Efficient Medical Image Segmentation via Reinforcement Learning-Driven K-Space Sampling
文献类型：期刊论文
| 作者 | Li, Yuqi4; Zeng, Hansheng5; Zhang, Fuyan4; Yang, Chuanguang4; Li, Yanli1,3; Ding, Weiping1,2 |
| 刊名 | IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
 |
| 出版日期 | 2025-11-11 |
| 页码 | 14 |
| 关键词 | Magnetic resonance imaging Image reconstruction Image segmentation Accuracy Reinforcement learning Pathology Medical diagnostic imaging Adaptation models Measurement Computational intelligence k-space sampling magnetic resonance imaging reinforcement learning |
| ISSN号 | 2471-285X |
| DOI | 10.1109/TETCI.2025.3621221 |
| 英文摘要 | Magnetic Resonance Imaging (MRI) excels in medical diagnostics with its superior soft tissue contrast and detailed anatomical visualization, providing critical support for precise medical image segmentation. However, traditional full K-space sampling is time-consuming, limiting efficiency in clinical settings. To address this challenge, we propose a novel method leveraging Reinforcement Learning (RL) to adaptively sample K-space, optimizing both MRI acquisition efficiency and segmentation accuracy. Our approach features an RL-driven policy network that strategically selects the most informative K-space samples, substantially reducing scan times while maintaining critical anatomical details. By integrating segmentation performance into the reward model, our method directly aligns the sampling process with accurate pathological segmentation. Furthermore, sparse K-space data are reconstructed into high-quality images, ensuring precise inputs for segmentation networks. Experiments on ACDC, AMOS, M&Ms-2, CHAOS and MSD datasets demonstrate that our approach not only accelerates MRI processing but also significantly enhances segmentation accuracy, showcasing its potential for clinical applications where speed and precision are paramount. |
| 资助项目 | National Key RD Plan of China[2024YFE0202700] ; National Natural Science Foundation of China[62576178] ; Natural Science Foundation of Jiangsu Province[BK20231337] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001616328500001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/43065]  |
| 专题 | 中国科学院计算技术研究所 |
| 通讯作者 | Ding, Weiping |
| 作者单位 | 1.Nantong Univ, Sch Artificial Intelligence & Comp Sci, Nantong 226007, Peoples R China 2.City Univ Macau, Fac Data Sci, Macau 999078, Peoples R China 3.Univ Sydney, Camperdown, NSW 2050, Australia 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 5.Univ Hong Kong, Pokfulam, Hong Kong, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Yuqi,Zeng, Hansheng,Zhang, Fuyan,et al. Efficient Medical Image Segmentation via Reinforcement Learning-Driven K-Space Sampling[J]. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE,2025:14. |
| APA | Li, Yuqi,Zeng, Hansheng,Zhang, Fuyan,Yang, Chuanguang,Li, Yanli,&Ding, Weiping.(2025).Efficient Medical Image Segmentation via Reinforcement Learning-Driven K-Space Sampling.IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE,14. |
| MLA | Li, Yuqi,et al."Efficient Medical Image Segmentation via Reinforcement Learning-Driven K-Space Sampling".IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2025):14. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。