Embedded Files
Aliasghar Mortazi, Naji Khosravan, Drew A. Torigian, Sila Kurugol, Ulas Bagci
Machine Learning in Medical Imaging 2019 (pdf)
Abstract: The performance of the state-of-the-art image segmentation methods heavily relies on the high-quality annotations, which are not easily affordable, particularly for medical data. To alleviate this limitation, in this study, we propose a weakly supervised image segmentation method based on a deep geodesic prior. We hypothesize that integration of this prior information can reduce the adverse effects of weak labels in segmentation accuracy. Our proposed algorithm is based on a prior information, extracted from an auto-encoder, trained to map objects geodesic maps to their corresponding binary maps. The obtained information is then used as an extra term in the loss function of the segmentor. In order to show efficacy of the proposed strategy, we have experimented segmentation of cardiac substructures with clean and two levels of noisy labels (L1, L2). Our experiments showed that the proposed algorithm boosted the performance of baseline deep learning-based segmentation for both clean and noisy labels by 4.4%, 4.6%(L1), and 6.3%(L2) in dice score, respectively. We also showed that the proposed method was more robust in the presence of high-level noise due to the existence of shape priors.
Naji Khosravan, Aliasghar Mortazi, Michael Wallace, Ulas Bagci
International Conference on Medical Image Computing and Computer-Assisted Intervention 2019 (pdf)
Abstract: Adversarial learning has been proven to be effective for capturing long-range and high-level label consistencies in semantic segmentation. Unique to medical imaging, capturing 3D semantics in an effective yet computationally efficient way remains an open problem. In this study, we address this computational burden by proposing a novel projective adversarial network, called PAN, which incorporates high-level 3D information through 2D projections. Furthermore, we introduce an attention module into our framework that helps for a selective integration of global information directly from our segmentor to our adversarial network. For the clinical application we chose pancreas segmentation from CT scans. Our proposed framework achieved state-of-the-art performance without adding to the complexity of the segmentor.
Xiahai Zhuang, Lei Li, Christian Payer, Darko Stern, Martin Urschler, Mattias P. Heinrich, Julien Oster, Chunliang Wang, Orjan Smedby, Cheng Bian, Xin Yang, Pheng-Ann Heng, Aliasghar Mortazi, Ulas Bagci, Guanyu Yang, Chenchen Sun, Gaetan Galisot, Jean-Yves Ramel, Thierry Brouard, Qianqian Tong, Weixin Si, Xiangyun Liao, Guodong Zeng, Zenglin Shi, Guoyan Zheng, Chengjia Wang, Tom MacGillivray, David Newby, Kawal Rhode, Sebastien Ourselin, Raad Mohiaddin, Jennifer Keegan, David Firmin, Guang Yang
Medical Image Analysis 2019 (pdf)
Abstract: Knowledge of whole heart anatomy is a prerequisite for many clinical applications. Whole heart segmentation (WHS), which delineates substructures of the heart, can be very valuable for modeling and analysis of the anatomy and functions of the heart. However, automating this segmentation can be arduous due to the large variation of the heart shape, and different image qualities of the clinical data. To achieve this goal, a set of training data is generally needed for constructing priors or for training. In addition, it is difficult to perform comparisons between different methods, largely due to differences in the datasets and evaluation metrics used. This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017. The challenge provides 120 three-dimensional cardiac images covering the whole heart, including 60 CT and 60 MRI volumes, all acquired in clinical environments with manual delineation. Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelve groups, have been evaluated. The results show that many of the deep learning (DL) based methods achieved high accuracy, even though the number of training datasets was limited. A number of them also reported poor results in the blinded evaluation, probably due to overfitting in their training. The conventional algorithms, mainly based on multi-atlas segmentation, demonstrated robust and stable performance, even though the accuracy is not as good as the best DL method in CT segmentation. The challenge, including the provision of the annotated training data and the blinded evaluation for submitted algorithms on the test data, continues as an ongoing benchmarking resource via its homepage (\url{this http URL}).
Aliasghar Mortazi and Ulas Bagci
Machine Learning in Medical Imaging 2018 (pdf)
Abstract: Deep neural network architectures have traditionally been designed and explored with human expertise in a long-lasting trial-and-error process. This process requires huge amount of time, expertise, and resources. To address this tedious problem, we propose a novel algorithm to optimally find hyperparameters of a deep network architecture automatically. We specifically focus on designing neural architectures for medical image segmentation task. Our proposed method is based on a policy gradient reinforcement learning for which the reward function is assigned a segmentation evaluation utility (i.e., dice index). We show the efficacy of the proposed method with its low computational cost in comparison with the state-of-the-art medical image segmentation networks. We also present a new architecture design, a densely connected encoder-decoder CNN, as a strong baseline architecture to apply the proposed hyperparameter search algorithm. We apply the proposed algorithm to each layer of the baseline architectures. As an application, we train the proposed system on cine cardiac MR images from Automated Cardiac Diagnosis Challenge (ACDC) MICCAI 2017. Starting from a baseline segmentation architecture, the resulting network architecture obtains the state-of-the-art results in accuracy without performing any trial-and-error based architecture design approaches or close supervision of the hyperparameters changes.
Jeremy Burt, Neslisah Torosdagli, Naji Khosravan, Harish RaviPrakash, Aliasghar Mortazi, Clark Rogers, Fiona Tissavirasingham, Sarfaraz Hussein, Ulas Bagci
The British Journal of Radiology 2018 (pdf)
Abstract: Deep Learning has demonstrated tremendous revolutionary changes in the computing industry and its effects in radiology and imaging sciences have begun to dramatically change screening paradigms. Specifically, these advances have influenced the development of computer aided detection and diagnosis (CAD) systems. These technologies have long been thought of as "second-opinion" tools for radiologists and clinicians. However, with significant improvements in deep neural networks, the diagnostic capabilities of learning algorithms are approaching levels of human expertise (radiologists, clinicians, etc.), shifting the CAD paradigm from a "second opinion" tool to a more collaborative utility. This paper reviews the recently developed CAD systems based on deep learning technologies for breast cancer diagnosis, explains their superiorities with respect to previously established systems, defines the methodologies behind the improved achievements including algorithmic developments, and describes remaining challenges in breast cancer screening and diagnosis. We also discuss possible future directions for new CAD models that continue to change as artificial intelligence algorithms evolve.
International Conference on Medical Image Computing and Computer-Assisted Intervention 2017 (pdf, The code will be available soon)
Abstract: Anatomical and biophysical modeling of left atrium (LA) and proximal pulmonary veins (PPVs) is important for clinical management of several cardiac diseases. Magnetic resonance imaging (MRI) allows qualitative assessment of LA and PPVs through visualization. However, there is a strong need for an advanced image segmentation method to be applied to cardiac MRI for quantitative analysis of LA and PPVs. In this study, we address this unmet clinical need by exploring a new deep learning-based segmentation strategy for quantification of LA and PPVs with high accuracy and heightened efficiency. Our approach is based on a multi-view convolutional neural network (CNN) with an adaptive fusion strategy and a new loss function that allows fast and more accurate convergence of the backpropagation based optimization. After training our network from scratch by using more than 60K 2D MRI images (slices), we have evaluated our segmentation strategy to the STACOM 2013 cardiac segmentation challenge benchmark. Qualitative and quantitative evaluations, obtained from the segmentation challenge, indicate that the proposed method achieved the state-of-the-art sensitivity (90%), specificity (99%), precision (94%), and efficiency levels (10 seconds in GPU, and 7.5 minutes in CPU)
International Workshop on Statistical Atlases and Computational Models of the Heart 2017 (pdf, The code will be available soon)
Abstract: Non-invasive detection of cardiovascular disorders from radiology scans requires quantitative image analysis of the heart and its substructures. There are well-established measurements that radiologists use for diseases assessment such as ejection fraction, volume of four chambers, and myocardium mass. These measurements are derived as outcomes of precise segmentation of the heart and its substructures. The aim of this paper is to provide such measurements through an accurate image segmentation algorithm that automatically delineates seven substructures of the heart from MRI and/or CT scans. Our proposed method is based on multi-planar deep convolutional neural networks (CNN) with an adaptive fusion strategy where we automatically utilize complementary information from different planes of the 3D scans for improved delineations. For CT and MRI, we have separately designed three CNNs (the same architectural configuration) for three planes, and have trained the networks from scratch for voxel-wise labeling for the following cardiac structures: myocardium of left ventricle (Myo), left atrium (LA), left ventricle (LV), right atrium (RA), right ventricle (RV), ascending aorta (Ao), and main pulmonary artery (PA). We have evaluated the proposed method with 4-fold-cross-validation on the multi-modality whole heart segmentation challenge (MM-WHS 2017) dataset. The precision and dice index of 0.93 and 0.90, and 0.87 and 0.85 were achieved for CT and MR images, respectively. While a CT volume was segmented about 50 seconds, an MRI scan was segmented around 17 seconds with the GPUs/CUDA implementation.
Deep Learning for Cardiac MRI: Automatically Segmenting Left Atrium Expert Human Level Performance,
Deep Learning for Cardiac MRI: Automatically Segmenting Left Atrium Expert Human Level Performance,
Annual Meeting of the Radiological Society of North America, 2017 (Oral presentation, The presentation will be available soon)
Machine Learning for Cardiac MRI: Automated Mapping of Left Atrium and Pulmonary Veins with Human Level Performance
Machine Learning for Cardiac MRI: Automated Mapping of Left Atrium and Pulmonary Veins with Human Level Performance
Accepted as one of the American Heart Association(AHA) CVRI Young Investigator Award finalists at North American Society for Cardiac Imaging 45th Annual Meeting 2017 (Oral presentation, The presentation will be available soon)
Sarfaraz Hussein, Aliasghar Mortazi, Harish Raviprakas, Jeremy Burt, and Ulas Bagci
Annual Meeting of the Radiological Society of North America, 2017 (Oral presentation, pdf)
Abstract: In recent years, there have been many efforts for distributing a big and complex duty among some agents in order to do it more simply. One of the theories that has received attention recently is called Embodiment. According to this theory, in cooperation of a set of agents for performing a particular task, expertise might not be integrated in a centralized controller; rather it gradually spreads to component and agents. Based on this theory and despite the fact that the human brain is the main controller, expertise is integrated in the body organs gradually. In multi-agent systems a central controller controls and programs whole duties and jobs that agents should perform, this leads to have a very complicated central controller. While in embodiment systems, initially each agent with different structures are fed with some knowledge in the specific duty and then are placed together to accomplish a common task. Now, we will examine this issue that how much improvement is earned when every agent has got a specific amount of partial knowledge separately in comparison with whole structure is defined beforehand. We try to implement embodied system on legs of a quadruped and compare result with the multi-agent system.
Google Sites
Report abuse