Left Ventricle Contouring in Cardiac Images Based on Deep Reinforcement Learning

Sixing Yin, Yameng Han, Judong Pan, Yining Wang, Shufang Li
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:1470-1481, 2022.

Abstract

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 along a specific trajectory in a cardiac image. 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 and its improved version, even with limited training set.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-yin22a, title = {Left Ventricle Contouring in Cardiac Images Based on Deep Reinforcement Learning}, author = {Yin, Sixing and Han, Yameng and Pan, Judong and Wang, Yining and Li, Shufang}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {1470--1481}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/yin22a/yin22a.pdf}, url = {https://proceedings.mlr.press/v172/yin22a.html}, abstract = {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 along a specific trajectory in a cardiac image. 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 and its improved version, even with limited training set.} }
Endnote
%0 Conference Paper %T Left Ventricle Contouring in Cardiac Images Based on Deep Reinforcement Learning %A Sixing Yin %A Yameng Han %A Judong Pan %A Yining Wang %A Shufang Li %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-yin22a %I PMLR %P 1470--1481 %U https://proceedings.mlr.press/v172/yin22a.html %V 172 %X 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 along a specific trajectory in a cardiac image. 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 and its improved version, even with limited training set.
APA
Yin, S., Han, Y., Pan, J., Wang, Y. & Li, S.. (2022). Left Ventricle Contouring in Cardiac Images Based on Deep Reinforcement Learning. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:1470-1481 Available from https://proceedings.mlr.press/v172/yin22a.html.

Related Material