Multi-view fusion network with test time augmentation for cardiac image segmentation and ejection fraction estimation

Accurate ejection fraction (EF) estimation is critical for diagnosing and managing heart failure. EF is typically calculated using the biplane method of disks, which relies on precise segmentation of the left ventricle from 2-chamber and 4-chamber views at the same cardiac phase. However, despite th...

Full description

Saved in:
Bibliographic Details
Main Authors: Waqas Anwaar, Van Manh, Wufeng Xue, Dong Ni
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025024831
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850035789792018432
author Waqas Anwaar
Van Manh
Wufeng Xue
Dong Ni
author_facet Waqas Anwaar
Van Manh
Wufeng Xue
Dong Ni
author_sort Waqas Anwaar
collection DOAJ
description Accurate ejection fraction (EF) estimation is critical for diagnosing and managing heart failure. EF is typically calculated using the biplane method of disks, which relies on precise segmentation of the left ventricle from 2-chamber and 4-chamber views at the same cardiac phase. However, despite the strong correlation between these views, variations in cardiac motion can lead to inconsistent segmentation performance when models are trained separately on each view. This results in suboptimal data utilization, limiting the performance and robustness of automated methods. To address this, we propose Multi-View XNet, a dual-headed encoder-decoder architecture that fuses information from both views using our novel Cross-View Fusion Module. The module regularizes mutual information in the latent space by simultaneously processing both views through separate encoder heads. The fused information is then passed to two decoder heads to output segmented results for each respective view, which are used to compute EF. To further enhance performance, we introduce test-time augmentation (TTA) to improve robustness against scanning variations. Our method outperforms state-of-the-art approaches in segmentation (DICE scores of 0.947 and 0.961 for endocardium and epicardium in end-diastole, and 0.932 and 0.957 in end-systole) and in clinical parameters (correlations of 0.980, 0.982, and 0.916 for EDV, ESV, and EF, respectively, with a mean absolute EF error of 4.7 percent). We also demonstrate generalization on an external dataset, achieving DICE scores of 0.921 and 0.933 for the endocardium and epicardium in ED, and 0.844 and 0.895 in ES. To support reproducibility and future research, our code is publicly available at: https://github.com/waqasanwaar/MV-XNet.
format Article
id doaj-art-10edc359947b414d96e4165f67d75fdc
institution DOAJ
issn 2590-1230
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-10edc359947b414d96e4165f67d75fdc2025-08-20T02:57:22ZengElsevierResults in Engineering2590-12302025-09-012710641310.1016/j.rineng.2025.106413Multi-view fusion network with test time augmentation for cardiac image segmentation and ejection fraction estimationWaqas Anwaar0Van Manh1Wufeng Xue2Dong Ni3National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, China; Medical Ultrasound Image Computing (MUSIC) Lab, Shenzhen University, ChinaNational-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, China; Medical Ultrasound Image Computing (MUSIC) Lab, Shenzhen University, ChinaNational-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, China; Medical Ultrasound Image Computing (MUSIC) Lab, Shenzhen University, China; Corresponding authors at: National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China.National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, China; Medical Ultrasound Image Computing (MUSIC) Lab, Shenzhen University, China; Corresponding authors at: National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China.Accurate ejection fraction (EF) estimation is critical for diagnosing and managing heart failure. EF is typically calculated using the biplane method of disks, which relies on precise segmentation of the left ventricle from 2-chamber and 4-chamber views at the same cardiac phase. However, despite the strong correlation between these views, variations in cardiac motion can lead to inconsistent segmentation performance when models are trained separately on each view. This results in suboptimal data utilization, limiting the performance and robustness of automated methods. To address this, we propose Multi-View XNet, a dual-headed encoder-decoder architecture that fuses information from both views using our novel Cross-View Fusion Module. The module regularizes mutual information in the latent space by simultaneously processing both views through separate encoder heads. The fused information is then passed to two decoder heads to output segmented results for each respective view, which are used to compute EF. To further enhance performance, we introduce test-time augmentation (TTA) to improve robustness against scanning variations. Our method outperforms state-of-the-art approaches in segmentation (DICE scores of 0.947 and 0.961 for endocardium and epicardium in end-diastole, and 0.932 and 0.957 in end-systole) and in clinical parameters (correlations of 0.980, 0.982, and 0.916 for EDV, ESV, and EF, respectively, with a mean absolute EF error of 4.7 percent). We also demonstrate generalization on an external dataset, achieving DICE scores of 0.921 and 0.933 for the endocardium and epicardium in ED, and 0.844 and 0.895 in ES. To support reproducibility and future research, our code is publicly available at: https://github.com/waqasanwaar/MV-XNet.http://www.sciencedirect.com/science/article/pii/S2590123025024831Multi-view fusionEjection fractionSegmentationEchocardiography
spellingShingle Waqas Anwaar
Van Manh
Wufeng Xue
Dong Ni
Multi-view fusion network with test time augmentation for cardiac image segmentation and ejection fraction estimation
Results in Engineering
Multi-view fusion
Ejection fraction
Segmentation
Echocardiography
title Multi-view fusion network with test time augmentation for cardiac image segmentation and ejection fraction estimation
title_full Multi-view fusion network with test time augmentation for cardiac image segmentation and ejection fraction estimation
title_fullStr Multi-view fusion network with test time augmentation for cardiac image segmentation and ejection fraction estimation
title_full_unstemmed Multi-view fusion network with test time augmentation for cardiac image segmentation and ejection fraction estimation
title_short Multi-view fusion network with test time augmentation for cardiac image segmentation and ejection fraction estimation
title_sort multi view fusion network with test time augmentation for cardiac image segmentation and ejection fraction estimation
topic Multi-view fusion
Ejection fraction
Segmentation
Echocardiography
url http://www.sciencedirect.com/science/article/pii/S2590123025024831
work_keys_str_mv AT waqasanwaar multiviewfusionnetworkwithtesttimeaugmentationforcardiacimagesegmentationandejectionfractionestimation
AT vanmanh multiviewfusionnetworkwithtesttimeaugmentationforcardiacimagesegmentationandejectionfractionestimation
AT wufengxue multiviewfusionnetworkwithtesttimeaugmentationforcardiacimagesegmentationandejectionfractionestimation
AT dongni multiviewfusionnetworkwithtesttimeaugmentationforcardiacimagesegmentationandejectionfractionestimation