Histopathological bladder cancer gene mutation prediction with hierarchical deep multiple-instance learning

doi:10.1016/j.media.2023.102824

	Histopathological bladder cancer gene mutation prediction with hierarchical deep multiple-instance learning
	Yan, Rui 1,2; Shen, Yijun 3,4; Zhang, Xueyuan 5; Xu, Peihang 3,4; Wang, Jun 6; Li, Jintao 1; Ren, Fei 1,7; Ye, Dingwei 3,4; Zhou, S. Kevin 1,8,9
	2023-07-01
发表期刊	MEDICAL IMAGE ANALYSIS
ISSN	1361-8415
卷号	87 页码:13
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.
关键词	Bladder cancer Contrastive learning Gene mutation prediction Histopathological image analysis Multiple instance learning
DOI	10.1016/j.media.2023.102824
收录类别	SCI
语种	英语
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
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000990996400001
出版者	ELSEVIER
引用统计	被引频次：4[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21428
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.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Fudan Univ, Shanghai Canc Ctr, Dept Urol, Shanghai 200032, Peoples R China 4.Fudan Univ, Shanghai Med Coll, Dept Oncol, Shanghai 200032, Peoples R China 5.Zhijian Life Technol Co Ltd, Beijing 100036, Peoples R China 6.Sun Yat Sen Univ, Canc Ctr, Dept Urol, Guangzhou 510060, Peoples R China 7.Chinese Acad Sci, Inst Comp Technol, SKLP, Beijing 100190, Peoples R China 8.Univ Sci & Technol China, Sch Biomed Engn, Suzhou 215123, Peoples R China 9.Univ Sci & Technol China, Suzhou Inst Adv Res, Suzhou 215123, 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.