Effective extraction of ventricles and myocardium objects from cardiac magnetic resonance images with a multi-task learning U-net.

Ren, Jinchang; Sun, He; Zhao, Huimin; Gao, Hao; Maclellan, Calum; Zhao, Sophia; Luo, Xiaoyu

Abstract

Accurate extraction of semantic objects such as ventricles and myocardium from magnetic resonance (MR) images is one essential but very challenging task for the diagnosis of the cardiac diseases. To tackle this problem, in this paper, an automatic end-to-end supervised deep learning framework is proposed, using a multi-task learning based U-Net (MTL-UNet). Specifically, an edge extraction module and a fusion-based module are introduced for effectively capturing the contextual information such as continuous edges and consistent spatial patterns in terms of intensity and texture features. With a weighted triple loss including the dice loss, the cross-entropy loss and the edge loss, the accuracy of object segmentation and extraction has been effectively improved. Extensive experiments on the publicly available ACDC 2017 dataset have validated the efficacy and efficiency of the proposed MTL-UNet model.

Citation

REN, J., SUN, H., ZHAO, H., GAO, H., MACLELLAN, C., ZHAO, S. and LUO, X. 2022. Effective extraction of ventricles and myocardium objects from cardiac magnetic resonance images with a multi-task learning U-net. Pattern recognition letters [online], 155, pages 165-170. Available from: https://doi.org/10.1016/j.patrec.2021.10.025

• Journal Article Type: Article
• Acceptance Date: Oct 22, 2021
• Online Publication Date: Oct 26, 2021
• Publication Date: Mar 31, 2022
• Deposit Date: Jan 10, 2022
• Publicly Available Date: Oct 27, 2022
• Journal: Pattern Recognition Letters
• Print ISSN: 0167-8655
• Electronic ISSN: 1872-7344
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 155
• Pages: 165-170
• DOI: https://doi.org/10.1016/j.patrec.2021.10.025
• Keywords: U-net; Multi-task learning; Magnetic resonance images (MRI); Ventricles and myocardium extraction; Fusion-based decoder
• Public URL: https://rgu-repository.worktribe.com/output/1512750