Weakly Supervised Framework for Cancer Region Detection of Hepatocellular Carcinoma in Whole-Slide Pathologic Images Based on Multiscale Attention Convolutional Neural Network

doi:10.1016/j.ajpath.2021.11.009

	Weakly Supervised Framework for Cancer Region Detection of Hepatocellular Carcinoma in Whole-Slide Pathologic Images Based on Multiscale Attention Convolutional Neural Network
	Diao, Songhui 1,2; Tian, Yinli 1,3; Hu, Wanming 4; Hou, Jiaxin 1,2; Lambo, Ricardo 1; Zhang, Zhicheng 5; Xie, Yaoqin 1,2; Nie, Xiu 6; Zhang, Fa 7; Racoceanu, Daniel 8; Qin, Wenjian 1,2
	2022-03-01
发表期刊	AMERICAN JOURNAL OF PATHOLOGY
ISSN	0002-9440
卷号	192 期号:3 页码:553-563
摘要	Visual inspection of hepatocellular carcinoma cancer regions by experienced pathologists in whole-slide images (WSIs) is a challenging, labor-intensive, and time-consuming task because of the large scale and high resolution of WSIs. Therefore, a weakly supervised framework based on a multiscale attention convolutional neural network (MSAN-CNN) was introduced into this process. Herein, patch-based images with image-level normal/tumor annotation (rather than images with pixel-level annotation) were fed into a classification neural network. To further improve the performances of cancer region detection, multiscale attention was introduced into the classification neural network. A total of 100 cases were obtained from The Cancer Genome Atlas and divided into 70 training and 30 testing data sets that were fed into the MSAN-CNN framework. The experimental results showed that this framework significantly outperforms the single-scale detection method according to the area under the curve and accuracy, sensitivity, and specificity metrics. When compared with the diagnoses made by three pathologists, MSAN-CNN performed better than a junior-and an intermediate-level pathologist, and slightly worse than a senior pathologist. Furthermore, MSAN-CNN provided a very fast detection time compared with the pathologists. Therefore, a weakly supervised framework based on MSAN-CNN has great potential to assist pathologists in the fast and accurate detection of cancer regions of hepatocellular carcinoma on WSIs.& nbsp;
DOI	10.1016/j.ajpath.2021.11.009
收录类别	SCI
语种	英语
资助项目	Shenzhen Science and Technology Program of China[JCYJ20200109115420720] ; National Natural Science Foundation of China[61901463] ; National Natural Science Foundation of China[62001464] ; National Natural Science Foundation of China[U20A20373] ; Guangdong province key research and development areas grant[2020B1111140001]
WOS研究方向	Pathology
WOS类目	Pathology
WOS记录号	WOS:000777781100013
出版者	ELSEVIER SCIENCE INC
引用统计	被引频次：8[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/2XEOYT63/18889
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Qin, Wenjian
作者单位	1.Chinese Acad Sci, Shenzhen Inst Adv Technol, 1068 Xueyuan Ave, Shenzhen 518055, Peoples R China 2.Univ Chinese Acad Sci, Shenzhen Coll Adv Technol, Shenzhen, Peoples R China 3.Chongqing Univ, Sch Microelect & Commun Engn, Chongqing, Peoples R China 4.Sun Yat Sen Univ, Dept Pathol, Canc Ctr, Guangzhou, Peoples R China 5.Stanford Univ, Dept Radiat Oncol, Stanford, CA USA 6.Huazhong Univ Sci & Technol, Tongji Med Coll, Union Hosp, Dept Pathol, Wuhan, Peoples R China 7.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 8.Sorbonne Univ, Hop La Pitie Salpetriere, AP HP, CNRS,INSERM,Paris Brain Inst,Inst Cerveaue,ICM, Paris, France
推荐引用方式 GB/T 7714	Diao, Songhui,Tian, Yinli,Hu, Wanming,et al. Weakly Supervised Framework for Cancer Region Detection of Hepatocellular Carcinoma in Whole-Slide Pathologic Images Based on Multiscale Attention Convolutional Neural Network[J]. AMERICAN JOURNAL OF PATHOLOGY,2022,192(3):553-563.
APA	Diao, Songhui.,Tian, Yinli.,Hu, Wanming.,Hou, Jiaxin.,Lambo, Ricardo.,...&Qin, Wenjian.(2022).Weakly Supervised Framework for Cancer Region Detection of Hepatocellular Carcinoma in Whole-Slide Pathologic Images Based on Multiscale Attention Convolutional Neural Network.AMERICAN JOURNAL OF PATHOLOGY,192(3),553-563.
MLA	Diao, Songhui,et al."Weakly Supervised Framework for Cancer Region Detection of Hepatocellular Carcinoma in Whole-Slide Pathologic Images Based on Multiscale Attention Convolutional Neural Network".AMERICAN JOURNAL OF PATHOLOGY 192.3(2022):553-563.