdi | IBM Research |
Wu, Joy Tzung-yu | IBM Research - Almaden |
Pillai, Anup | IBM Research |
Sharma, Arjun | IBM |
Gur, Yaniv | IBM Almaden Research Center |
Ahmad, Hassan | IBM |
Wunnava, Venkateswar | Deccan Hospital |
Chiranjeevi, J | Deccan Hospital |
Polaka, Kiran Kumar Reddy | Deccan Hospital |
Chowdary, Minnekanti Sunil | Deccan Hospital |
Reddy, Dc | Osmania University |
Syeda-Mahmood, Tanveer | IBM Almaden Research Center |
Keywords: X-ray imaging, Lung, Machine learning
Abstract: We propose a novel deep neural network architecture for normalcy detection in chest x-ray images. This architecture treats the problem as fine-grained binary classification in which the normal cases are well-defined as a class while leaving all other cases in the broad class of abnormal. It employs several components that allow generalization and prevent overfitting across demographics. The model is trained and validated on a large public dataset of frontal chest X-ray images. It is then tested independently on images from a clinical institution of differing patient demographics using a three radiologist consensus for ground truth labeling. The model provides an area under ROC curve of 0.96 when tested on 1271 images. Using this model, we can automatically remove nearly a third of disease-free chest X-ray screening images from the workflow, without introducing any false negatives thus raising the potential of expediting radiology workflows in hospitals in future.
|
|
16:00-17:30, Paper TuPbPo-03.2 | Add to My Program |
Estimating Local Tissue Expansion in Thoracic Computed Tomography Images Using Convolutional Neural Networks |
|
Gerard, Sarah E. | Brigham Women's Hospital and Harvard Medical School |
Reinhardt, Joseph M. | The University of Iowa |
Christensen, Gary E. | The University of Iowa |
San Jose Estepar, Raul | Brigham Women's Hospital and Harvard Medical School |
Keywords: Computed tomography (CT), Lung, Machine learning
Abstract: Registration of lungs in thoracic computed tomography (CT) images produces a dense correspondence which can be analyzed to estimate local tissue expansion. However, the validity of this local expansion estimate is dependent on the accuracy of the image registration. In this work, a convolutional neural network (CNN) model is used to directly estimate the local tissue expansion between lungs imaged at two lung volumes, without requiring image registration. The network was trained with 5705 subjects from COPDGene with varying degrees of disease severity. The CNN-based model was evaluated with 3046 subjects from COPDGene. At the global scale, the mean lung expansion estimated from the CNN-based and registration-based models were highly correlated (rs = 0.945). At the local scale, the proposed method achieved a voxelwise Spearman correlation of 0.871 ± 0.080. At the regional scale, Dice coefficient for high and low func- tioning regions was 0.806 ± 0.065 and 0.805 ± 0.066, respectively. The results indicate the CNN-based model was able to reproduce image registration derived tissue expansion images without explicitly estimating the correspondence.
|
|
16:00-17:30, Paper TuPbPo-03.3 | Add to My Program |
Improving Lung Nodule Detection with Learnable Non-Maximum Suppression |
|
Capia Quispe, Elvis Rusnel | University of Campinas |
Melo e Sousa, Azael | Unicamp |
Falcao, Alexandre Xavier | University of Campinas |
Keywords: Computed tomography (CT), Lung, Machine learning
Abstract: Current lung nodule detection methods generate several candidate regions per nodule, such that a Non-Maximum Suppression (NMS) algorithm is required to select a single region per nodule while eliminating the redundant ones. GossipNet is a 1D Neural Network (NN) for NMS, which can learn the NMS parameters rather than relying on handcrafted ones. However, GossipNet does not take advantage of image features to learn NMS. We use Faster R-CNN with ResNet18 for candidate region detection and present FeatureNMS --- a neural network that provides additional image features to the input of GossipNet, which result from a transformation over the voxel intensities of each candidate region in the CT image. Experiments indicate that FeatureNMS can improve nodule detection in 2.33% and 0.91%, on average, when compared to traditional NMS and the original GossipNet, respectively.
|
|
16:00-17:30, Paper TuPbPo-03.4 | Add to My Program |
DeepSEED: 3D Squeeze-And-Excitation Encoder-Decoder Convolutional Neural Networks for Pulmonary Nodule Detection |
|
Li, Yuemeng | University of Pennsylvania |
Fan, Yong | University of Pennsylvania |
Keywords: Lung, Computer-aided detection and diagnosis (CAD), Computed tomography (CT)
Abstract: Pulmonary nodule detection plays an important role in lung cancer screening with low-dose computed tomography (CT) scans. It remains challenging to build nodule detection deep learning models with good generalization performance due to unbalanced positive and negative samples. In order to overcome this problem and further improve state-of-the-art nodule detection methods, we develop a novel deep 3D convolutional neural network with an Encoder-Decoder structure in conjunction with a region proposal network. Particularly, we utilize a dynamically scaled cross entropy loss to reduce the false positive rate and combat the sample imbalance problem associated with nodule detection. We adopt the squeeze-and-excitation structure to learn effective image features and utilize inter-dependency information of different feature maps. We have validated our method based on publicly available CT scans with manually labelled ground-truth obtained from LIDC/IDRI dataset and its subset LUNA16 with thinner slices. Ablation studies and experimental results have demonstrated that our method could outperform state-of-the-art nodule detection methods by a large margin.
|
|
16:00-17:30, Paper TuPbPo-03.5 | Add to My Program |
Lung Nodule Malignancy Classification Based on NLSTx Data |
|
Veasey, Benjamin | University of Louisville |
Farhangi, Mohammad Mehdi | University of Louisville |
Frigui, Hichem | University of Louisville |
Broadhead, Justin | University of Louisville |
Dahle, Michael | University of Louisville |
Pezeshk, Aria | U.S. Food and Drug Administration |
Seow, Albert | University of Louisville |
Amini, Amir | University of Louisville |
Keywords: Lung, Classification, Computed tomography (CT)
Abstract: While several datasets containing CT images of lung nodules exist, they do not contain definitive diagnoses and often rely on radiologists' visual assessment for malignancy rating. This is in spite of the fact that lung cancer is one of the top three most frequently misdiagnosed diseases based on visual assessment. In this paper, we propose a dataset of difficult-to-diagnose lung nodules based on data from the National Lung Screening Trial (NLST), which we refer to as NLSTx. In NLSTx, each malignant nodule has a definitive ground truth label from biopsy. Herein, we also propose a novel deep convolutional neural network (CNN) / recurrent neural network framework that allows for use of pre-trained 2-D convolutional feature extractors, similar to those developed in the ImageNet challenge. Our results show that the proposed framework achieves comparable performance to an equivalent 3-D CNN while requiring half the number of parameters.
|
|
16:00-17:30, Paper TuPbPo-03.6 | Add to My Program |
Relational Learning between Multiple Pulmonary Nodules Via Deep Set Attention Transformers |
|
Yang, Jiancheng | Shanghai Jiao Tong University |
Deng, Haoran | Shanghai Jiao Tong University |
Huang, Xiaoyang | Shanghai Jiao Tong University |
Ni, Bingbing | Shanghai Jiao Tong University |
Xu, Yi | Shanghai Jiao Tong University |
Keywords: Machine learning, Computer-aided detection and diagnosis (CAD)
Abstract: Diagnosis and treatment of multiple pulmonary nodules are clinically important but challenging. Prior studies on nodule characterization use solitary-nodule approaches on multiple nodular patients, which ignores the relations between nodules. In this study, we propose a multiple instance learning (MIL) approach and empirically prove the benefit to learn the relations between multiple nodules. By treating the multiple nodules from a same patient as a whole, critical relational information between solitary-nodule voxels is extracted. To our knowledge, it is the first study to learn the relations between multiple pulmonary nodules. Inspired by recent advances in natural language processing (NLP) domain, we introduce a self-attention transformer equipped with 3D CNN, named NoduleSAT, to replace typical pooling-based aggregation in multiple instance learning. Extensive experiments on lung nodule false positive reduction on LUNA16 database, and malignancy classification on LIDC-IDRI database, validate the effectiveness of the proposed method.
|
|
16:00-17:30, Paper TuPbPo-03.7 | Add to My Program |
Localization of Critical Findings in Chest X-Ray without Local Annotations Using Multi-Instance Learning |
|
Schwab, Evan | Philips Research North America |
Gooßen, Andre | Philips Research Germany |
Deshpande, Hrishikesh | Philips Research, Hamburg, Germany |
Saalbach, Axel | Philips GmbH, Innovative Technologies |
Keywords: X-ray imaging, Pattern recognition and classification, Lung
Abstract: The automatic detection of critical findings in chest X-rays (CXR), such as pneumothorax, is important for assisting radiologists in their clinical workflow like triaging time-sensitive cases and screening for incidental findings. While deep learning (DL) models has become a promising predictive technology with near-human accuracy, they commonly suffer from a lack of explainability, which is an important aspect for clinical deployment of DL models in the highly regulated healthcare industry. For example, localizing critical findings in an image is useful for explaining the predictions of DL classification algorithms. While there have been a host of joint classification and localization methods for computer vision, the state-of-the-art DL models require locally annotated training data in the form of pixel level labels or bounding box coordinates. In the medical domain, this requires an expensive amount of manual annotation by medical experts for each critical finding. This requirement becomes a major barrier for training models that can rapidly scale to various findings. In this work, we address these shortcomings with an interpretable DL algorithm based on multi-instance learning that jointly classifies and localizes critical findings in CXR without the need for local annotations. We show competitive classification results on three different critical findings (pneumothorax, pneumonia, and pulmonary edema) from three different CXR datasets.
|
|
16:00-17:30, Paper TuPbPo-03.8 | Add to My Program |
Locally Adaptive Half-Max Methods for Airway Lumen-Area and Wall-Thickness and Their Repeat CT Scan Reproducibility |
|
Nadeem, Syed Ahmed | University of Iowa |
Hoffman, Eric | University of Iowa |
Comellas, Alejandro | Department of Internal Medicine, University of Iowa, Iowa City, |
Saha, Punam K. | University of Iowa |
Keywords: Lung, Computed tomography (CT), Quantification and estimation
Abstract: Quantitative computed tomography (CT)-based characterization of bronchial metrics is increasingly being used to investigate chronic obstructive pulmonary disease (COPD)-related phenotypes. Automated methods for airway measurements benefit large multi-site studies by reducing cost and subjectivity errors. Critical challenges for CT-based analysis of airway morphology are related to location of lumen and wall transitions in the presence of varying scales and intensity-contrasts from proximal to distal sites. This paper introduces locally adaptive half-max methods to locate airway lumen and wall transitions and compute cross-sectional lumen area and wall-thickness. Also, the method uses a consistency analysis of wall-thickness to avoid adjoining-structure-artifacts. Experimental results show that computed bronchial measures at individual anatomic airway tree locations are repeat CT scan reproducible with intra-class correlation coefficient (ICC) values exceeding 0.9 and 0.8 for lumen-area and wall-thickness, respectively. Observed ICC values for derived morphologic measures, e.g., lumen-area compactness (ICC>0.67) and tapering (ICC>0.47) are relatively lower.
|
|
16:00-17:30, Paper TuPbPo-03.9 | Add to My Program |
Airway Segmentation in Speech MRI Using the U-Net Architecture |
|
Erattakulangara, Subin | University of Iowa |
Lingala, Sajan Goud | The University of Iowa |
Keywords: Magnetic resonance imaging (MRI), Image segmentation
Abstract: We develop a fully automated airway segmentation method to segment the vocal tract airway from surrounding soft tissue in speech MRI. We train a U-net architecture to learn the end to end mapping between a mid-sagittal image (at the input), and the manually segmented airway (at the output). We base our training on the open source University of Southern California’s (USC) speech morphology MRI database consisting of speakers producing a variety of sustained vowel and consonant sounds. Once trained, our model performs fast airway segmentations on unseen images at the order of 210 ms/slice on a modern CPU with 12 cores. Using manual segmentation as a reference, we evaluate the performances of the proposed U-net airway segmentation, against existing seed-growing segmentation, and manual segmentation from a different user. We demonstrate improved DICE similarity with U-net compared to seed-growing, and minor differences in DICE similarity of U-net compared to manual segmentation from the second user.
|
|
16:00-17:30, Paper TuPbPo-03.10 | Add to My Program |
Assessment of Lung Biomechanics in COPD Using Image Registration |
|
Pan, Yue | University of Iowa |
Christensen, Gary E. | The University of Iowa |
Durumeric, Oguz | University of Iowa |
Gerard, Sarah | The University of Iowa |
Bhatt, Surya P. | University of Alabama at Birmingham, Birmingham |
Barr, R. Graham | Columbia University Medical Center |
Hoffman, Eric | University of Iowa |
Reinhardt, Joseph M. | The University of Iowa |
Keywords: Modeling - Anatomical, physiological and pathological, Lung, Computed tomography (CT)
Abstract: Lung biomechanical properties can be used to detect disease, assess abnormal lung function, and track disease progression.In this work, we used computed tomography (CT) imaging to measure three biomechanical properties in the lungs of subjects with varying degrees of chronic obstructive pulmonary disease (COPD): the Jacobian determinant (J), a measure of volumetric expansion or contraction; the anisotropic deformation index (ADI), a measure of the magnitude of anisotropic deformation; and the the slab-rod index (SRI), a measure of the nature of anisotropy (i.e., whether the volume is deformed to a rod-like or slab-like shape). We analyzed CT data from247 subjects collected as part of the Subpopulations and Inter-mediate Outcome Measures in COPD Study (SPIROMICS). The results show that the mean J and mean ADI decrease as disease severity increases, indicating less volumetric expansion and more isotroic expansion with increased disease. No differences in average SRI index were observed across the different levels of disease. The methods and analysis described in this study may provide new insights into our understanding of the biomechanical behavior of the lung and the changesthat occur with COPD.
|
|
TuPbPo-04 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Machine Learning for Brain Studies II |
|
|
Chair: Bas, Erhan | General Electrics |
Co-Chair: Freiman, Moti | Technion - Israel Institute of Technology |
|
16:00-17:30, Paper TuPbPo-04.1 | Add to My Program |
Walking Imagery Evaluation Based on Multi-View Features and Stacked Denoising Auto-Encoder Network |
|
Liang, Enmin | Shenzhen University |
Lei, Baiying | Shenzhen University |
Elazab, Ahmed | Shenzhen University |
Liang, Shuang | Chinese Academy of Sciences |
Wang, Qiong | Shenzhen Institutes of Advanced Technology, Chinese Academy of S |
Wang, Tianfu | Shenzhen University |
Keywords: EEG & MEG, Machine learning
Abstract: Brain-computer interfaces (BCIs) based on motor imagery (MI) have played an important role and obtained remarkable achievement in exercise rehabilitation. However, most of the previous researches focused on the upper limb, while many disabled patients need the same technology to assist their rehabilitation training. It is more difficult to detect lower limb MI than upper limb because of the deeper and smaller corresponding sensorimotor cortex. To solve this problem, a new paradigm is proposed to perform waking imagery (WI) for subjects in a virtual environment (VE) to further enhance their brain activities. Furthermore, to decode WI efficiently when facing the low reliable and limited data, we propose a stacked denoising auto-encoder (SDAE) network which is trained on multi-view data obtained in VE. First, the spatial and time-frequency-based features are extracted and fused from the raw data. Second, we use SDAE network to extract the hidden features from the above features. Third, we fuse the previous features and hidden features to train the Softmax classifier. Experimental results on our self-collected data demonstrate that, SDAE network outperforms other deep learning methods in classifying WI in VE.
|
|
16:00-17:30, Paper TuPbPo-04.2 | Add to My Program |
Temporally Adaptive-Dynamic Sparse Network for Modeling Disease Progression |
|
Zhang, Jie | Arizona State University |
Wang, Yalin | Arizona State University |
Keywords: Computer-aided detection and diagnosis (CAD), Brain, Magnetic resonance imaging (MRI)
Abstract: Alzheimer's disease (AD) is a neurodegenerative disorder with progressive impairment of memory and cognitive functions. Sparse coding (SC) has been demonstrated to be an efficient and effective method for AD diagnosis and prognosis. However, previous SC methods usually focus on the baseline data while ignoring the consistent longitudinal features with strong sparsity pattern along the disease progression. Additionally, SC methods extract sparse features from image patches separately rather than learn with the dictionary atoms across the entire subject. To address these two concerns and comprehensively capture temporal-subject sparse features towards earlier and better discriminability of AD, we propose a novel supervised SC network termed Temporally Adaptive-Dynamic Sparse Network (TADsNet) to uncover the sequential correlation and native subject-level codes from the longitudinal brain images. Our work adaptively updates the sparse codes to impose the temporal regularized correlation and dynamically mine the dictionary atoms to make use of entire subject-level features. Experimental results on ADNI-I cohort validate the superiority of our approach.
|
|
16:00-17:30, Paper TuPbPo-04.3 | Add to My Program |
Bayesian Skip-Autoencoders for Unsupervised Hyperintense Anomaly Detection in High Resolution Brain MRI |
|
Baur, Christoph | TU Munich |
Wiestler, Benedikt | Dept. of Neuroradiology, TU Munich University Hospital |
Albarqouni, Shadi | ETH Zurich |
Navab, Nassir | TU Munich |
Keywords: Image segmentation, Brain, Magnetic resonance imaging (MRI)
Abstract: Autoencoder-based approaches for Unsupervised Anomaly Detection (UAD) in brain MRI have recently gained a lot of attention and have shown promising performance. However, brain MR images are particularly complex and require large model capacity for learning a proper reconstruction, which existing methods encounter by restricting themselves to downsampled data or anatomical subregions. In this work, we show that models with limited capacity can be trained and used for UAD in full brain MR images at their native resolution by introducing skip-connections, a concept which has already proven beneficial for biomedical image segmentation and image-to-image translation, and a dropout-based mechanism to prevent the model from learning an identity mapping. In an ablative study on two different pathologies we show considerable improvements over State-of-the-Art Autoencoder-based UAD models. The stochastic nature of the model also allows to investigate epistemic uncertainty in our so-called Skip-Autoencoder, which is briefly portrayed.
|
|
16:00-17:30, Paper TuPbPo-04.4 | Add to My Program |
Learning to Detect Brain Lesions from Noisy Annotations |
|
Karimi, Davood | Boston Children's Hospital, Harvard Medical School |
Peters, Jurriaan | Boston Children's Hospital |
Ouaalam, Abdelhakim | Boston Childrens Hospital |
Prabhu, Sanjay | Boston Children's Hospital, Harvard Medical School |
Sahin, Mustafa | Boston Children's Hospital |
Krueger, Darcy A | Cincinnati Children's Hospital Medical Center |
Kolevzon, Alexander | Seaver Autism Center for Research and Treatment, Icahn School Of |
Eng, Charis | Genomic Medicine Institute, Cleveland Clinic |
Warfield, Simon K. | Harvard Medical School |
Gholipour, Ali | Children's Hospital Boston and Harvard Medical School |
Keywords: Machine learning, Image segmentation, Magnetic resonance imaging (MRI)
Abstract: Supervised training of deep neural networks in medical imaging applications relies heavily on expert-provided annotations. These annotations, however, are often imperfect, as voxel-by-voxel labeling of structures on 3D images is difficult and laborious. In this paper, we focus on one common type of label imperfection, namely, false negatives. Focusing on brain lesion detection, we propose a method to train a convolutional neural network (CNN) to segment lesions while simultaneously improving the quality of the training labels by identifying false negatives and adding them to the training labels. To identify lesions missed by annotators in the training data, our method makes use of the 1) CNN predictions, 2) prediction uncertainty estimated during training, and 3) prior knowledge about lesion size and features. On a dataset of 165 scans of children with tuberous sclerosis complex from five centers, our method achieved better lesion detection and segmentation accuracy than the baseline CNN trained on the noisy labels, and than several alternative techniques.
|
|
16:00-17:30, Paper TuPbPo-04.5 | Add to My Program |
A High-Powered Brain Age Prediction Model Based on Convolutional Neural Network |
|
Rao, Guangxiang | Institute of Automation, Chinese Academy of Sciences |
Li, Ang | Institute of Automation, Chinese Academy of Sciences |
Liu, Yong | Chinese Academy of Sciences |
Liu, Bing | Institute of Automation, Chinese Academy of Sciences |
Keywords: Magnetic resonance imaging (MRI), Brain, Machine learning
Abstract: Predicting individual chronological age based on neuroimaging data is very promising and important for understanding the trajectory of normal brain development. In this work, we proposed a new model to predict brain age ranging from 12 to 30 years old, based on structural magnetic resonance imaging and a deep learning approach with reduced model complexity and computational cost. We found that this model can predict brain age accurately not only in the training set (N = 1721, mean absolute error is 1.89 in 10-fold cross validation) but in an independent validation set (N = 226, mean absolute error is 1.96), substantially outperforming the previous published models. Given the considerable accuracy and generalizability, it is promising to further deploy our model in the clinic and help to investigate the pathophysiology of neurodevelopmental disorders.
|
|
16:00-17:30, Paper TuPbPo-04.6 | Add to My Program |
Deep Network-Based Feature Selection for Imaging Genetics: Application to Identifying Biomarkers for Parkinson’s Disease |
|
Kim, Mansu | University of Pennsylvania |
Won, Ji Hye | Sungkyunkwan University |
Hong, Jisu | Sungkyunkwan University |
Kwon, Junmo | Sungkyunkwan University |
Park, Hyunjin | Sungkyunkwan University |
Shen, Li | University of Pennsylvania |
Keywords: Machine learning, Data Mining, Brain
Abstract: Imaging genetics is a methodology for discovering associations between imaging and genetic variables. Many studies adopted sparse models such as sparse canonical correlation analysis (SCCA) for imaging genetics. These methods are limited to modeling the linear imaging genetics relationship and cannot capture the non-linear high-level relationship between the explored variables. Deep learning approaches are underexplored in imaging genetics, compared to their great successes in many other biomedical domains such as image segmentation and disease classification. In this work, we proposed a deep learning model to select genetic features that can explain the imaging features well. Our empirical study on simulated and real datasets demonstrated that our method outperformed the widely used SCCA method and was able to select important genetic features in a robust fashion. These promising results indicate our deep learning model has the potential to reveal new biomarkers to improve mechanistic understanding of the studied brain disorders.
|
|
16:00-17:30, Paper TuPbPo-04.7 | Add to My Program |
Deep Multimodal Brain Network Learning for Joint Analysis of Structural Morphometry and Functional Connectivity |
|
Zhang, Wen | School of Computing, Informatics, and Decision Systems Engineeri |
Wang, Yalin | Arizona State University |
Keywords: Multi-modality fusion, Graphical models & methods, Machine learning
Abstract: Learning from the multimodal brain imaging data attracts a large amount of attention in medical image analysis due to the proliferation of multimodal data collection. It is widely accepted that multimodal data can provide complementary information than mining from a single modality. However, unifying the image-based knowledge from the multimodal data is very challenging due to different image signals, resolution, data structure, etc.. In this study, we design a supervised deep model to jointly analyze brain morphometry and functional connectivity on the cortical surface and we name it deep multimodal brain network learning (DMBNL). Two graph-based kernels, i.e., geometry-aware surface kernel (GSK) and topology-aware network kernel (TNK), are proposed for processing the cortical surface morphometry and brain functional network. The vertex features on the cortical surface from GSK is pooled and feed into TNK as its initial regional features. In the end, the graph-level feature is computed for each individual and thus can be applied for classification tasks. We test our model on a large autism imaging dataset. The experimental results prove the effectiveness of our model.
|
|
16:00-17:30, Paper TuPbPo-04.8 | Add to My Program |
Adaptive Weighted Minimax-Concave Penalty Based Dictionary Learning for Brain MR Images |
|
Pokala, Praveen Kumar | Indian Institute of Science, Bangalore |
Chemudupati, Satvik | Indian Institute of Science |
Seelamantula, Chandra Sekhar | Indian Institute of Science, Bangalore |
Keywords: Blind source separation & Dictionary learning, Magnetic resonance imaging (MRI), Brain
Abstract: We consider adaptive weighted minimax-concave (WMC) penalty as a generalization of the minimax-concave penalty (MCP) and vector MCP (VMCP). We develop a computationally efficient algorithm for sparse recovery considering the WMC penalty. Our algorithm in turn employs the fast iterative soft-thresholding algorithm (FISTA) but with the key difference that the threshold is adapted from one iteration to the next. The new sparse recovery algorithm when used for dictionary learning has a better representation capability as demonstrated by an application to magnetic resonance image denoising. The denoising performance turns out to be superior to the state-of-the-art techniques considering the standard performance metrics namely peak signal-to-noise ratio (PSNR) and structural similarity index metric (SSIM).
|
|
16:00-17:30, Paper TuPbPo-04.9 | Add to My Program |
Automatic Depression Detection Via Facial Expressions Using Multiple Instance Learning |
|
Wang, Yanfei | IBM |
Ma, Jie | IBM |
Hao, BIbo | IBM |
Hu, Pengwei | IBM |
Wang, Xiaoqian | Peking University |
Mei, Jing | IBM |
Li, Shaochun | IBM |
Keywords: Pattern recognition and classification, Computer-aided detection and diagnosis (CAD), Nerves
Abstract: Depression affects more than 300 million people around the world and is the leading cause of disability in USA for individuals ages from 15 to 44. The damage of it compares to most common diseases like cancer, diabetes, or heart disease according to the WHO report. However, people with depression symptoms sometimes do not receive proper treatment due to access barriers. In this paper, we propose a method that automatically detects depression using only landmarks of facial expressions, which are easy to collect with less privacy exposure. We deal with the coarse-grained labels i.e. one final label for the long-time series video clips, which is the common cases in applications, through the integration of feature manipulation and multiple instance learning. The effectiveness of our method is compared to other visual based methods, and our method even outperforms multi-modal methods that use multiple modalities.
|
|
TuPbPo-05 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Heart Imaging and Analysis II |
|
|
|
16:00-17:30, Paper TuPbPo-05.1 | Add to My Program |
Automatic Determination of the Fetal Cardiac Cycle in Ultrasound Using Spatio-Temporal Neural Networks |
|
Lok Hin, Lee | University of Oxford |
Noble, J Alison | University of Oxford |
Keywords: Fetus, Machine learning, Ultrasound
Abstract: The characterization of the fetal cardiac cycle is an important determination of fetal health and stress. The anomalous appearance of different anatomical structures during different phases of the heart cycle is a key indicator of fetal congenital hearth disease. However, locating the fetal heart using ultrasound is challenging, as the heart is small and indistinct. In this paper, we present a viewpoint agnostic solution that automatically characterizes the cardiac cycle in clinical ultrasound scans of the fetal heart. When estimating the state of the cardiac cycle, our model achieves a mean-squared error of 0.177 between the ground truth cardiac cycle and our prediction. We also show that our network is able to localize the heart, despite the lack of labels indicating the location of the heart in the training process.
|
|
16:00-17:30, Paper TuPbPo-05.2 | Add to My Program |
A Myocardial T1-Mapping Framework with Recurrent and U-Net Convolutional Neural Networks |
|
Jeelani, Haris | University of Virginia |
Yang, Yang | Icahn School of Medicine at Mount Sinai |
Zhou, Ruixi | University of Virginia |
Kramer, Christopher | University of Virginia Health System |
Salerno, Michael | University of Virginia |
Weller, Daniel | University of Virginia |
Keywords: Magnetic resonance imaging (MRI), Heart, Image enhancement/restoration(noise and artifact reduction)
Abstract: Noise and aliasing artifacts arise in various accelerated cardiac magnetic resonance (CMR) imaging applications. In accelerated myocardial T1-mapping, the traditional three-parameter based nonlinear regression may not provide accurate estimates due to sensitivity to noise. A deep neural network-based framework is proposed to address this issue. The DeepT1 framework consists of recurrent and U-net convolution networks to produce a single output map from the noisy and incomplete measurements. The results show that DeepT1 provides noise-robust estimates compared to the traditional pixel-wise three parameter fitting.
|
|
16:00-17:30, Paper TuPbPo-05.3 | Add to My Program |
Supervised Learning for Segmenting Open Boundaries in Medical Images |
|
Amer, Karim | Nile University |
Jacob, Athira | Siemens Healthineers |
Funka-Lea, Gareth | Siemens Corp. Research |
El-Zehiry, Noha | Siemens Healthcare |
Keywords: Ultrasound, Image segmentation, Heart
Abstract: Image segmentation is one of the most important building blocks in many medical imaging applications. Often, it is the first step in any artificial intelligence (AI) assisted diagnosis system. Most convolutional neural network image-to-image segmentation algorithms compute binary mask segmentation and extract the object boundary as the edge of the binary mask always leading to a closed boundary. In this paper, we present a novel image-to-image segmentation algorithm that learns open boundaries. The object delineation is directly learnt by training a U-Net like network on distance map representation of the boundary without any constraints on its shape or topology. We validate the proposed approach on the segmentation of the left atrium in intra-cardiac echocardiography images. For this application, it is important to produce segmentation only where a strong evidence of the anatomy exists. To our knowledge, this is the first work to train a U-Net on distance map ground truth representation for open boundary segmentation.
|
|
16:00-17:30, Paper TuPbPo-05.4 | Add to My Program |
A Context Based Deep Learning Approach for Unbalanced Medical Image Segmentation |
|
Murugesan, Balamurali | Indian Institute of Technology Madras |
Sarveswaran, Kaushik | Healthcare Technology Innovation Centre, IIT Madras Research Par |
S, Vijaya Raghavan | Healthcare Technology Innovation Centre |
M Shankaranarayana, Sharath | Indian Institute of Technology Madras |
Sirukarumbur Shanmugaram, Keerthi Ram | IIT Madras |
Sivaprakasam, Mohanasankar | Indian Institute of Technology Madras |
Keywords: Image segmentation, Heart, Magnetic resonance imaging (MRI)
Abstract: Automated medical image segmentation is an important step in many medical procedures. Recently, deep learning networks have been widely used for various medical image segmentation tasks, with U-Net and generative adversarial nets (GANs) being some of the commonly used ones. Foreground-background class imbalance is a common occurrence in medical images, and U-Net has difficulty in handling class imbalance because of its cross entropy (CE) objective function. Similarly, GAN also suffers from class imbalance because the discriminator looks at the entire image to classify it as real or fake. Since the discriminator is essentially a deep learning classifier, it is incapable of correctly identifying minor changes in small structures. To address these issues, we propose a novel context based CE loss function for U-Net, and a novel architecture Seg-GLGAN. The context based CE is a linear combination of CE obtained over the entire image and its region of interest (ROI). In Seg-GLGAN, we introduce a novel context discriminator to which the entire image and its ROI are fed as input, thus enforcing local context. We conduct extensive experiments using two challenging unbalanced datasets: PROMISE12 and ACDC. We observe that segmentation results obtained from our methods give better segmentation metrics as compared to various baseline methods.
|
|
16:00-17:30, Paper TuPbPo-05.5 | Add to My Program |
Improved Simultaneous Multi-Slice Imaging for Perfusion Cardiac MRI Using Outer Volume Suppression and Regularized Reconstruction |
|
Demirel, Omer Burak | University of Minnesota |
Weingärtner, Sebastian | Stanford University |
Moeller, Steen | University of Minnesota |
Akcakaya, Mehmet | University of Minnesota |
Keywords: Heart, Image reconstruction - analytical & iterative methods, Magnetic resonance imaging (MRI)
Abstract: Perfusion cardiac MRI (CMR) is a radiation-free and non-invasive imaging tool which has gained increasing interest for the diagnosis of coronary artery disease. However, resolution and coverage are limited in perfusion CMR due to the necessity of single snap-shot imaging during the first-pass of a contrast agent. Simultaneous multi-slice (SMS) imaging has the potential for high acceleration rates with minimal signal-to-noise ratio (SNR) loss. However, its utility in CMR has been limited to moderate acceleration factors due to residual leakage artifacts from the extra-cardiac tissue such as the chest and the back. Outer volume suppression (OVS) with leakage-blocking reconstruction has been used to enable higher acceleration rates in perfusion CMR, but suffers from higher noise amplification. In this study, we sought to augment OVS-SMS/MB imaging with a regularized leakage-blocking reconstruction algorithm to improve image quality. Results from highly-accelerated perfusion CMR show that the method improves upon SMS-SPIRiT in terms of leakage reduction and split slice (ss)-GRAPPA in terms of noise mitigation.
|
|
16:00-17:30, Paper TuPbPo-05.6 | Add to My Program |
Segmentation and Uncertainty Measures of Cardiac Tissues on Optical Coherence Tomography Via Convolutional Neural Networks |
|
Huang, Ziyi | Columbia University |
Gan, Yu | The University of Alabama |
Lye, Theresa | Columbia University |
Theagene, Darnel | Columbia University |
Chintapalli, Spandana | Columbia University |
Virdi, Simeran | Imperial College London |
Laine, Andrew F. | Columbia University |
Angelini, Elsa | Imperial NIHR BRC, Imperial College London |
Hendon, Christine | Columbia University |
Keywords: Optical coherence tomography, Image segmentation, Heart
Abstract: Segmentation of human cardiac tissue has a great potential to provide critical clinical guidance for Radiofrequency Ablation (RFA). Uncertainty in cardiac tissue segmentation is high because of the ambiguity of the subtle boundary and intra-/inter-physician variations. In this paper, we proposed a deep learning framework for Optical Coherence Tomography (OCT) cardiac segmentation with uncertainty measurement. Our proposed method employs additional dropout layers to assess the uncertainty of pixel-wise label prediction. In addition, we improve the segmentation performance by using focal loss to put more weights on mis-classified examples. Experimental results show that our method achieves high accuracy on pixel-wise label prediction. The feasibility of our method for uncertainty measurement is also demonstrated with excellent correspondence between uncertain regions within OCT images and heterogeneous regions within corresponding histology images.
|
|
16:00-17:30, Paper TuPbPo-05.7 | Add to My Program |
Segmentation of Five Components in Four Chamber View of Fetal Echocardiography |
|
Yang, Tingyang | Beihang University |
Han, Jiancheng | Beijing Anzhen Hospital, Capital Medical University |
Zhu, Haogang | Beihang University |
Li, Tiantian | Beihang University |
Liu, Xiaowei | Beijing Anzhen Hospital |
Gu, Xiaoyan | Beijing Anzhen Hospital, Capital Medical University |
Liu, Xiangyu | Beihang University |
An, Shan | Beihang University |
Yingying, Zhang | Beihang University |
Zhang, Ye | Beijing Anzhen Hospital |
He, Yihua | Beijing Anzhen Hospital Affiliated to Capital Medical University |
Keywords: Image segmentation, Fetus, Heart
Abstract: It is clinically significant to segment five components in four chamber view of fetal echocardiography, including four chambers and the descending aorta. This study completes the multi-disease segmentation and multi-class semantic segmentation of the five key components. After comparing the performance of DeeplabV3+ and U-net in the segmentation task, we choose the former as it provides accurate segmentation in other six disease groups as well as the normal group. With the data proportion balance strategy, the segmentation performance of the Ebstein’s anomaly group is improved significantly in spite of its small proportion. We empirically evaluate this strategy in terms of mean iou (MIOU), cross entropy loss (CE) and dice score (DS). The proportion of the atrial abnormality and ventricular abnormality in the entire data set is increased, so that the model learns more semantics. We simulate multiple scenes with uncertain attitudes of the fetus, which provides rich multi-scene semantic information and enhances the robustness of the model.
|
|
TuPbPo-06 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Optical Coherence Tomography II |
|
|
Chair: Rivenson, Yair | 1981 |
|
16:00-17:30, Paper TuPbPo-06.1 | Add to My Program |
Perceptual-Assisted Adversarial Adaptation for Choroid Segmentation in Optical Coherence Tomography |
|
Chai, Zhenjie | Shanghaitech University |
Zhou, Kang | ShanghaiTech University |
Yang, Jianlong | Cixi Institute of Biomedical Engineering, Chinese Academy of Sci |
Ma, Yuhui | University of Chinese Academy of Sciences, Cixi Institute of Bio |
Chen, Zhi | Fudan University Eye and ENT Hospital |
Gao, Shenghua | ShanghaiTech University |
Liu, Jiang | Southern University of Science and Technology |
Keywords: Image segmentation, Eye, Optical coherence tomography
Abstract: Accurate choroid segmentation in optical coherence tomography (OCT) image is vital because the choroid thickness is a major quantitative biomarker of many ocular diseases. Deep learning has shown its superiority in the segmentation of the choroid region but subjects to the performance degeneration caused by the domain discrepancies (e.g., noise level and distribution) among datasets obtained from the OCT devices of different manufacturers. In this paper, we present an unsupervised perceptual-assisted adversarial adaptation (PAAA) framework for efficiently segmenting the choroid area by narrowing the domain discrepancies between different domains. The adversarial adaptation module in the proposed framework encourages the prediction structure information of the target domain to be similar to that of the source domain. Besides, a perceptual loss is employed for matching their shape information (the curvatures of Bruch’s membrane and choroid-sclera interface) which can result in a fine boundary prediction. The results of quantitative experiments show that the proposed PAAA segmentation framework outperforms other state-of-the-art methods.
|
|
16:00-17:30, Paper TuPbPo-06.2 | Add to My Program |
Memory-Augmented Anomaly Generative Adversarial Network for Retinal Oct Images Screening |
|
Zhang, Chengfen | PingAn Technology (Shenzhen) Co., Ltd |
Wang, Yue | Ping an Technology (Shenzhen) Co |
Zhao, Xinyu | Department of Ophthalmology, Peking Union Medical College Hospit |
Guo, Yan | PingAn Technology (Shenzhen) Co., Ltd., Shenzhen, China |
Xie, Guotong | PingAn Tech |
Lv, Chuanfeng | PingAn Tech |
Lv, Bin | PingAn Technology (Shenzhen) Co., Ltd |
Keywords: Optical coherence tomography, Classification, Eye
Abstract: Optical coherence tomography (OCT) plays an important role in retinal disease screening. Traditional classification-based screening methods require complicated annotation works. Due to the difficulty of collecting abnormal samples, some anomaly detection methods have been applied to screen retinal lesions only based on normal samples. However, most existing anomaly detection methods are time consuming and easily misjudging abnormal OCT images with implicit lesions like small drusen. To solve these problems, we propose a memory-augmented anomaly generative adversarial network (MA-GAN) for retinal OCT screening. Within the generator, we establish a memory module to enhance the detail expressing abilities of typical OCT normal patterns. Meanwhile, the discriminator of MA-GAN is decomposed orthogonally so that it has the encoding ability simultaneously. As a result, the abnormal image can be screened by the greater difference in the distribution of pixels and features between the original image and its reconstructed image. The model trained with 13000 normal OCT images reaches 0.875 AUC on the test set of 2000 normal images and 1000 anomalous images. And the inference time only takes 35 milliseconds for each image. Compared to other anomaly detection methods, our MA-GAN has the advantages in model accuracy and computation time for retinal OCT screening.
|
|
16:00-17:30, Paper TuPbPo-06.3 | Add to My Program |
Full Field Optical Coherence Tomography Image Denoising Using Deep Learning with Spatial Compounding |
|
Chen, I-Ling | National Taiwan University |
Ho, Tuan-Shu | National Taiwan University |
Lu, Chih-Wei | Apollo Medical Optics |
Keywords: Optical coherence tomography, Image enhancement/restoration(noise and artifact reduction), Skin
Abstract: In recent years, deep learning is widely and successfully applied in the medical images which have been established an abundant database in clinical practice. OCT is a relatively new imaging technique and worth in-depth exploration in the deep learning field, however, it is still in an early stage where medical doctors are learning to interpret its images. For shortening the learning curve, this paper used a deep convolutional neural network on a high-resolution full-field OCT system to enhance features in images. By combining with the spatial compounding technique, a noise map prediction method can be employed to discriminate noises from signals and thus increase the image quality. For 100 testing samples, the average of PSNR and SSIM have improved from 20.7 and 0.43 to 26.55 and 0.68 after denoising by the proposed denoising model. Moreover, some important features would be more distinct to support diagnosis in clinical data.
|
|
16:00-17:30, Paper TuPbPo-06.4 | Add to My Program |
High-Speed Markerless Tissue Motion Tracking Using Volumetric Optical Coherence Tomography Images |
|
Schlüter, Matthias | Hamburg University of Technology |
Glandorf, Lukas | Hamburg University of Technology |
Sprenger, Johanna | Hamburg University of Technology |
Gromniak, Martin | Hamburg University of Technology |
Neidhardt, Maximilian | Hamburg University of Technology |
Saathoff, Thore | Hamburg University of Technology |
Schlaefer, Alexander | Hamburg University of Technology |
Keywords: Motion compensation and analysis, Optical coherence tomography, Tissue
Abstract: Modern optical coherence tomography (OCT) devices provide volumetric images with micrometer-scale spatial resolution and a temporal resolution beyond video rate. In this work, we analyze an OCT-based prototypical tracking system which processes 831 volumes per second, estimates translational motion, and automatically adjusts the field-of-view, which has a size of few millimeters, to follow a sample even along larger distances. The adjustment is realized by two galvo mirrors and a motorized reference arm, such that no mechanical movement of the scanning setup is necessary. Without requiring a marker or any other knowledge about the sample, we demonstrate that reliable tracking of velocities up to 25 mm/s is possible with mean tracking errors in the order of 0.25 mm. Further, we report successful tracking of lateral velocities up to 70 mm/s with errors below 0.3 mm.
|
|
16:00-17:30, Paper TuPbPo-06.5 | Add to My Program |
Weakly Supervised Vulnerable Plaques Detection by Ivoct Image |
|
Shi, Peiwen | Xi'an Jiaotong University |
Xin, Jingmin | Xi'an Jiaotong University |
Zheng, Nanning | Xi'an Jiaotong University |
Keywords: Computer-aided detection and diagnosis (CAD), Tissue, Optical coherence tomography
Abstract: Vulnerable plaque is a major factor leading to the onset of acute coronary syndrome (ACS), and accordingly, the detection of vulnerable plaques (VPs) could guide cardiologists to provide appropriate surgical treatments before the occurrence of an event. In general, hundreds of images are acquired for each patient during surgery. Hence a fast and accurate automatic detection algorithm is needed. However, VPs’ detection requires extensive annotation of lesion’s boundary by an expert practitioner, unlike diagnoses. Therefore in this paper, a multiple instances learning-based method is proposed to locate VPs with the image-level labels only. In the proposed method, the clip proposal module, the feature extraction module, and the detection module are integrated to recognize VPs and detect the lesion area. Finally, experiments are performed on the 2017 IVOCT dataset to examine the task of weakly supervised detection of VPs. Although the bounding box of VPs is not used, the proposed method yields comparable performance with supervised learning methods.
|
|
16:00-17:30, Paper TuPbPo-06.6 | Add to My Program |
Automated Quantification of Macular Vasculature Changes from OCTA Images of Hematologic Patients |
|
Engberg, Astrid | Technical University of Denmark |
Amini, Abdullah | University of Copenhagen |
Willerslev, Anne | Rigshospitalet-Glostrup |
Larsen, Michael | University of Copenhagen |
Sander, Birgit | Rigshospitalet-Glostrup |
Kessel, Line | University of Copenhagen |
Dahl, Anders Bjorholm | Technical University of Denmark, Department of Applied Mathemati |
Dahl, Vedrana Andersen | Technical University of Denmark |
Keywords: Vessels, Quantification and estimation, Optical coherence tomography
Abstract: Abnormal blood compositions can lead to abnormal blood flow which can influence the macular vasculature. Optical coherence tomography angiography (OCTA) makes it possible to study the macular vasculature and potential vascular abnormalities induced by hematological disorders. Here, we investigate vascular changes in control subjects and in hematologic patients before and after treatment. Since these changes are small, they are difficult to notice in the OCTA images. To quantify vascular changes, we propose a method for combined capillary registration, dictionary-based segmentation and local density estimation. Using this method, we investigate three patients and five controls, and our results show that we can detect small changes in the vasculature in patients with large changes in blood composition.
|
|
TuPbPo-07 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Skin Imaging & Analysis |
|
|
Co-Chair: Witte, Russell | University of Arizona |
|
16:00-17:30, Paper TuPbPo-07.1 | Add to My Program |
Automating Vitiligo Skin Lesion Segmentation Using Convolutional Neural Networks |
|
Low, Makena | Stanford University |
Huang, Victor | University of California, Davis |
Raina, Priyanka | Stanford University |
Keywords: Skin, Machine learning, Other-modality
Abstract: The measurement of several skin conditions' progression and severity relies on the accurate segmentation (border detection) of lesioned skin images. One such condition is vitiligo. Existing methods for vitiligo image segmentation require manual intervention, which is time-inefficient, labor-intensive, and irreproducible between physicians. We introduce a convolutional neural network (CNN) that quickly and robustly performs such segmentations without manual intervention. We use the U-Net with a modified contracting path to generate an initial segmentation of the lesion. Then, we run the segmentation through the watershed algorithm using high-confidence pixels as "seeds." We train the network on 247 images with a variety of lesion sizes, complexities, and anatomical sites. Our network noticeably outperforms the state-of-the-art U-Net -- scoring a Jaccard Index (JI) of 73.6% (compared to 36.7%). Segmentation occurs in a few seconds, which is a substantial improvement from the previously proposed semi-autonomous watershed approach (2-29 minutes per image).
|
|
16:00-17:30, Paper TuPbPo-07.2 | Add to My Program |
Fusing Metadata and Dermoscopy Images for Skin Disease Diagnosis |
|
Li, Weipeng | Sun Yat-Sen University |
Zhuang, Jiaxin | Sun Yat-Sen University |
Wang, Ruixuan | Sun Yat-Sen University |
Zhang, JianGuo | Department of Computer Science and Engineering, Southern Univers |
Zheng, Wei-Shi | School of Data and Computer Science, Sun Yat-Sen University |
Keywords: Skin, Classification, Pattern recognition and classification
Abstract: To date, it is still difficult and challenging to automatically classify dermoscopy images. Although the state-of-the-art convolutional networks were applied to solve the classification problem and achieved overall decent prediction results, there is still room for performance improvement, especially for rare disease categories. Considering that human dermatologists often make use of other information (e.g., body locations of skin lesions) to help diagnose, we propose using both dermoscopy images and non-image metadata for intelligent diagnosis of skin diseases. Specifically, the metadata information is innovatively applied to control the importance of different types of visual information during diagnosis. Comprehensive experiments with various deep learning model architectures demonstrated the superior performance of the proposed fusion approach especially for relatively rare diseases. All our codes will be made publicly available.
|
|
16:00-17:30, Paper TuPbPo-07.3 | Add to My Program |
Kappa Loss for Skin Lesion Segmentation in Fully Convolutional Network |
|
Zhang, Jing | INSA Rouen |
Petitjean, Caroline | Université De Rouen |
Ainouz, Samia | Institut National Des Sciences Appliquées De Rouen | INSA Rouen |
Keywords: Optoacoustic/photoacoustic imaging, Skin, Machine learning
Abstract: Skin melanoma represents a major health issue. Today, diagnosis and follow-up maybe performed thanks to computer-aided diagnosis tool, to help dermatologists segment and quantitatively describe the image content. In particular, deep convolutional neural networks (CNN) have lately been become the state-of-the-art in medical image segmentation. The loss function plays an important role in CNN in the process of backpropagation. In this work, we propose a metric-inspired loss function, based on the Kappa index. Unlike the Dice loss, the Kappa loss takes into account all the pixels in the image, including the true negative, which we believe can improve the accuracy of the evaluation process between prediction and ground truth. We demonstrate the differentiability of the Kappa loss and present some results on six public datasets of skin lesion. Experiments have shown promising results in skin lesion segmentation.
|
|
16:00-17:30, Paper TuPbPo-07.4 | Add to My Program |
A Multi-Task Self-Supervised Learning Framework for Scopy Images |
|
Li, Yuexiang | Tencent |
Chen, Jiawei | Tencent |
Zheng, Yefeng | Tencent Youtu Lab |
Keywords: Machine learning, Cervix, Skin
Abstract: The training of deep learning models requires large amount of training data. However, as the annotations of medical data are difficult to acquire, the quantity of annotated medical images is often not enough to well train the deep learning networks. In this paper, we propose a novel multi-task self-supervised learning framework, namely ColorMe, for the scopy images, which deeply exploits the rich information embedded in raw data and looses the demand of training data. The approach pre-trains neural networks on multiple proxy tasks, i.e., green to red/blue colorization and color distribution estimation, which are defined in terms of the prior-knowledge of scopy images. Compared to the train-from-scratch strategy, fine-tuning from these pre-trained networks leads to a better accuracy on various tasks -- cervix type classification and skin lesion segmentation.
|
|
16:00-17:30, Paper TuPbPo-07.5 | Add to My Program |
Complementary Network with Adaptive Receptive Fields for Melanoma Segmentation |
|
Guo, Xiaoqing | City University of Hong Kong |
Chen, Zhen | City University of Hong Kong |
Yuan, Yixuan | City University of Hong Kong |
Keywords: Skin, Image segmentation
Abstract: Automatic melanoma segmentation in dermoscopic images is essential in computer-aided diagnosis of skin cancer. Existing methods may suffer from the hole and shrink problems with limited segmentation performance. To tackle these issues, we propose a novel complementary network with adaptive receptive filed learning. Instead of regarding the segmentation task independently, we introduce a foreground network to detect melanoma lesions and a background network to mask non-melanoma regions. Moreover, we propose adaptive atrous convolution (AAC) and knowledge aggregation module (KAM) to fill holes and alleviate the shrink problems. AAC allows us to explicitly control the receptive field at multiple scales. KAM convolves shallow feature maps by dilated convolutions with adaptive receptive fields, which are adjusted according to deep feature maps. In addition, A novel mutual loss is proposed to utilize the dependency between the foreground and background networks, thereby enabling the reciprocally influence within these two networks. Consequently, this mutual training strategy enables the semi-supervised learning and improve the boundary-sensitivity. Training with Skin Imaging Collaboration (ISIC) 2018 skin lesion segmentation dataset, our method achieves a dice coefficient of 86.4% and shows better performance compared with state-of-the-art melanoma segmentation methods.
|
|
16:00-17:30, Paper TuPbPo-07.6 | Add to My Program |
Leveraging Adaptive Color Augmentation in Convolutional Neural Networks for Deep Skin Lesion Segmentation |
|
Saha, Anindo | Universitat De Girona |
Prasad, Prem | Universitat De Girona |
Thabit, Abdullah | Universitat De Girona |
Keywords: Skin, Image segmentation, Machine learning
Abstract: Fully automatic detection of skin lesions in dermatoscopic images can facilitate early diagnosis and repression of malignant melanoma and non-melanoma skin cancer. Although convolutional neural networks are a powerful solution, they are limited by the illumination spectrum of annotated dermatoscopic screening images, where color is an important discriminative feature. In this paper, we propose an adaptive color augmentation technique to amplify data expression and model performance, while regulating color difference and saturation to minimize the risks of using synthetic data. Through deep visualization, we qualitatively identify and verify the semantic structural features learned by the network for discriminating skin lesions against normal skin tissue. The overall system achieves a Dice Ratio of 0.891 with 0.943 sensitivity and 0.932 specificity on the ISIC 2018 Testing Set for segmentation.
|
|
16:00-17:30, Paper TuPbPo-07.7 | Add to My Program |
Deep Disentangled Representation Learning of PET Images for Lymphoma Outcome Prediction |
|
Guo, Yu | Tianjin University |
Decazes, Pierre | University of Medicine, Rouen; Department of Nuclear Medicine, H |
Becker, Stéphanie | Department of Nuclear Medicine, Henri Becquerel Cancer Center |
Li, Hua | Washington University School of Medicine |
Ruan, Su | Universite De Rouen |
Keywords: Radiation therapy, planing and treatment, Classification, Nuclear imaging (e.g. PET, SPECT)
Abstract: Image feature extraction based on deep disentangled representation learning of PET images is proposed for the prediction of lymphoma treatment response. Our method encodes PET images as spatial representations and modality representations by performing supervised tumor segmentation and image reconstruction. In this way, the whole image features (global features) as well as tumor region features (local features) can be extracted without the labor-intensive tumor segmentation and feature calculation procedure. The learned global and local image features are then joined with several prognostic factors evaluated by physicians based on clinical information, and used as input of a SVM classifier for predicting outcome results of lymphoma patients. In this study, 186 lymphoma patient data were included for training and testing the proposed model. The proposed method was compared with the traditional straightforward feature extraction method. The better prediction results of the proposed method also show its efficiency for prognostic prediction related feature extraction in PET images.
|
|
TuPbPo-08 Poster Session, Oakdale Foyer Coral Foyer |
Add to My Program |
Abstract Posters: Machine Learning Methods |
|
|
Chair: Yoo, Jaejun | KAIST |
|
16:00-17:30, Paper TuPbPo-08.1 | Add to My Program |
Lightweight U-Net for High-Resolution Breast Imaging |
|
Tardy, Mickael | LS2N, Ecole Centrale De Nantes, Hera-MI SAS |
Mateus, Diana | Centrale Nantes |
Keywords: Breast, Image segmentation, Machine learning
Abstract: We study the fully convolutional neural networks in the
context of malignancy detection for breast cancer
screening. We solve a supervised segmentation task looking
for an acceptable compromise between the precision of the
network and the computational complexity.
|
|
16:00-17:30, Paper TuPbPo-08.2 | Add to My Program |
Machine Learning Algorithm for Prostate Segmentation in Transrectal Ultrasound |
|
Garikipati, Anurag | Eigen Health Services LLC |
Venkataraman, Rajesh | Eigen Health Services LLC |
Keywords: Image segmentation, Prostate, Machine learning
Abstract: Ultrasound segmentation of the prostate is a key step for elastic registration (fusion) of magnetic resonance images (MRI) and ultrasound (US) images used for 3D targeted biopsies. To provide more robust segmentation, we propose a machine learning model for automatic segmentation in transrectal US images.
|
|
16:00-17:30, Paper TuPbPo-08.3 | Add to My Program |
Generalization Power of Deep Learning Approaches: Learning from the Output of Classical Image Processing Methods |
|
ALOm, Md | University of Dayton |
Aspiras, , Theus | University of Dayton |
Oprea-Ilies, Gabriela | Emory University |
Bowen, Tj | DeepLens |
Asar, Vijayan K. | University of Dayton |
Keywords: Image segmentation, Machine learning, Computational Imaging
Abstract: Due to the scarcity in the availability of large amount of
labeled samples, training a deep learning model is becoming
a very challenging task in computational pathology. In this
paper, we show a solution for automatically generating
labeled samples using classical image processing methods
and exploring the generalization power of a DL approach for
region segmentation. A Recurrent Residual U-Net (R2U-Net)
model is trained on the labeled samples generated by
employing Blue Ratio (BR) estimate along with an adaptive
thresholding approach and verified by an expert
pathologist. Testing of the system is performed on a set of
completely new samples collected from a different Whole
Slide Image (WSI). The R2U-Net shows significantly better
performance compared to the BR with adaptive thresholding
method alone, which proves the generalizability and
robustness of DL methods for segmentation tasks in
computational pathology.
|
|
16:00-17:30, Paper TuPbPo-08.4 | Add to My Program |
Iterative Deep Learning Based Segmentation on Cyclic Immunofluorescence Imaging by Using Recursive Refinement |
|
Ternes, Luke | Oregon Health and Science University |
Chang, Young Hwan | Oregon Health and Science University |
Gray, Joe | Oregon Health & Science University |
Thibault, Guillaume | Oregon Health & Science University |
Keywords: Image segmentation, Machine learning
Abstract: Most deep learning segmentation architectures require a
large amount of training data, comprised of thousands of
manually annotated images. Despite being time consuming to
create, manual annotations are more accurate than
algorithmic segmentations and, therefore, result in better
training. Here we describe a strategy that utilizes
iterative learning and ground truth refinement improve
segmentations without using manual annotations. Alternating
Cyclic Immunofluorescent (Cyclic-IF) stains and averaging
prediction masks at each iteration are implemented to
reduce the propagation of errors through the models.
Segmentation performed using this strategy reaches the
accuracy of manual segmentation after a few iterations.
Using this strategy can reduce the number of manual
annotations needed to produce accurate segmentation masks.
|
|
16:00-17:30, Paper TuPbPo-08.5 | Add to My Program |
Detecting Intracranial Aneurysm Rupture from Triangulated Vessel Surfaces Using a Novel GraphNet Approach |
|
Ma, Ze | Union Strong Technology Beijing Co |
Song, Ling | Union Strong Technology Beijing Co |
Feng, Xue | The University of Virginia |
Yang, Guangming | Union Strong Technology Beijing Co |
Zhu, Wei | Beijing Tiantan Hospital |
Liu, Jian | Beijing Tiantan Hospital |
Zhang, Yisen | Beijing Tiantan Hospital |
Yang, Xinjian | Beijing Tiantan Hospital |
Yin, Yin | Union Strong Technology Beijing Co |
Keywords: Machine learning, Angiographic imaging, Brain
Abstract: Intracranial aneurysm (IA) is a life-threatening blood spot in human's brain if it ruptures and causes cerebral hemorrhage. It is challenging to detect whether an IA has ruptured from medical images. In this paper, we propose a novel graph based neural network named GraphNet to detect IA rupture from 3D surface data. GraphNet is based on graph convolution network (GCN) and is designed for graph-level classification and node-level segmentation. The network uses GCN blocks to extract surface local features and pools to global features. 1250 patient data including 385 ruptured and 865 unruptured IAs were collected from clinic for experiments. The performance on randomly selected 234 test patient data was reported. The experiment with the proposed GraphNet achieved accuracy of 0.82, area-under-curve (AUC) of receiver operating characteristic (ROC) curve 0.82 in the classification task, significantly outperforming the baseline approach without using graph based networks. The segmentation output of the model achieved mean graph-node-based dice coefficient (DSC) score 0.88.
|
|
16:00-17:30, Paper TuPbPo-08.6 | Add to My Program |
Identification of Lung Tissue Patterns in Subjects with Chronic Obstructive Pulmonary Disease Using a Convolutional Deep Learning Model |
|
Li, Frank | University of Iowa |
Lin, Ching-Long | University of Iowa |
|
|
16:00-17:30, Paper TuPbPo-08.8 | Add to My Program |
Approximating Spherical Mean Technique for Single Shell Dw-Mri Using Deep Learning |
|
Nath, Vishwesh | Vanderbilt University |
Pathak, Sudhir | University of Pittsburgh |
Parvathaneni, Prasanna | National Institutes of Health |
Schilling, Kurt G. | Vanderbilt University Institute of Imaging Science |
Panesar, Sandip | Stanford University |
Fernandez-Miranda, Juan | Stanford University |
Schneider, Walter | University of Pittsburgh |
Landman, Bennett | Vanderbilt University |
Keywords: Diffusion weighted imaging, Brain, Machine learning
Abstract: Diffusion-weighted magnetic resonance imaging (DW-MRI) is a
unique tool for non-invasive assessment of tissue
microstructure. Estimates of quantitative tissue properties
are gaining traction for improving understanding of
neuro-degenerative disorders. A plethora of methods that
estimate microstructure have been proposed, albeit
predominantly using high quality DW-MRI data (high sampling
of gradient directions, multiple diffusivity values,
varying diffusivity values >1000 s/mm2). An impediment to
wider application of these methods is the limitation of
acquisition of high-quality DW-MRI, which is especially
burdensome in a clinical setting. In this work we propose
to use deep learning methods to leverage recovery of
micro-structural estimates from DW-MRI acquisitions than
can be acquired on clinical scanner with low b-value (1000
s/mm2). We show that the recovery of quantitative
micro-structural maps derived from spherical mean technique
(SMT) is possible using deep learned MT-CSD estimates on
single b-value of ~1000 s/mm2. For this study we utilized a
total of 15 subjects from human connectome project (5
training, 2 validation, 5 testing). The results are
evaluated in terms or RMSE of SMT measures predicted vs
gold standard “truth” estimates using all shells. Overall
RMSE of intra-cellular volume fraction, axial diffusivity,
transverse diffusivity for single voxel and patch-based
approaches are: 0.0893 vs 0.0768, 0.0004 vs 0.0003 mm2/s,
0.0003 vs 0.0001 mm2/s, relatively 7-10% error.
|
|
16:00-17:30, Paper TuPbPo-08.9 | Add to My Program |
Integrating Learned Data and Image Models through Consensus Equilibrium for Model-Based Image Reconstruction |
|
Ghani, Muhammad Usman | Boston University |
Karl, Clem | Boston University |
Keywords: Computational Imaging, Image reconstruction - analytical & iterative methods, Machine learning
Abstract: Model-based image reconstruction (MBIR) approaches provide
a principled way to combine sensor and image prior models
to solve imaging inverse problems. Plug-and-play MBIR
(PnP-MBIR) approaches use variable splitting and allow the
use of rich image priors. This work extends this idea to
data-domain modeling and presents a new MBIR framework that
enables integration of data-domain and image-domain prior
models and allows high-quality reconstructions even for
imperfect data imaging problems such as limited-angle CT,
accelerated MRI, or diverging-wave Ultrasound imaging. In
this work, we use this newly developed framework to explore
the potential of learned data and image models for
biomedical applications of tomographic imaging problems.
|
|
16:00-17:30, Paper TuPbPo-08.10 | Add to My Program |
Journal Paper: Multi-Objective Based Radiomic Feature Selection for Lesion Malignancy Classification |
|
Zhou, Zhiguo | University of Central Missouri |
Keywords: Computer-aided detection and diagnosis (CAD), Machine learning, Pattern recognition and classification
Abstract: Accurately classifying the malignancy of lesions detected in a screening scan is critical for reducing false positives. Radiomics has shown promising result in nodule classification. Since not all the radiomic features play a positive role in building the predictive model, and some of them may be redundant or even reduce the model performance, selecting an optimal feature subset is critical. We aim to develop a new multi-objective based feature selection (MO-FS) algorithm for radiomics-based lesion malignancy classification.
|
|
16:00-17:30, Paper TuPbPo-08.11 | Add to My Program |
Predicting Treatment Outcome after Immunotherapy through Automated Multi-Objective Delta-Radiomics Model in Melanoma |
|
Zhou, Zhiguo | University of Central Missouri |
Keywords: Computer-aided detection and diagnosis (CAD), Data Mining, Machine learning
Abstract: Immunotherapy drugs which is led by immunocheckpoint inhibitors can increase the patient survival rate significantly and reduce the recurrence risk greatly. However, it is very difficult to predict the treatment outcome after immunotherapy. Recently, Delta-radiomic strategy has achieve great success in treatment outcome prediction. In this study, a new automated multi-objective delta-radiomics model (Auto-MODR) was developed for predicting treatment outcome after immunotherapy. The experimental results demonstrated that when combining pre-treatment radiomic features with delta-radiomic features, Auto-MODR can obtain best performance.
|
|
16:00-17:30, Paper TuPbPo-08.12 | Add to My Program |
Mask Uncertainty Regularization to Improve Machine Learning-Based Medical Image Segmentation |
|
Groza, Vladimir | Median Technologies |
Huet, Benoit | Median Technologies |
Boujemaa, Nozha | Median Technologies |
Keywords: Machine learning, Image segmentation, Computed tomography (CT)
Abstract: Segmentation of the different structures on CT and MRI
scans is still challenging problem which requires very
accurate and confident ground truth (GT) segmentation and
strong automated solutions. This work present an approach to naturally adjust the
training process by smoothing the borders of the
segmentation mask in the band of several pixels. The
proposed method can be considered as either regularization
or data pre-processing step to compensate uncertainty of
the GT. This method can be used for any organs segmentation problem
both binary and multiclass. As one of the applications we
report results in terms of Dice, Precision and Recall
scores of the numerical experiments for the binary
segmentation of the spleen on abdominal CT scans. Obtained results demonstrate stable and continuous
improvement from very strong baseline in target Dice metric
up to 3.8% for one fold and 1% for the mean averaged 5-fold
ensemble, achieving Dice of 0.9486 and Recall 0.9535.
|
|
|