IRUS Total

JAS-GAN: generative adversarial network based joint atrium and scar segmentations on unbalanced atrial targets

File Description SizeFormat 
JASGAN_JBHI_CleanManuscript.pdfAccepted version3.24 MBAdobe PDFView/Open
Title: JAS-GAN: generative adversarial network based joint atrium and scar segmentations on unbalanced atrial targets
Authors: Chen, J
Yang, G
Khan, H
Zhang, H
Zhang, Y
Zhao, S
Mohiaddin, R
Wong, T
Firmin, D
Keegan, J
Item Type: Journal Article
Abstract: Automated and accurate segmentation of the 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 state-of-the-art 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.
Issue Date: 1-Jan-2022
Date of Acceptance: 30-Apr-2021
URI: http://hdl.handle.net/10044/1/89713
DOI: 10.1109/JBHI.2021.3077469
ISSN: 2168-2194
Publisher: Institute of Electrical and Electronics Engineers
Start Page: 103
End Page: 114
Journal / Book Title: IEEE Journal of Biomedical and Health Informatics
Volume: 26
Issue: 1
Copyright Statement: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
Sponsor/Funder: British Heart Foundation
Funder's Grant Number: PG/16/78/32402
Keywords: eess.IV
Publication Status: Published
Online Publication Date: 2021-05-04
Appears in Collections:National Heart and Lung Institute
Faculty of Medicine