Artificial Intelligence for Predicting HER2 Status of Gastric Cancer Based on Whole‐Slide Histopathology Images: A Retrospective Multicenter Study

Abstract Human epidermal growth factor receptor 2 (HER2) positive gastric cancer (GC) shows a robust response to the combined therapy based HER2‐targeted therapy. The application of these therapies is highly dependent on the evaluation of tumor HER2 status. However, there are many risks and challeng...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuhan Liao, Xinhua Chen, Shupeng Hu, Bing Chen, Xinghua Zhuo, Hao Xu, Xiaojin Wu, Xiaofeng Zeng, Huimin Zeng, Donghui Zhang, Yunfei Zhi, Liang Zhao
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Advanced Science
Subjects:
Online Access:https://doi.org/10.1002/advs.202408451
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850119325593108480
author Yuhan Liao
Xinhua Chen
Shupeng Hu
Bing Chen
Xinghua Zhuo
Hao Xu
Xiaojin Wu
Xiaofeng Zeng
Huimin Zeng
Donghui Zhang
Yunfei Zhi
Liang Zhao
author_facet Yuhan Liao
Xinhua Chen
Shupeng Hu
Bing Chen
Xinghua Zhuo
Hao Xu
Xiaojin Wu
Xiaofeng Zeng
Huimin Zeng
Donghui Zhang
Yunfei Zhi
Liang Zhao
author_sort Yuhan Liao
collection DOAJ
description Abstract Human epidermal growth factor receptor 2 (HER2) positive gastric cancer (GC) shows a robust response to the combined therapy based HER2‐targeted therapy. The application of these therapies is highly dependent on the evaluation of tumor HER2 status. However, there are many risks and challenges in HER2 assessment in GC. Therefore, an economically viable and readily available instrument is requisite for distinguishing HER2 status among patients diagnosed with GC. The study has innovatively developed a deep learning model, HER2Net, which can predict the HER2 status by quantitatively calculating the proportion of HER2 high‐expression regions. The HER2Net is trained on an internal training set derived from 531 hematoxylin & eosin (H&E) whole slide images (WSI) of 520 patients. Subsequently, the performance of HER2Net is validated on an internal test set from 115 H&E WSI of 111 patients and an external multi‐center test set from 102 H&E WSI of 101 patients. The HER2Net achieves an accuracy of 0.9043 on the internal test set, and an accuracy of 0.8922 on an external test set from multiple institutes. This discovery indicates that the HER2Net can potentially offer a novel methodology for the identification of HER2‐positive GC.
format Article
id doaj-art-29a0c1c9f11c4790950a91c7746b60e3
institution OA Journals
issn 2198-3844
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Advanced Science
spelling doaj-art-29a0c1c9f11c4790950a91c7746b60e32025-08-20T02:35:40ZengWileyAdvanced Science2198-38442025-03-011210n/an/a10.1002/advs.202408451Artificial Intelligence for Predicting HER2 Status of Gastric Cancer Based on Whole‐Slide Histopathology Images: A Retrospective Multicenter StudyYuhan Liao0Xinhua Chen1Shupeng Hu2Bing Chen3Xinghua Zhuo4Hao Xu5Xiaojin Wu6Xiaofeng Zeng7Huimin Zeng8Donghui Zhang9Yunfei Zhi10Liang Zhao11Department of Pathology Nanfang Hospital Southern Medical University Guangzhou 510515 ChinaDepartment of General Surgery Nanfang Hospital Southern Medical University Guangzhou 510515 ChinaSchool of Computer Science University of Manchester Manchester M13 9PL UKDepartment of Pathology Nanfang Hospital Southern Medical University Guangzhou 510515 ChinaDepartment of Pathology Nanfang Hospital Southern Medical University Guangzhou 510515 ChinaDepartment of Pathology Nanfang Hospital Southern Medical University Guangzhou 510515 ChinaDepartment of Pathology Shunde Hospital of Southern Medical University (The First People's Hospital of Shunde) Foshan Guangdong 528399 ChinaDepartment of Pathology Shunde Hospital of Southern Medical University (The First People's Hospital of Shunde) Foshan Guangdong 528399 ChinaDepartment of Pathology Shunde Hospital of Southern Medical University (The First People's Hospital of Shunde) Foshan Guangdong 528399 ChinaDepartment of Pathology Affiliated Cancer Hospital and Institute of Guangzhou Medical University Guangzhou 510095 ChinaDepartment of Gastroenterology Chinese Academy of Medical Sciences Peking Union Medical College Hospital Beijing 100730 ChinaDepartment of Pathology Nanfang Hospital Southern Medical University Guangzhou 510515 ChinaAbstract Human epidermal growth factor receptor 2 (HER2) positive gastric cancer (GC) shows a robust response to the combined therapy based HER2‐targeted therapy. The application of these therapies is highly dependent on the evaluation of tumor HER2 status. However, there are many risks and challenges in HER2 assessment in GC. Therefore, an economically viable and readily available instrument is requisite for distinguishing HER2 status among patients diagnosed with GC. The study has innovatively developed a deep learning model, HER2Net, which can predict the HER2 status by quantitatively calculating the proportion of HER2 high‐expression regions. The HER2Net is trained on an internal training set derived from 531 hematoxylin & eosin (H&E) whole slide images (WSI) of 520 patients. Subsequently, the performance of HER2Net is validated on an internal test set from 115 H&E WSI of 111 patients and an external multi‐center test set from 102 H&E WSI of 101 patients. The HER2Net achieves an accuracy of 0.9043 on the internal test set, and an accuracy of 0.8922 on an external test set from multiple institutes. This discovery indicates that the HER2Net can potentially offer a novel methodology for the identification of HER2‐positive GC.https://doi.org/10.1002/advs.202408451deep learning modelgastric cancerhuman epidermal growth factor receptor 2whole slide images
spellingShingle Yuhan Liao
Xinhua Chen
Shupeng Hu
Bing Chen
Xinghua Zhuo
Hao Xu
Xiaojin Wu
Xiaofeng Zeng
Huimin Zeng
Donghui Zhang
Yunfei Zhi
Liang Zhao
Artificial Intelligence for Predicting HER2 Status of Gastric Cancer Based on Whole‐Slide Histopathology Images: A Retrospective Multicenter Study
Advanced Science
deep learning model
gastric cancer
human epidermal growth factor receptor 2
whole slide images
title Artificial Intelligence for Predicting HER2 Status of Gastric Cancer Based on Whole‐Slide Histopathology Images: A Retrospective Multicenter Study
title_full Artificial Intelligence for Predicting HER2 Status of Gastric Cancer Based on Whole‐Slide Histopathology Images: A Retrospective Multicenter Study
title_fullStr Artificial Intelligence for Predicting HER2 Status of Gastric Cancer Based on Whole‐Slide Histopathology Images: A Retrospective Multicenter Study
title_full_unstemmed Artificial Intelligence for Predicting HER2 Status of Gastric Cancer Based on Whole‐Slide Histopathology Images: A Retrospective Multicenter Study
title_short Artificial Intelligence for Predicting HER2 Status of Gastric Cancer Based on Whole‐Slide Histopathology Images: A Retrospective Multicenter Study
title_sort artificial intelligence for predicting her2 status of gastric cancer based on whole slide histopathology images a retrospective multicenter study
topic deep learning model
gastric cancer
human epidermal growth factor receptor 2
whole slide images
url https://doi.org/10.1002/advs.202408451
work_keys_str_mv AT yuhanliao artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT xinhuachen artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT shupenghu artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT bingchen artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT xinghuazhuo artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT haoxu artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT xiaojinwu artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT xiaofengzeng artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT huiminzeng artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT donghuizhang artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT yunfeizhi artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy
AT liangzhao artificialintelligenceforpredictingher2statusofgastriccancerbasedonwholeslidehistopathologyimagesaretrospectivemulticenterstudy