Cargando…
Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning
Deep reinforcement learning (DRL) has been utilized in numerous computer vision tasks, such as object detection, autonomous driving, etc. However, relatively few DRL methods have been proposed in the area of image segmentation, particularly in left ventricle segmentation. Reinforcement learning-base...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8037138/ https://www.ncbi.nlm.nih.gov/pubmed/33805558 http://dx.doi.org/10.3390/s21072375 |
_version_ | 1783677073502502912 |
---|---|
author | Xiong, Jingjing Po, Lai-Man Cheung, Kwok Wai Xian, Pengfei Zhao, Yuzhi Rehman, Yasar Abbas Ur Zhang, Yujia |
author_facet | Xiong, Jingjing Po, Lai-Man Cheung, Kwok Wai Xian, Pengfei Zhao, Yuzhi Rehman, Yasar Abbas Ur Zhang, Yujia |
author_sort | Xiong, Jingjing |
collection | PubMed |
description | Deep reinforcement learning (DRL) has been utilized in numerous computer vision tasks, such as object detection, autonomous driving, etc. However, relatively few DRL methods have been proposed in the area of image segmentation, particularly in left ventricle segmentation. Reinforcement learning-based methods in earlier works often rely on learning proper thresholds to perform segmentation, and the segmentation results are inaccurate due to the sensitivity of the threshold. To tackle this problem, a novel DRL agent is designed to imitate the human process to perform LV segmentation. For this purpose, we formulate the segmentation problem as a Markov decision process and innovatively optimize it through DRL. The proposed DRL agent consists of two neural networks, i.e., First-P-Net and Next-P-Net. The First-P-Net locates the initial edge point, and the Next-P-Net locates the remaining edge points successively and ultimately obtains a closed segmentation result. The experimental results show that the proposed model has outperformed the previous reinforcement learning methods and achieved comparable performances compared with deep learning baselines on two widely used LV endocardium segmentation datasets, namely Automated Cardiac Diagnosis Challenge (ACDC) 2017 dataset, and Sunnybrook 2009 dataset. Moreover, the proposed model achieves higher F-measure accuracy compared with deep learning methods when training with a very limited number of samples. |
format | Online Article Text |
id | pubmed-8037138 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-80371382021-04-12 Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning Xiong, Jingjing Po, Lai-Man Cheung, Kwok Wai Xian, Pengfei Zhao, Yuzhi Rehman, Yasar Abbas Ur Zhang, Yujia Sensors (Basel) Article Deep reinforcement learning (DRL) has been utilized in numerous computer vision tasks, such as object detection, autonomous driving, etc. However, relatively few DRL methods have been proposed in the area of image segmentation, particularly in left ventricle segmentation. Reinforcement learning-based methods in earlier works often rely on learning proper thresholds to perform segmentation, and the segmentation results are inaccurate due to the sensitivity of the threshold. To tackle this problem, a novel DRL agent is designed to imitate the human process to perform LV segmentation. For this purpose, we formulate the segmentation problem as a Markov decision process and innovatively optimize it through DRL. The proposed DRL agent consists of two neural networks, i.e., First-P-Net and Next-P-Net. The First-P-Net locates the initial edge point, and the Next-P-Net locates the remaining edge points successively and ultimately obtains a closed segmentation result. The experimental results show that the proposed model has outperformed the previous reinforcement learning methods and achieved comparable performances compared with deep learning baselines on two widely used LV endocardium segmentation datasets, namely Automated Cardiac Diagnosis Challenge (ACDC) 2017 dataset, and Sunnybrook 2009 dataset. Moreover, the proposed model achieves higher F-measure accuracy compared with deep learning methods when training with a very limited number of samples. MDPI 2021-03-29 /pmc/articles/PMC8037138/ /pubmed/33805558 http://dx.doi.org/10.3390/s21072375 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ). |
spellingShingle | Article Xiong, Jingjing Po, Lai-Man Cheung, Kwok Wai Xian, Pengfei Zhao, Yuzhi Rehman, Yasar Abbas Ur Zhang, Yujia Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning |
title | Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning |
title_full | Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning |
title_fullStr | Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning |
title_full_unstemmed | Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning |
title_short | Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning |
title_sort | edge-sensitive left ventricle segmentation using deep reinforcement learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8037138/ https://www.ncbi.nlm.nih.gov/pubmed/33805558 http://dx.doi.org/10.3390/s21072375 |
work_keys_str_mv | AT xiongjingjing edgesensitiveleftventriclesegmentationusingdeepreinforcementlearning AT polaiman edgesensitiveleftventriclesegmentationusingdeepreinforcementlearning AT cheungkwokwai edgesensitiveleftventriclesegmentationusingdeepreinforcementlearning AT xianpengfei edgesensitiveleftventriclesegmentationusingdeepreinforcementlearning AT zhaoyuzhi edgesensitiveleftventriclesegmentationusingdeepreinforcementlearning AT rehmanyasarabbasur edgesensitiveleftventriclesegmentationusingdeepreinforcementlearning AT zhangyujia edgesensitiveleftventriclesegmentationusingdeepreinforcementlearning |