Author: Steffen Czolbe

Authors: Akshay V Gaikwad (Indian Institute of Technology (IIT), Bombay)*; Suyash P. Awate (Indian Institute of Technology (IIT) Bombay)

Poster

Abstract: Typical methods for semantic image segmentation rely on large training sets comprising pixel-level segmentations and pixel-level classifications. In medical applications, a large number of training images with per-pixel segmentations are diffcult to obtain. In addition, many applications involve images or image tiles containing a single object/region of interest, where the image/tile-level information about object/region class is readily available. We propose a novel deep-neural-network (DNN) framework for joint segmentation and recognition of objects relying on weakly-supervised learning from training sets having very few expert segmentations, but with object-class labels available for all images/tiles. For weakly-supervised learning, we propose a variational-learning framework relying on Monte Carlo expectation maximization (MCEM), infering a posterior distribution on the missing segmentations. We design an effective Metropolis-Hastings posterior sampler coupled with suitable sample reparametrizations to enable end-to-end backpropagation. We design an effective posterior sampler coupled with suitable sample reparametrizations to enable end-to-end backpropagation. Our end-to-end learning DNN first produces probabilistic segmentations of objects, and then their probabilistic classifications. Results on two publicly available real-world datasets show the benefits of our strategies of (i) joint object segmentation and recognition as well as (ii) weakly-supervised MCEM-based learning.

Authors: Jose Bouza (University of Florida)*; Chun-Hao Yang (University of Florida); David Vaillancourt (University of Florida); Baba C Vemuri (University of Florida)

Poster

Abstract: In this paper, we present a novel generalization of the Volterra Series, which can be viewed as a higher-order convolution, to manifold-valued functions. A special case of the manifold-valued Volterra Series (MVVS) gives us a natural extension of the ordinary convolution to manifold-valued functions that we call, the manifold-valued convolution (MVC). We prove that these generalizations preserve the equivariance properties of the Euclidean Volterra Series and the traditional convolution operator. We present novel deep network architectures using the MVVS and the MVC operations which are then validated via two experiments. These include, (i) movement disorder classification from diffusion magnetic resonance images (dMRI), and (ii) fODF reconstruction from compressed sensed dMRIs. Both experiments outperform the state-of-the-art

Authors: Yunhe Gao (Rutgers University); Zhiqiang Tang (Rutgers); Dimitris N. Metaxas (Rutgers); Mu Zhou (Rutgers university)

Poster

Abstract: Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks’ generalization performance. In medical image analysis, a well-designed augmentation policy usually requires much expert knowledge and is difficult to generalize to multiple tasks due to the vast discrepancies among pixel intensities, image appearances, and object shapes in different medical tasks. To automate medical data augmentation, we propose a regularized adversarial training framework via two min-max objectives and three differentiable augmentation models covering affine transformation, deformation, and appearance changes. Our method is more automatic and efficient than previous automatic augmentation methods, which still rely on pre-defined operations with human-specified ranges and costly bi-level optimization. Extensive experiments demonstrated that our approach, with less training overhead, achieves superior performance over state-of-the-art auto-augmentation methods on both tasks of 2D skin cancer classification and 3D organs-at-risk segmentation.

Authors: Shaheer Ullah Saeed (University College London); Yunguan Fu (University College London); Zachary M C Baum (University College London); Qianye Yang (University College London); Mirabela Rusu (Stanford University); Richard Fan (Stanford University); Geoffrey A Sonn (Stanford University); Dean Barratt (University College London); Yipeng Hu (University College London)

Poster

Abstract: In this paper, we consider a type of image quality assessment (IQA) as a task-specific measurement, which can be used to select images that are more amenable to a given target task, such as image classification or segmentation. We propose to train simultaneously two neural networks for image selection and a target task using reinforcement learning. A controller network learns an image selection policy by maximising an accumulated reward based on the target task performance on the controller-selected validation set, whilst the target task predictor is optimised using the training set. The trained controller is therefore able to reject images that lead to poor accuracy in the target task. In this work, we show that controller-predicted IQA can be significantly different from task-specific quality labels manually defined by humans. Furthermore, we demonstrate that it is possible to learn effective IQA without a “clean” validation set, thereby avoiding the requirement for human labels of task amenability. Using 6712, labelled and segmented, clinical ultrasound images from 259 patients, experimental results on holdout data show that the proposed IQA achieved a mean classification accuracy of 0.94±0.01 and a mean segmentation Dice of 0.89±0.02, by discarding 5% and 15% of the acquired images, respectively. The significantly improved performance was observed for both tested tasks, compared with the respective 0.90±0.01 and 0.82±0.02 from networks without considering task amenability. This enables IQA feedback during real-time ultrasound acquisition among many other medical imaging applications.

Authors: Zhongyi Han (Shandong University)*; Rundong He (Shandong University); Tianyang Li (Shandong University of Traditional Chinese Medicine); Benzheng Wei (Shandong University of Traditional Chinese Medicine); Jian Wang (ShanDong JiaoTong University); Yilong Yin (Shandong University)

Poster

Abstract: With the COVID-19 pandemic bringing about a severe global crisis, our health systems are under tremendous pressure. Automated screening plays a critical role in the fight against this pandemic, and much of the previous work has been very successful in designing effective screening models. However, they would lose effectiveness under the semi-supervised learning environment with only positive and unlabeled (PU) data, which is easy to collect clinically. In this paper, we report our attempt towards achieving semi-supervised screening of COVID-19 from PU data. We propose a new PU learning method called Constraint Non-Negative Positive Unlabeled Learning (cnPU). It suggests the constraint non-negative risk estimator, which is more robust against overfitting than previous PU learning methods when giving limited positive data. It also embodies a new and efficient optimization algorithm that can make the model learn well on positive data and avoid overfitting on unlabeled data. To the best of our knowledge, this is the first work that realizes PU learning of COVID-19. A series of empirical studies show that our algorithm remarkably outperforms state of the art in real datasets of two medical imaging modalities, including X-ray and computed tomography. These advantages endow our algorithm as a robust and useful computer-assisted tool in the semi-supervised screening of COVID-19.

Authors: Long Xie (University of Pennsylvania); Laura Wisse (Lund University); Jiancong Wang (University of Pennsylvania); Sadhana Ravikumar (University of Pennsylvania); Trevor Glenn (University of Pennsylvania); Anica Luther (Lund University); Sydney Lim (University of Pennsylvania); David Wolk (University of Pennsylvania); Paul Yushkevich (UPENN)

Poster

Abstract: Deep learning (DL) is the state-of-the-art methodology in various medical image segmentation tasks. However, it requires relatively large amounts of manually labeled training data, which may be infeasible to generate in some applications. In addition, DL methods have relatively poor generalizability to out-of-sample data. Multi-atlas segmentation (MAS), on the other hand, has promising performance using limited amounts of training data and good generalizability. A hybrid method that integrates the high accuracy of DL and good generalizability of MAS is highly desired and could play an important role in segmentation problems where manually labeled data is hard to generate. Most of the prior work focuses on improving single components of MAS using DL rather than directly optimizing the final segmentation accuracy via an end-to-end pipeline. Only one study explored this idea in binary segmentation of 2D images, but it remains unknown whether it generalizes well to multi-class 3D segmentation problems. In this study, we propose a 3D end-to-end hybrid pipeline, named deep label fusion (DLF), that takes advantage of the strengths of MAS and DL. Experimental results demonstrate that DLF yields significant improvements over conventional label fusion methods as well as U-Net, a direct DL approach, in the context of segmenting medial temporal lobe subregions using 3T T1-weighted and T2-weighted structural MRI. Further, when applied to an unseen similar dataset that is acquired in 7T, DLF maintains its superior performance, which demonstrates its good generalizability.