Automated and accurate segmentations of left atrium (LA) and atrial scars from late gadolinium-enhanced cardiac magnetic resonance (LGE CMR) images are in high demand for quantifying atrial scars. The previous quantification of atrial scars relies on a two-phase segmentation for LA and atrial scars due to their large volume difference (unbalanced atrial targets). In this paper, we propose an inter-cascade generative adversarial network, namely JAS-GAN, to segment the unbalanced atrial targets from LGE CMR images automatically and accurately in an end-to-end way. Firstly, JAS-GAN investigates an adaptive attention cascade to automatically correlate the segmentation tasks of the unbalanced atrial targets. The adaptive attention cascade mainly models the inclusion relationship of the two unbalanced atrial targets, where the estimated LA acts as the attention map to adaptively focus on the small atrial scars roughly. Then, an adversarial regularization is applied to the segmentation tasks of the unbalanced atrial targets for making a consistent optimization. It mainly forces the estimated joint distribution of LA and atrial scars to match the real ones. We evaluated the performance of our JAS-GAN on a 3D LGE CMR dataset with 192 scans. Compared with the state-of-theart methods, our proposed approach yielded better segmentation performance (Average Dice Similarity Coefficient (DSC) values of 0.946 and 0.821 for LA and atrial scars, respectively), which indicated the effectiveness of our proposed approach for segmenting unbalanced atrial targets.
Semi-supervised learning provides great sig-1 nificance in left atrium (LA) segmentation model learn-2 ing with insufficient labelled data. Generalising semi-3 supervised learning to cross-domain data is of high importance to further improve model robustness. However, 5 the widely existing distribution difference and sample mismatch between different data domains hinder the gener-7 alisation of semi-supervised learning. In this study, we 8 alleviate these problems by proposing an Adaptive Hier-9 archical Dual Consistency (AHDC) for the semi-supervised 10 LA segmentation on cross-domain data. The AHDC mainly 11 consists of a Bidirectional Adversarial Inference module 12 (BAI) and a Hierarchical Dual Consistency learning module 13 (HDC). The BAI overcomes the difference of distributions 14 and the sample mismatch between two different domains. It mainly learns two mapping networks adversarially to 16 obtain two matched domains through mutual adaptation. 17 The HDC investigates a hierarchical dual learning paradigm 18 for cross-domain semi-supervised segmentation based on 19 the obtained matched domains. It mainly builds two dual-20 modelling networks for mining the complementary informa-21 tion in both intra-domain and inter-domain. For the intra-22 domain learning, a consistency constraint is applied to the 23 dual-modelling targets to exploit the complementary mod-24 elling information. For the inter-domain learning, a consistency constraint is applied to the LAs modelled by two dual-26 modelling networks to exploit the complementary knowledge among different data domains. We demonstrated the 28 performance of our proposed AHDC on four 3D late gadolin-29 ium enhancement cardiac MR (LGE-CMR) datasets from
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.