Development and validation of an AI foundation model for endoscopic diagnosis of esophagogastric junction adenocarcinoma: a cohort and deep learning study

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ma, Yikun, Li, Bo, Chen, Ying, Yue, Zijie, Xu, Shuchang, Li, Jingyao, Ma, Lei, Zhong, Liang, Zou, Duowu, Xu, Leiming, Zhong, Yunshi, Li, Xiaobo, Ding, Weiqun, Zhang, Minmin, He, Dongli, Li, Zhenghong, Chen, Ye, Zhao, Ye, Zhuo, Jialong, Wu, Xiaofen, Yi, Lisha, Shi, Miaojing, Sun, Huihui
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915508211679232
author Ma, Yikun
Li, Bo
Chen, Ying
Yue, Zijie
Xu, Shuchang
Li, Jingyao
Ma, Lei
Zhong, Liang
Zou, Duowu
Xu, Leiming
Zhong, Yunshi
Li, Xiaobo
Ding, Weiqun
Zhang, Minmin
He, Dongli
Li, Zhenghong
Chen, Ye
Zhao, Ye
Zhuo, Jialong
Wu, Xiaofen
Yi, Lisha
Shi, Miaojing
Sun, Huihui
author_facet Ma, Yikun
Li, Bo
Chen, Ying
Yue, Zijie
Xu, Shuchang
Li, Jingyao
Ma, Lei
Zhong, Liang
Zou, Duowu
Xu, Leiming
Zhong, Yunshi
Li, Xiaobo
Ding, Weiqun
Zhang, Minmin
He, Dongli
Li, Zhenghong
Chen, Ye
Zhao, Ye
Zhuo, Jialong
Wu, Xiaofen
Yi, Lisha
Shi, Miaojing
Sun, Huihui
contents The early detection of esophagogastric junction adenocarcinoma (EGJA) is crucial for improving patient prognosis, yet its current diagnosis is highly operator-dependent. This paper aims to make the first attempt to develop an artificial intelligence (AI) foundation model-based method for both screening and staging diagnosis of EGJA using endoscopic images. In this cohort and learning study, we conducted a multicentre study across seven Chinese hospitals between December 28, 2016 and December 30, 2024. It comprises 12,302 images from 1,546 patients; 8,249 of them were employed for model training, while the remaining were divided into the held-out (112 patients, 914 images), external (230 patients, 1,539 images), and prospective (198 patients, 1,600 images) test sets for evaluation. The proposed model employs DINOv2 (a vision foundation model) and ResNet50 (a convolutional neural network) to extract features of global appearance and local details of endoscopic images for EGJA staging diagnosis. Our model demonstrates satisfactory performance for EGJA staging diagnosis across three test sets, achieving an accuracy of 0.9256, 0.8895, and 0.8956, respectively. In contrast, among representative AI models, the best one (ResNet50) achieves an accuracy of 0.9125, 0.8382, and 0.8519 on the three test sets, respectively; the expert endoscopists achieve an accuracy of 0.8147 on the held-out test set. Moreover, with the assistance of our model, the overall accuracy for the trainee, competent, and expert endoscopists improves from 0.7035, 0.7350, and 0.8147 to 0.8497, 0.8521, and 0.8696, respectively. To our knowledge, our model is the first application of foundation models for EGJA staging diagnosis and demonstrates great potential in both diagnostic accuracy and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17660
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Development and validation of an AI foundation model for endoscopic diagnosis of esophagogastric junction adenocarcinoma: a cohort and deep learning study
Ma, Yikun
Li, Bo
Chen, Ying
Yue, Zijie
Xu, Shuchang
Li, Jingyao
Ma, Lei
Zhong, Liang
Zou, Duowu
Xu, Leiming
Zhong, Yunshi
Li, Xiaobo
Ding, Weiqun
Zhang, Minmin
He, Dongli
Li, Zhenghong
Chen, Ye
Zhao, Ye
Zhuo, Jialong
Wu, Xiaofen
Yi, Lisha
Shi, Miaojing
Sun, Huihui
Computer Vision and Pattern Recognition
The early detection of esophagogastric junction adenocarcinoma (EGJA) is crucial for improving patient prognosis, yet its current diagnosis is highly operator-dependent. This paper aims to make the first attempt to develop an artificial intelligence (AI) foundation model-based method for both screening and staging diagnosis of EGJA using endoscopic images. In this cohort and learning study, we conducted a multicentre study across seven Chinese hospitals between December 28, 2016 and December 30, 2024. It comprises 12,302 images from 1,546 patients; 8,249 of them were employed for model training, while the remaining were divided into the held-out (112 patients, 914 images), external (230 patients, 1,539 images), and prospective (198 patients, 1,600 images) test sets for evaluation. The proposed model employs DINOv2 (a vision foundation model) and ResNet50 (a convolutional neural network) to extract features of global appearance and local details of endoscopic images for EGJA staging diagnosis. Our model demonstrates satisfactory performance for EGJA staging diagnosis across three test sets, achieving an accuracy of 0.9256, 0.8895, and 0.8956, respectively. In contrast, among representative AI models, the best one (ResNet50) achieves an accuracy of 0.9125, 0.8382, and 0.8519 on the three test sets, respectively; the expert endoscopists achieve an accuracy of 0.8147 on the held-out test set. Moreover, with the assistance of our model, the overall accuracy for the trainee, competent, and expert endoscopists improves from 0.7035, 0.7350, and 0.8147 to 0.8497, 0.8521, and 0.8696, respectively. To our knowledge, our model is the first application of foundation models for EGJA staging diagnosis and demonstrates great potential in both diagnostic accuracy and efficiency.
title Development and validation of an AI foundation model for endoscopic diagnosis of esophagogastric junction adenocarcinoma: a cohort and deep learning study
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.17660