Published on Tue Jun 08 2021

Left Ventricle Contouring in Cardiac Images Based on Deep Reinforcement Learning

Sixing Yin, Yameng Han, Shufang Li

Medical image segmentation is one of the important tasks of computer-aided diagnosis in medical image analysis. Most medical images have blurred boundaries and uneven intensity distribution. Using existing segmentation methods, the discontinuity within the target area and discontinuity of the target boundary are likely to lead to rough or even erroneous boundary delineation.

1
0
0
Abstract

Medical image segmentation is one of the important tasks of computer-aided diagnosis in medical image analysis. Since most medical images have the characteristics of blurred boundaries and uneven intensity distribution, through existing segmentation methods, the discontinuity within the target area and the discontinuity of the target boundary are likely to lead to rough or even erroneous boundary delineation. In this paper, we propose a new iterative refined interactive segmentation method for medical images based on agent reinforcement learning, which focuses on the problem of target segmentation boundaries. We model the dynamic process of drawing the target contour in a certain order as a Markov Decision Process (MDP) based on a deep reinforcement learning method. In the dynamic process of continuous interaction between the agent and the image, the agent tracks the boundary point by point in order within a limited length range until the contour of the target is completely drawn. In this process, the agent can quickly improve the segmentation performance by exploring an interactive policy in the image. The method we proposed is simple and effective. At the same time, we evaluate our method on the cardiac MRI scan data set. Experimental results show that our method has a better segmentation effect on the left ventricle in a small number of medical image data sets, especially in terms of segmentation boundaries, this method is better than existing methods. Based on our proposed method, the dynamic generation process of the predicted contour trajectory of the left ventricle will be displayed online at https://github.com/H1997ym/LV-contour-trajectory.

Sat Nov 23 2019
Computer Vision
Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning
Existing automatic 3D image segmentation methods usually fail to meet the needs of clinics. We treat each voxel as an agent with a shared behavior strategy so that it can be solved with multi-agent reinforcement learning. Experimental results on various medical datasets have shown that our method significantly outperforms state-
0
0
0
Wed Jun 10 2020
Computer Vision
Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
Deep neural network (DNN) based approaches have been widely investigated and deployed in medical image analysis. The proposed approach can be utilized for tuning hyper-parameters, and selecting necessary data augmentation with certain probabilities.
0
0
0
Mon Mar 27 2017
Computer Vision
The Deep Poincar\'e Map: A Novel Approach for Left Ventricle Segmentation
Precise segmentation of the left ventricle (LV) within cardiac MRI images is a prerequisite for the quantitative measurement of heart function. The task is challenging due to the limited availability of labeled data and artifacts from cardiac imaging.
0
0
0
Thu Jul 19 2018
Machine Learning
Automatically Designing CNN Architectures for Medical Image Segmentation
Deep neural network architectures have traditionally been designed andexplored with human expertise in a long-lasting trial-and-error process. We propose a novel algorithm to optimally find hyperparameters of a deep network architecture automatically. We show the efficacy of the proposed method with its low computational cost.
0
0
0
Tue Nov 06 2018
Machine Learning
Towards continual learning in medical imaging
This work investigates continual learning of two segmentation tasks in brain MRI with neural networks. We investigate elastic weight consolidation, a recently proposed method based on Fisher information. Our findings show this recent method reduces catastrophic forgetting, while large room for improvement exists in these challenging settings.
0
0
0
Mon Sep 02 2019
Machine Learning
Resource Optimized Neural Architecture Search for 3D Medical Image Segmentation
Neural Architecture Search (NAS) is a framework which automates the task of designing neural networks. There are only a few NAS methods suitable for 3D medical image segmentation. Medical 3D images are generally very large; thus it is difficult to apply previous NAS methods.
0
0
0