中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Histopathological bladder cancer gene mutation prediction with hierarchical deep multiple-instance learning

文献类型：期刊论文

作者Yan, Rui8,9; Shen, Yijun4,5; Zhang, Xueyuan6; Xu, Peihang4,5; Wang, Jun1; Li, Jintao8; Ren, Fei7,8; Ye, Dingwei4,5; Zhou, S. Kevin2,3,8
刊名MEDICAL IMAGE ANALYSIS
出版日期2023-07-01
卷号87页码:13
ISSN号1361-8415
关键词Bladder cancer Contrastive learning Gene mutation prediction Histopathological image analysis Multiple instance learning
DOI10.1016/j.media.2023.102824
英文摘要Gene mutation detection is usually carried out by molecular biological methods, which is expensive and has a long-time cycle. In contrast, pathological images are ubiquitous. If clinically significant gene mutations can be predicted only through pathological images, it will greatly promote the widespread use of gene mutation detection in clinical practice. However, current gene mutation prediction methods based on pathological images are ineffective because of the inability to identify mutated regions in gigapixel Whole Slide Image (WSI). To address this challenge, hereby we propose a carefully designed framework for WSI-based gene mutation prediction, which consists of three parts. (i) The first part of cancerous area segmentation, based on supervised learning, quickly filters out a large number of non-mutated regions; (ii) the second part of cancerous patch clustering, based on the representations derived from contrastive learning, ensures the comprehensiveness of patch selection; and (iii) the third part of mutation classification, based on the proposed hierarchical deep multi-instance learning method (HDMIL), ensures that sufficient patches are considered and inaccurate selections are ignored. In addition, benefiting from a two-stage attention mechanism in HDMIL, the patches that are highly correlated with gene mutations can be identified. This interpretability can help a pathologist to analyze the correlation between gene mutation and histopathological morphology. Experimental results demonstrate that the proposed gene mutation prediction framework significantly outperforms the state-of-the-art methods. In the TCGA bladder cancer dataset, five clinically relevant gene mutations are well predicted.
资助项目National Key Research and Development Program of China[2021YFF1201005] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA16021400] ; Clinical Research Plan of Shanghai Hospital Development Center, China[SHDC2020CR4031] ; Informatization Plan of Chinese Academy of Sciences[CAS-WX2021SF-0101]
WOS研究方向Computer Science ; Engineering ; Radiology, Nuclear Medicine & Medical Imaging
语种英语
出版者ELSEVIER
WOS记录号WOS:000990996400001
源URL[http://119.78.100.204/handle/2XEOYT63/21427]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Ren, Fei; Ye, Dingwei; Zhou, S. Kevin
作者单位1.Sun Yat Sen Univ, Canc Ctr, Dept Urol, Guangzhou 510060, Peoples R China
2.Univ Sci & Technol China, Sch Biomed Engn, Suzhou 215123, Peoples R China
3.Univ Sci & Technol China, Suzhou Inst Adv Res, Suzhou 215123, Peoples R China
4.Fudan Univ, Shanghai Canc Ctr, Dept Urol, Shanghai 200032, Peoples R China
5.Fudan Univ, Shanghai Med Coll, Dept Oncol, Shanghai 200032, Peoples R China
6.Zhijian Life Technol Co Ltd, Beijing 100036, Peoples R China
7.Chinese Acad Sci, Inst Comp Technol, SKLP, Beijing 100190, Peoples R China
8.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
9.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Yan, Rui,Shen, Yijun,Zhang, Xueyuan,et al. Histopathological bladder cancer gene mutation prediction with hierarchical deep multiple-instance learning[J]. MEDICAL IMAGE ANALYSIS,2023,87:13.
APA Yan, Rui.,Shen, Yijun.,Zhang, Xueyuan.,Xu, Peihang.,Wang, Jun.,...&Zhou, S. Kevin.(2023).Histopathological bladder cancer gene mutation prediction with hierarchical deep multiple-instance learning.MEDICAL IMAGE ANALYSIS,87,13.
MLA Yan, Rui,et al."Histopathological bladder cancer gene mutation prediction with hierarchical deep multiple-instance learning".MEDICAL IMAGE ANALYSIS 87(2023):13.

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。