Accurate diagnosis and prognosis prediction of gastric cancer using deep learning on digital pathological images: A retrospective multicentre study

To reduce the high incidence and mortality of gastric cancer (GC), we aimed to develop deep learning-based models to assist in predicting the diagnosis and overall survival (OS) of GC patients using pathological images. 2333 hematoxylin and eosin-stained pathological pictures of 1037 GC patients wer...

Full description

Saved in:
Bibliographic Details
Published in:EBioMedicine 2021-11, Vol.73, p.103631, Article 103631
Main Authors: Huang, Binglu, Tian, Shan, Zhan, Na, Ma, Jingjing, Huang, Zhiwei, Zhang, Chukang, Zhang, Hao, Ming, Fanhua, Liao, Fei, Ji, Mengyao, Zhang, Jixiang, Liu, Yinghui, He, Pengzhan, Deng, Beiying, Hu, Jiaming, Dong, Weiguo
Format: Article
Language:English
Subjects:
Algorithms
Area Under Curve
Biomarkers, Tumor
Deep Learning
Diagnosis
Female
Gastric cancer
Humans
Image Processing, Computer-Assisted - methods
Immunohistochemistry
Male
Multiple instance learning
Neoplasm Grading
Neoplasm Staging
Overall survival
Pathology, Molecular - methods
Research paper
Retrospective Studies
ROC Curve
Stomach Neoplasms - diagnosis
Stomach Neoplasms - mortality
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To reduce the high incidence and mortality of gastric cancer (GC), we aimed to develop deep learning-based models to assist in predicting the diagnosis and overall survival (OS) of GC patients using pathological images. 2333 hematoxylin and eosin-stained pathological pictures of 1037 GC patients were collected from two cohorts to develop our algorithms, Renmin Hospital of Wuhan University (RHWU) and the Cancer Genome Atlas (TCGA). Additionally, we gained 175 digital pictures of 91 GC patients from National Human Genetic Resources Sharing Service Platform (NHGRP), served as the independent external validation set. Two models were developed using artificial intelligence (AI), one named GastroMIL for diagnosing GC, and the other named MIL-GC for predicting outcome of GC. The discriminatory power of GastroMIL achieved accuracy 0.920 in the external validation set, superior to that of the junior pathologist and comparable to that of expert pathologists. In the prognostic model, C-indices for survival prediction of internal and external validation sets were 0.671 and 0.657, respectively. Moreover, the risk score output by MIL-GC in the external validation set was proved to be a strong predictor of OS both in the univariate (HR = 2.414, P 
ISSN:2352-3964
2352-3964
DOI:10.1016/j.ebiom.2021.103631