Classification of myocardial fibrosis in DE-MRI based on semi-supervised semantic segmentation and dual attention mechanism. (October 2022)

• Record Type: Journal Article
• Authors: Ding, Yuhan; Xie, Weifang; Wong, Kelvin K.L.; Liao, Zhifang
• Is Part Of: Computer methods and programs in biomedicine. Volume 225(2022)
• Publication Date: 2022-10
• Subjects: Semi-Supervised Semantic Segmentation -- Dual Attention Mechanism -- DE-MRI -- Myocardial Fibrosis -- Cardiac Image Classification; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.107041
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: This paper studies the segmentation and classification of myocardial fibrosis in DE-MRI images based on semi-supervised semantic segmentation and dual attention mechanism. The gradient weighted class activation mapping method is introduced to analyze the trained classification network visually, and it is found that the combination of the attention mechanism and the backbone network can effectively improve the classification accuracy. Experiments on the EMIDEC dataset show that each method module has dramatically improved its performance. The comparison with the existing methods shows that the performance of this method is slightly inferior to the current optimal weakly supervised method. The model can effectively improve the efficiency and accuracy of image classification. Abstract: Objective: It is essential to utilize cardiac delayed-enhanced magnetic resonance imaging (DE-MRI) to diagnose cardiovascular disease. By segmenting myocardium DE-MRI images, it provides critical information for the evaluation and treatment of myocardial infarction. As a consequence, it is vital to investigate the segmentation and classification technique of myocardial DE-MRI. Methods: Firstly, an end-to-end minimally supervised and semi-supervised semantic DE-MRI myocardial fibrosis segmentation framework is proposed, which combines image classification and semantic segmentation branches based on the self-attention mechanism. Following that, a residual hole network fused with the dual attention mechanism was built, and a double attention metabolic pathway classification method for cardiac fibrosis in DE-MRI images was developed. Results: By adding pixel-level labels to an extra 40 training images, the segmentation model may enhance semantic segmentation performance by 2.6 percent (from 61.2 percent to 63.8 percent). When the number of pixel-level labels is increased to 80, semi-supervised feature extraction increases by 4.7 percent when compared to weakly guided semantic segmentation. Adding an attention mechanism to the critical network DRN (Deep Residual Network) can increase the classifier's performance by a small amount. Experiments revealed that the models worked effectively. Conclusion: This paper investigates the segmentation and classification of cardiac fibrosis in DE-MRI data using a semi-supervised semantic segmentation and dual attention mechanism, dealing with the issue that existing segmentation algorithms have difficulty segmenting myocardial fibrosis tissue. In the future, we can consider optimizing the design of the attention module to reduce the module computation.