A deep learning model and human-machine fusion for prediction of EBV-associated gastric cancer from histopathology

Xueyi Zheng, Ruixuan Wang, Xinke Zhang, Yan Sun, Haohuan Zhang, Zihan Zhao, Yuanhang Zheng, Jing Luo, Jiangyu Zhang, Hongmei Wu, Dan Huang, Wenbiao Zhu, Jianning Chen, Qinghua Cao, Hong Zeng, Rongzhen Luo, Peng Li, Lilong Lan, Jingping Yun, Dan Xie, Wei-Shi Zheng (), Junhang Luo () and Muyan Cai ()
Additional contact information
Xueyi Zheng: Sun Yat-sen University Cancer Center
Ruixuan Wang: Sun Yat-sen University
Xinke Zhang: Sun Yat-sen University Cancer Center
Yan Sun: Tianjin Medical University Cancer Institute and Hospital
Haohuan Zhang: Sun Yat-sen University
Zihan Zhao: Sun Yat-sen University Cancer Center
Yuanhang Zheng: Sun Yat-sen University
Jing Luo: Sun Yat-sen University
Jiangyu Zhang: Affiliated Cancer Hospital & Institute of Guangzhou Medical University
Hongmei Wu: Guangdong Academy of Medical Sciences
Dan Huang: Fudan University Shanghai Cancer Center
Wenbiao Zhu: Meizhou People’s Hospital
Jianning Chen: Sun Yat-sen University
Qinghua Cao: Sun Yat-sen University
Hong Zeng: Sun Yat-Sen University
Rongzhen Luo: Sun Yat-sen University Cancer Center
Peng Li: Sun Yat-sen University Cancer Center
Lilong Lan: Sun Yat-sen University Cancer Center
Jingping Yun: Sun Yat-sen University Cancer Center
Dan Xie: Sun Yat-sen University Cancer Center
Wei-Shi Zheng: Sun Yat-sen University
Junhang Luo: Sun Yat-Sen University
Muyan Cai: Sun Yat-sen University Cancer Center

Nature Communications, 2022, vol. 13, issue 1, 1-12

Abstract: Abstract Epstein–Barr virus-associated gastric cancer (EBVaGC) shows a robust response to immune checkpoint inhibitors. Therefore, a cost-efficient and accessible tool is needed for discriminating EBV status in patients with gastric cancer. Here we introduce a deep convolutional neural network called EBVNet and its fusion with pathologists for predicting EBVaGC from histopathology. The EBVNet yields an averaged area under the receiver operating curve (AUROC) of 0.969 from the internal cross validation, an AUROC of 0.941 on an external dataset from multiple institutes and an AUROC of 0.895 on The Cancer Genome Atlas dataset. The human-machine fusion significantly improves the diagnostic performance of both the EBVNet and the pathologist. This finding suggests that our EBVNet could provide an innovative approach for the identification of EBVaGC and may help effectively select patients with gastric cancer for immunotherapy.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nature.com/articles/s41467-022-30459-5 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:13:y:2022:i:1:d:10.1038_s41467-022-30459-5

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

DOI: 10.1038/s41467-022-30459-5

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 ().