Artificial intelligence for detecting superficial esophageal squamous cell carcinoma under multiple endoscopic imaging modalities: A multicenter study. Issue 1 (4th October 2021)

• Record Type: Journal Article
• Authors: Yuan, Xiang‐Lei; Guo, Lin‐Jie; Liu, Wei; Zeng, Xian‐Hui; Mou, Yi; Bai, Shuai; Pan, Zhen‐Guo; Zhang, Tao; Pu, Wen‐Feng; Wen, Chun; Wang, Jun; Zhou, Zheng‐Duan; Feng, Jing; Hu, Bing
• Other Names: Yu Jun guestEditor.
• Is Part Of: Journal of gastroenterology and hepatology. Volume 37:Issue 1(2022)
• Page Start: 169
• Page End: 178
• Publication Date: 2021-10-04
• Subjects: artificial intelligence -- deep convolutional neural network -- detect -- superficial esophageal squamous cell carcinoma; Gastroenterology -- Periodicals; Digestive organs -- Diseases -- Periodicals; Liver -- Diseases -- Periodicals; Gastroenterology -- Periodicals; Liver Diseases -- Periodicals; 616.33
• DOI: 10.1111/jgh.15689
• Languages: English
• ISSNs: 0815-9319

Abstract

Abstract: Background and Aim: Diagnosis of esophageal squamous cell carcinoma (ESCC) is complicated and requires substantial expertise and experience. This study aimed to develop an artificial intelligence (AI) system for detecting superficial ESCC under multiple endoscopic imaging modalities. Methods: Endoscopic images were retrospectively collected from West China Hospital, Sichuan University as a training dataset and an independent internal validation dataset. Images from other four hospitals were used as an external validation dataset. The AI system was compared with 11 experienced endoscopists. Furthermore, videos were collected to assess the performance of the AI system. Results: A total of 53 933 images from 2621 patients and 142 videos from 19 patients were used to develop and validate the AI system. In the internal and external validation datasets, the performance of the AI system under all or different endoscopic imaging modalities was satisfactory, with sensitivity of 92.5–99.7%, specificity of 78.5–89.0%, and area under the receiver operating characteristic curves of 0.906–0.989. The AI system achieved comparable performance with experienced endoscopists. Regarding superficial ESCC confined to the epithelium, the AI system was more sensitive than experienced endoscopists on white‐light imaging (90.8% vs 82.5%, P = 0.022). Moreover, the AI system exhibited good performance in videos, with sensitivity of 89.5–100% and specificity of 73.7–89.5%. Conclusions: We developed an AI system that showed comparable performance with experienced endoscopists in detecting superficial ESCC under multiple endoscopic imaging modalities and might provide valuable support for inexperienced endoscopists, despite requiring further evaluation.