Clinically applicable histopathological diagnosis system for gastric cancer detection using deep learning

Zhigang Song, Shuangmei Zou, Weixun Zhou, Yong Huang, Liwei Shao, Jing Yuan, Xiangnan Gou, Wei Jin, Zhanbo Wang, Xin Chen, Xiaohui Ding, Jinhong Liu, Chunkai Yu, Calvin Ku, Cancheng Liu, Zhuo Sun, Gang Xu, Yuefeng Wang, Xiaoqing Zhang, Dandan Wang, Shuhao Wang (), Wei Xu, Richard C. Davis and Huaiyin Shi ()
Additional contact information
Zhigang Song: The Chinese PLA General Hospital
Shuangmei Zou: Chinese Academy of Medical Sciences and Peking Union Medical College
Weixun Zhou: Peking Union Medical College Hospital
Yong Huang: The Chinese PLA General Hospital
Liwei Shao: The Chinese PLA General Hospital
Jing Yuan: The Chinese PLA General Hospital
Xiangnan Gou: The Chinese PLA General Hospital
Wei Jin: The Chinese PLA General Hospital
Zhanbo Wang: The Chinese PLA General Hospital
Xin Chen: The Chinese PLA General Hospital
Xiaohui Ding: The Chinese PLA General Hospital
Jinhong Liu: The Chinese PLA General Hospital
Chunkai Yu: Beijing Shijitan Hospital, Capital Medical University
Calvin Ku: Thorough Images
Cancheng Liu: Thorough Images
Zhuo Sun: Thorough Images
Gang Xu: Thorough Images
Yuefeng Wang: Thorough Images
Xiaoqing Zhang: Thorough Images
Dandan Wang: Peking University Health Science Center
Shuhao Wang: Thorough Images
Wei Xu: Tsinghua University
Richard C. Davis: Duke University Medical Center
Huaiyin Shi: The Chinese PLA General Hospital

Nature Communications, 2020, vol. 11, issue 1, 1-9

Abstract: Abstract The early detection and accurate histopathological diagnosis of gastric cancer increase the chances of successful treatment. The worldwide shortage of pathologists offers a unique opportunity for the use of artificial intelligence assistance systems to alleviate the workload and increase diagnostic accuracy. Here, we report a clinically applicable system developed at the Chinese PLA General Hospital, China, using a deep convolutional neural network trained with 2,123 pixel-level annotated H&E-stained whole slide images. The model achieves a sensitivity near 100% and an average specificity of 80.6% on a real-world test dataset with 3,212 whole slide images digitalized by three scanners. We show that the system could aid pathologists in improving diagnostic accuracy and preventing misdiagnoses. Moreover, we demonstrate that our system performs robustly with 1,582 whole slide images from two other medical centres. Our study suggests the feasibility and benefits of using histopathological artificial intelligence assistance systems in routine practice scenarios.

Date: 2020
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.nature.com/articles/s41467-020-18147-8 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:11:y:2020:i:1:d:10.1038_s41467-020-18147-8

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-020-18147-8

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().