Author: Steffen Czolbe

Authors: Matthias Perkonigg (Medical University of Vienna)*; Johannes Hofmanninger (Medical University of Vienna); Georg Langs (Medical University of Vienna)

Poster

Abstract:

Imaging in clinical routine is subject to changing scanner protocols, hardware, or policies in a typically heterogeneous set of acquisition hardware. Accuracy and reliability of deep learning models suffer from those changes as data and targets become inconsistent with their initial static training set. Continual learning can adapt to a continuous data stream of a changing imaging environment.
Here, we propose a method for continual active learning on a data stream of medical images. It recognizes shifts or additions of new imaging sources – domains -, adapts training accordingly, and selects optimal examples for labelling. Model training has to cope with a limited labelling budget, resembling typical real world scenarios. We demonstrate our method on T1-weighted magnetic resonance images from three different scanners with the task of brain age estimation. Results demonstrate that the proposed method outperforms naive active learning while requiring less manual labelling.

Authors: Mobarakol Islam (Imperial College London)*; Ben Glocker (Imperial College London)

Poster

Abstract: The task of image segmentation is inherently noisy due to ambiguities regarding the exact location of boundaries between anatomical structures. We argue that this information can be extracted from the expert annotations at no extra cost, and when integrated into state-of-the-art neural networks, it can lead to improved calibration between soft probabilistic predictions and the underlying uncertainty. We built upon label smoothing (LS) where a network is trained on `blurred’ versions of the ground truth labels which has been shown to be effective for calibrating output predictions. However, LS is not taking the local structure into account and results in overly smoothed predictions with low confidence even for non-ambiguous regions. Here, we propose Spatially Varying Label Smoothing (SVLS), a soft labeling technique that captures the structural uncertainty in semantic segmentation. SVLS also naturally lends itself to incorporate inter-rater uncertainty when multiple labelmaps are available. The proposed approach is extensively validated on four clinical segmentation tasks with different imaging modalities, number of classes and single and multi-rater expert annotations. The results demonstrate that SVLS, despite its simplicity, obtains superior boundary prediction with improved uncertainty and model calibration.

Authors: Yuexiang Li (Youtu Lab, Tencent)*; Jiawei Chen (Tencent); Kai Ma (Tencent); Yefeng Zheng (Tencent)

Poster

Abstract: Cervical cancer causes the fourth most cancer-related deaths of women worldwide. One of the most commonly-used clinical tools for the diagnosis of cervical intraepithelial neoplasia (CIN) and cervical cancer is colposcopy examination. However, due to the challenging imaging conditions such as light reflection on the cervix surface, the clinical accuracy of colposcopy examination is relatively low. In this paper, we propose a computer-aided diagnosis (CAD) system to accurately segment the lesion areas (i.e., CIN and cancer) from colposcopic images, which can not only assist colposcopists for clinical decision, but also provide the guideline for the location of biopsy sites. In clinical practice, colposcopists often need to zoom in the potential lesion area for clearer observation. The colposcopic images with multi-scale views result in a difficulty for current straight-forward deep learning networks to process. To address the problem, we propose a novel attention mechanism, namely feature library, which treats the whole backbone network as a pool of features and extract the useful features on different scales from the pool to recalibrate the most informative representation. Furthermore, to well-train and evaluate our deep learning network, we collect a large-scale colposcopic image dataset for CervIcal lesioN sEgMentAtion (CINEMA), consisting of 34,337 images from 9,652 patients. The lesion areas in the colposcopic images are manually annotated by experienced colposcopists. Extensive experiments are conducted on the CINEMA dataset, which demonstrate the effectiveness of our feature library dealing with cervical lesions of varying sizes.

Authors: Hsi-Wei Hsieh (Johns Hopkins University); Nicolas Charon (Johns Hopkins University )*

Poster

Abstract: This paper introduces an extension of diffeomorphic registration to enable the morphological analysis of data structures with inherent density variations and imbalances. Building on the framework of Large Diffeomorphic Metric Matching (LDDMM) registration and measure representations of shapes, we propose to augment previous measure deformation approaches with an additional density (or mass) transformation process. We then derive a variational formulation for the joint estimation of optimal deformation and density change between two measures. Based on the obtained optimality conditions, we deduce a shooting algorithm to numerically estimate solutions and illustrate the practical interest of this model for several types of geometric data such as fiber bundles with inconsistent fiber densities or incomplete surfaces.

Authors: Daniel H. Pak (Yale University)*; Minliang Liu (Georgia Institute of Technology); Shawn Ahn (Yale University); Andres Caballero (Georgia Institute of Technology); John A Onofrey (Yale University); Liang Liang (University of Miami); Wei Sun (Georgia Institute of Technology); James S Duncan (Yale University)

Poster

Abstract: Finite Element Analysis (FEA) is useful for simulating Transcather Aortic Valve Replacement (TAVR), but has a significant bottleneck at input mesh generation. Existing automated methods for imaging-based valve modeling often make heavy assumptions about imaging characteristics and/or output mesh topology, limiting their adaptability. In this work, we propose a deep learning-based deformation strategy for producing aortic valve FE meshes from noisy 3D CT scans of TAVR patients. In particular, we propose a novel image analysis problem formulation that allows for training of mesh prediction models using segmentation labels (i.e. weak supervision), and identify a unique set of losses that improve model performance within this framework. Our method can handle images with large amounts of calcification and low contrast, and is compatible with predicting both surface and volumetric meshes. The predicted meshes have good surface and correspondence accuracy, and produce reasonable FEA results.

Authors: Munan Ning (National University of Defense Technology)*; Cheng Bian (Tencent); DONG WEI (Tencent Jarvis Lab); Shuang Yu (Tencent); Chenglang Yuan (Tencent); Yaohua Wang ( National University of Defense Technology); Yang Guo (National University of Defense Technology); Kai Ma (Tencent); Yefeng Zheng (Tencent)

Poster

Abstract: Domain shift happens in cross-domain scenarios commonly because of the wide gaps between different domains: when applying a deep learning model well-trained in one domain to another target domain, the model usually performs poorly. To tackle this problem, unsupervised domain adaptation (UDA) techniques are proposed to bridge the gap between different domains, for the purpose of improving model performance without annotation in the target domain. Particularly, UDA has a great value for multimodal medical image analysis, where annotation difficulty is a practical concern. However, most existing UDA methods can only achieve satisfactory improvements in one adaptation direction (e.g., MRI to CT), but often perform poorly in the other (CT to MRI), limiting their practical usage. In this paper, we propose a bidirectional UDA (BiUDA) framework based on disentangled representation learning for equally competent two-way UDA performances. This framework employs a unified domain-aware pattern encoder which not only can adaptively encode images in different domains through a domain controller, but also improve model efficiency by eliminating redundant parameters. Furthermore, to avoid distortion of contents and patterns of input images during the adaptation process, a content-pattern consistency loss is introduced. Additionally, for better UDA segmentation performance, a label consistency strategy is proposed to provide extra supervision by recomposing target-domain-styled images and corresponding source-domain annotations. Comparison experiments and ablation studies conducted on two public datasets demonstrate the superiority of our BiUDA framework to current state-of-the-art UDA methods and the effectiveness of its novel designs. By successfully addressing two-way adaptations, our BiUDA framework offers a flexible solution of UDA techniques to the real-world scenario.

Authors: Yubo Zhang (The University of North Carolina at Chapel Hill)*; Shuxian Wang (The University of North Carolina at Chapel Hill); Ruibin Ma (University of North Carolina at Chapel Hill); Sarah McGill (University of North Carolina at Chapel Hill); Julian Rosenman (University of North Carolina at Chapel Hill); Steve Pizer (University of North Carolina)

Poster

Abstract: High screening coverage during colonoscopy is crucial to effectively prevent colon cancer. Previous work has allowed alerting the doctor to unsurveyed regions by reconstructing the 3D colonoscopic surface from colonoscopy videos in real-time. However, the lighting inconsistency of colonoscopy videos can cause a key component of the colonoscopic reconstruction system, the SLAM optimization, to fail. In this work we focus on the lighting problem in colonoscopy videos. To successfully improve the lighting consistency of colonoscopy videos, we have found necessary a lighting correction that adapts to the intensity distribution of recent video frames. To achieve this in real-time, we have designed and trained an RNN network. This network adapts the gamma value in a gamma-correction process. Applied in the colonoscopic surface reconstruction system, our light-weight model significantly boosts the reconstruction success rate, making a larger proportion of colonoscopy video segments reconstructable and improving the reconstruction quality of the already reconstructed segments.

Authors: Lok hin Lee (University of Oxford)*; Yuan Gao (University of Oxford); Alison Noble (University of Oxford)

Poster

Abstract: Deep learning models with large learning capacities often overfit to medical imaging datasets. This is because training sets are often relatively small due to the significant time and financial costs incurred in medical data acquisition and labelling. Data augmentation is therefore often used to expand the availability of training data and to increase generalization. However, augmentation strategies are often chosen on an ad-hoc basis without justification. In this paper, we present an augmentation policy search method with the goal of improving model classification performance. We include in the augmentation policy search additional transformations that are often used in medical image analysis and evaluate their performance. In addition, we extend the augmentation policy search to include non-linear mixed-example data augmentation strategies. Using these learned policies, we show that principled data augmentation for medical image model training can lead to significant improvements in ultrasound standard plane detection, with an an average F1-score improvement of 7.0\% overall over naive data augmentation strategies in ultrasound fetal standard plane classification. We find that the learned representations of ultrasound images are better clustered and defined with optimized data augmentation.