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

Ren, Jinchang and Sun, He and Zhao, Huimin and Gao, Hao and Maclellan, Calum and Zhao, Sophia and Luo, Xiaoyu (2021) Effective extraction of ventricles and myocardium objects from cardiac magnetic resonance images with a multi-task learning U-Net. Pattern Recognition Letters. ISSN 0167-8655 (https://doi.org/10.1016/j.patrec.2021.10.025)

[thumbnail of Ren-etal-PRL-2021-Effective-extraction-of-ventricles-and-myocardium-objects] Text. Filename: Ren_etal_PRL_2021_Effective_extraction_of_ventricles_and_myocardium_objects.pdf
Accepted Author Manuscript
Restricted to Repository staff only until 26 October 2022.
License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 logo

Download (1MB) | Request a copy

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.