Deep learning in digital pathology image analysis:a survey

作     者：Shujian Deng Xin Zhang Wen Yan Eric I-Chao Chang Yubo Fan Maode Lai Yan Xu Shujian Deng;Xin Zhang;Wen Yan;Eric I-Chao Chang;Yubo Fan;Maode Lai;Yan Xu

作者机构：School of Biological Science and Medical EngineeringBeihang UniversityBeijing 100191China Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education and State Key Laboratory of Software Development EnvironmentBeihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Biomedical EngineeringBeihang UniversityBeijing 100191China Microsoft Research AsiaBeijing 100080China Department of PathologySchool of MedicineZhejiang UniversityHangzhou 310007China 

出 版 物：《Frontiers of Medicine》 (医学前沿（英文版）)

年 卷 期：2020年第14卷第4期

页      面：470-487页

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 100207[医学-影像医学与核医学] 1002[医学-临床医学] 081203[工学-计算机应用技术] 08[工学] 1010[医学-医学技术（可授医学、理学学位）] 0835[工学-软件工程] 10[医学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was supported by the National Science and Technology Major Project of the Ministry of Science and Technology of China(No.2017YFC0110903) Microsoft Research under the eHealth program the National Natural Science Foundation of China(No.81771910) the Beijing Natural Science Foundation in China(No.4152033) the Technology and Innovation Commission of Shenzhen in China(No.shenfagai2016-627) the Beijing Young Talent Project in China,the Fundamental Research Funds for the Central Universities of China(No.SKLSDE-2017ZX-08)from the State Key Laboratory of Software Development Environment in Beihang University in China,and the 111 Project in China(No.B13003) 

主　　题：pathology deep learning segmentation detection classification 

摘      要：deep learning(DL)has achieved state-of-the-art performance in many digital pathology analysis *** methods usually require hand-crafted domain-specific features,and DL methods can learn representations without manually designed *** terms of feature extraction,DL approaches are less labor intensive compared with conventional machine learning *** this paper,we comprehensively summarize recent DL-based image analysis studies in histopathology,including different tasks(e.g.,classification,semantic segmentation,detection,and instance segmentation)and various applications(e.g.,stain normalization,cell/gland/region structure analysis).DL methods can provide consistent and accurate *** is a promising tool to assist pathologists in clinical diagnosis.