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

文献类型：期刊论文

作者Diao, Songhui2,3; Tian, Yinli2,4; Hu, Wanming5; Hou, Jiaxin2,3; Lambo, Ricardo2; Zhang, Zhicheng6; Xie, Yaoqin2,3; Nie, Xiu1; Zhang, Fa7; Racoceanu, Daniel8
刊名AMERICAN JOURNAL OF PATHOLOGY
出版日期2022-03-01
卷号192期号:3页码:553-563
ISSN号0002-9440
DOI10.1016/j.ajpath.2021.11.009
英文摘要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;
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
语种英语
出版者ELSEVIER SCIENCE INC
WOS记录号WOS:000777781100013
源URL[http://119.78.100.204/handle/2XEOYT63/18888]  
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.Huazhong Univ Sci & Technol, Tongji Med Coll, Union Hosp, Dept Pathol, Wuhan, Peoples R China
2.Chinese Acad Sci, Shenzhen Inst Adv Technol, 1068 Xueyuan Ave, Shenzhen 518055, Peoples R China
3.Univ Chinese Acad Sci, Shenzhen Coll Adv Technol, Shenzhen, Peoples R China
4.Chongqing Univ, Sch Microelect & Commun Engn, Chongqing, Peoples R China
5.Sun Yat Sen Univ, Dept Pathol, Canc Ctr, Guangzhou, Peoples R China
6.Stanford Univ, Dept Radiat Oncol, Stanford, CA USA
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.

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。