Myocardial Segmentation of Cardiac MRI Sequences With Temporal Consistency for Coronary Artery Disease Diagnosis

Frontiers in Cardiovascular Medicine

article

Yutian Chen¹  Wen Xie¹  Jiawei Zhang¹  Hailong Qiu¹  Dewen Zeng⁶  Yiyu Shi⁶  Haiyun Yuan¹  Jian Zhuang¹  Qianjun Jia¹  Yanchun Zhang⁵  Yuhao Dong¹  Meiping Huang¹  Xiaowei Xu¹ 

[1] Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences;Guangdong Provincial Key Laboratory of South China Structural Heart Disease, Guangdong Cardiovascular Institute;Department of Computer Science, Carnegie Mellon University;Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University;Cyberspace Institute of Advanced Technology, Guangzhou University;Department of Computer Science and Engineering, University of Notre Dame;Department of Catheterization Lab, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences

关键词: myocardial segmentation;    MRI;    cardiac sequences;    temporal consistency;    coronary artery disease;    diagnosis;   

DOI  :  10.3389/fcvm.2022.804442

学科分类：地球科学(综合)

来源: Frontiers

【 摘 要 】

Coronary artery disease (CAD) is the most common cause of death globally, and its diagnosis is usually based on manual myocardial (MYO) segmentation of MRI sequences. As manual segmentation is tedious, time-consuming, and with low replicability, automatic MYO segmentation using machine learning techniques has been widely explored recently. However, almost all the existing methods treat the input MRI sequences independently, which fails to capture the temporal information between sequences, e.g., the shape and location information of the myocardium in sequences along time. In this article, we propose a MYO segmentation framework for sequence of cardiac MRI (CMR) scanning images of the left ventricular (LV) cavity, right ventricular (RV) cavity, and myocardium. Specifically, we propose to combine conventional neural networks and recurrent neural networks to incorporate temporal information between sequences to ensure temporal consistency. We evaluated our framework on the automated cardiac diagnosis challenge (ACDC) dataset. The experiment results demonstrate that our framework can improve the segmentation accuracy by up to 2% in the Dice coefficient.

【 授权许可】

CC BY