文献类型：期刊文献

英文题名：Automatic Pancreatic Ductal Adenocarcinoma Detection in Whole Slide Images Using Deep Convolutional Neural Networks

作者：Fu, Hao[1];Mi, Weiming[2];Pan, Boju[3];Guo, Yucheng[4,5];Li, Junjie[3];Xu, Rongyan[6];Zheng, Jie[4,5];Zou, Chunli[4,5];Zhang, Tao[2];Liang, Zhiyong[3];Zou, Junzhong[1];Zou, Hao[4,5]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Dept Automat, Shanghai, Peoples R China;[2]Tsinghua Univ, Sch Informat Sci & Technol, Dept Automat, Beijing, Peoples R China;[3]Peking Union Med Coll & Chinese Acad Med Sci, Mol Pathol Res Ctr, Dept Pathol, Peking Union Med Coll Hosp PUMCH, Beijing, Peoples R China;[4]Tsimage Med Technol, Yihai Ctr, Shenzhen, Peoples R China;[5]Tsinghua Univ Shenzhen, Ctr Intelligent Med Imaging & Hlth, Res Inst, Shenzhen, Peoples R China;[6]Chinese Acad Sci, Shanghai Chenshan Plant Sci Res Ctr, Shanghai, Peoples R China

年份：2021

卷号：11

外文期刊名：FRONTIERS IN ONCOLOGY

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000670911900001)】；

基金：This work was supported by the Foundation of Beijing Municipal Science and Technology Commission(Z181100001918004), the National Key Research and Development Program of China (2018YFF0301102 and 2018YFF0301105), and the National Natural Science Foundation of China (Nos.61976091).

语种：英文

外文关键词：pancreatic ductal adenocarcinoma (PDAC); histology; deep learning; convolutional neural network; whole-slide image analysis

摘要：Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest cancer types worldwide, with the lowest 5-year survival rate among all kinds of cancers. Histopathology image analysis is considered a gold standard for PDAC detection and diagnosis. However, the manual diagnosis used in current clinical practice is a tedious and time-consuming task and diagnosis concordance can be low. With the development of digital imaging and machine learning, several scholars have proposed PDAC analysis approaches based on feature extraction methods that rely on field knowledge. However, feature-based classification methods are applicable only to a specific problem and lack versatility, so that the deep-learning method is becoming a vital alternative to feature extraction. This paper proposes the first deep convolutional neural network architecture for classifying and segmenting pancreatic histopathological images on a relatively large WSI dataset. Our automatic patch-level approach achieved 95.3% classification accuracy and the WSI-level approach achieved 100%. Additionally, we visualized the classification and segmentation outcomes of histopathological images to determine which areas of an image are more important for PDAC identification. Experimental results demonstrate that our proposed model can effectively diagnose PDAC using histopathological images, which illustrates the potential of this practical application.