[1]陈志颖,陈春晓△,吴泽静,等.基于深度学习的膀胱癌多参数磁共振成像无监督配准方法研究[J].生物医学工程研究,2023,02:145-151.
CHEN Zhiying,CHEN Chunxiao,WU Zejing,et al.Research on unsupervised registration method of bladder cancer multi-parameter MRI based on deep learning[J].Journal of Biomedical Engineering Research,2023,02:145-151.
点击复制
基于深度学习的膀胱癌多参数磁共振成像无监督配准方法研究(PDF)
《生物医学工程研究》[ISSN:1006-6977/CN:61-1281/TN]
- 期数:
-
2023年02期
- 页码:
-
145-151
- 栏目:
-
- 出版日期:
-
2023-06-25
文章信息/Info
- Title:
-
Research on unsupervised registration method of bladder cancer multi-parameter MRI based on deep learning
- 文章编号:
-
1672-6278 (2023)02-0145-07
- 作者:
-
陈志颖; 陈春晓△; 吴泽静; 徐俊琪
-
(南京航空航天大学 生物医学工程系,南京 211106)
- Author(s):
-
CHEN Zhiying; CHEN Chunxiao; WU Zejing; XU Junqi
-
(Department of Biomedical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China)
-
- 关键词:
-
膀胱癌诊断; 多参数磁共振; 跨模态配准; 深度学习; 端到端; 无监督学习; 相似性度量
- Keywords:
-
Diagnosis of bladder cancer; Multi-parameter MRI; Cross-modal registration; Deep learning; End-to-end; Unsupervised learning; Similarity measure
- 分类号:
-
R318.51, TP391.9, TP183
- DOI:
-
10.19529/j.cnki.1672-6278.2023.02.06
- 文献标识码:
-
A
- 摘要:
-
针对传统基于迭代优化的医学影像配准方法速度慢、泛化性差的问题,本研究提出了一种基于深度学习的膀胱癌磁共振成像(magnetic resonance image, MRI)跨模态无监督配准方法,并采用具有随机块采样的标准互信息(patch normalized mutual information, Patch-NMI)进行无监督训练。相比传统的迭代配准方法,本研究算法在进行膀胱癌动态增强成像(dynamic contrast-enhanced imaging, DCE)和T2加权像(T2-weighted imaging, T2WI)配准时,精度提升了1.3%,速度提高了20.42倍。实验结果表明,本算法在进行膀胱癌DCE和T2WI配准时,精度更高,速度更快。
- Abstract:
-
To solve the slow speed and poor generalization of traditional medical image registration based on iterative optimization, we proposed a cross-modal unsupervised registration method of bladder cancer MRI based on deep learning.The patch normalized mutual information (Patch-NMI) loss with random block sampling was used for unsupervised training. Compared with the traditional iterative registration method,the accuracy of the proposed algorithm was improved by 1.3%, and the speed was improved by 20.42 times in the registration of dynamic contrast-enhanced imaging (DCE) and T2-weighted imaging (T2WI). The results show that this algorithm has higher accuracy and faster speed in the registration of DCE and T2WI.
备注/Memo
- 备注/Memo:
-
(收稿日期:2022-09-30)△通信作者Email: ccxbme@nuaa.edu.cn
更新日期/Last Update:
2023-07-13