Left ventricle contouring in cardiac images based on deep reinforcement learning

作     者：Yin, Sixing Han, Yameng Pan, Judong Wang, Yining Li, Shufang Yu, F. Richard 

作者机构：Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China University of California San Francisco San FranciscoCA94117 United States State Key Laboratory of Complex Severe and Rare Diseases Chinese Academy of Medical Sciences Peking Union Medical College Beijing100730 China The Department of Systems and Computer Engineering Carleton University OttawaONK1S 5B6 Canada 

出 版 物：《TechRxiv》 (TechRxiv)

年 卷 期：2021年

核心收录：

主　　题：Reinforcement learning 

摘      要：Assessment of the left ventricle segmentation in cardiac magnetic resonance imaging (MRI) is of crucial importance for cardiac disease diagnosis. However, conventional manual segmentation is a tedious task that requires excessive human effort, which makes automated segmentation highly desirable in practice to facilitate the process of clinical diagnosis. In this paper, we propose a novel reinforcement-learning-based framework for left ventricle contouring, which mimics how a cardiologist outlines the left ventricle in a cardiac image. Since such a contour drawing process is simply moving a paintbrush along a specific trajectory, it is thus analogized to a path finding problem. Following the algorithm of proximal policy optimization (PPO), we train a policy network, which makes a stochastic decision on the agent’s movement according to its local observation such that the generated trajectory matches the true contour of the left ventricle as much as possible. Moreover, we design a deep learning model with a customized loss function to generate the agent’s landing spot (or coordinate of its initial position on a cardiac image). The experiment results show that the coordinate of the generated landing spot is sufficiently close to the true contour and the proposed reinforcement-learning-based approach outperforms the existing U-net model even with limited training set. © 2021, CC BY.