Chen Shurong, Xu Louzhe, Yan Lingling, Zhang Jie, Zhou Xuefeng, Wang Jiayi, Yan Tianlian, Wang Jinghua, He Xinjue, Ma Han, Zhang Xuequn, Zhu Shenghua, Zhang Yizhen, Xu Chengfu, Gao Jianguo, Ji Xia, Bai Dezhi, Chen Yuan, Chen Hongda, Ke Yini, Li Lan, Yu Chaohui, Mao Xinli, Li Ting, Chen Yi
Department of Gastroenterology, the First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, China.
Institute of Biomedical Engineering, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin, China.
Endoscopy. 2025 Apr;57(4):299-309. doi: 10.1055/a-2451-3071. Epub 2024 Oct 24.
Autoimmune gastritis (AIG), distinct from Helicobacter pylori-associated atrophic gastritis (HpAG), is underdiagnosed due to limited awareness. This multicenter study aimed to develop a novel endoscopic artificial intelligence (AI) system for assisting in AIG diagnosis.
Patients diagnosed with AIG, HpAG, or nonatrophic gastritis (NAG), were retrospectively enrolled from six centers. Endoscopic images with relevant demographic and medical data were collected for development of the AI-assisted system based on a multi-site feature fusion model. The diagnostic performance of the AI model was evaluated in internal and external datasets. Endoscopists' performance with and without AI support was tested and compared using Mann-Whitney U test. Heatmap analysis was performed to interpret AI model outputs.
18 828 endoscopy images from 1070 patients (294 AIG, 386 HpAG, 390 NAG) were collected. On testing datasets, AI identified AIG with 96.9 % sensitivity, 92.2 % specificity, and area under the receiver operating characteristic curve (AUROC) of 0.990 (internal), and 90.3 % sensitivity, 93.1 % specificity, and AUROC of 0.973 (external). The performance of AI (sensitivity 91.3 %) was comparable to that of experts (87.3 %) and significantly outperformed nonexperts (70.0 %; = 0.01). With AI support, the overall performance of endoscopists was improved (sensitivity 90.3 % [95 %CI 86.0 %-93.2 %] vs. 78.7 % [95 %CI 73.6 %-83.2 %]; = 0.008). Heatmap analysis revealed consistent focus of AI on atrophic areas.
This novel AI system demonstrated expert-level performance in identifying AIG and enhanced the diagnostic ability of endoscopists. Its application could be useful in guiding biopsy sampling and improving early detection of AIG.
自身免疫性胃炎（AIG）与幽门螺杆菌相关性萎缩性胃炎（HpAG）不同，由于认识有限，其诊断不足。这项多中心研究旨在开发一种新型内镜人工智能（AI）系统，以协助AIG诊断。
从六个中心回顾性纳入诊断为AIG、HpAG或非萎缩性胃炎（NAG）的患者。收集具有相关人口统计学和医学数据的内镜图像，用于基于多部位特征融合模型开发AI辅助系统。在内部和外部数据集中评估AI模型的诊断性能。使用Mann-Whitney U检验测试并比较内镜医师在有和没有AI支持下的表现。进行热图分析以解释AI模型输出。
收集了来自1070例患者（294例AIG、386例HpAG、390例NAG）的18828张内镜图像。在测试数据集中，AI识别AIG的灵敏度为96.9%，特异度为92.2%，受试者操作特征曲线下面积（AUROC）为0.990（内部），灵敏度为90.3%，特异度为93.1%，AUROC为0.973（外部）。AI的表现（灵敏度91.3%）与专家相当（87.3%），且显著优于非专家（70.0%；P=0.01）。在AI支持下，内镜医师的总体表现得到改善（灵敏度90.3% [95%CI 86.0%-93.2%] 对78.7% [95%CI 73.6%-83.2%]；P=0.008）。热图分析显示AI始终聚焦于萎缩区域。
这种新型AI系统在识别AIG方面表现出专家级水平，并提高了内镜医师的诊断能力。其应用可能有助于指导活检采样并改善AIG的早期检测。
