Xintian Yang1,2, Han Wang3, Qian Dong1,2, Yonghong Xu4, Hua Liu4, Xiaoying Ma5, Jing Yan4, Qian Li4, Chenyu Yang1,2, Xiaoyu Li4. 1. Department of Pediatric Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China. 2. Shandong Key Laboratory of Digital Medicine and Computer Assisted Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China. 3. Department of Pathology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, China. 4. Department of Gastroenterology, The Affiliated Hospital of Qingdao University, Qingdao, China. 5. Department of Gastroenterology, Qingdao Municipal Hospital, Qingdao, China.
Abstract
BACKGROUND: Gastrointestinal stromal tumors (GISTs) and gastrointestinal leiomyomas (GILs) are the most common subepithelial lesions (SELs). All GISTs have malignant potential; however, GILs are considered benign. Current imaging cannot effectively distinguish GISTs from GILs. We aimed to develop an artificial intelligence (AI) system to differentiate these tumors using endoscopic ultrasonography (EUS). METHODS: The AI system was based on EUS images of patients with histologically confirmed GISTs or GILs. Participants from four centers were collected to develop and retrospectively evaluate the AI-based system. The system was used when endosonographers considered SELs to be GISTs or GILs. It was then used in a multicenter prospective diagnostic test to clinically explore whether joint diagnoses by endosonographers and the AI system can distinguish between GISTs and GILs to improve the total diagnostic accuracy for SELs. RESULTS: The AI system was developed using 10 439 EUS images from 752 participants with GISTs or GILs. In the prospective test, 132 participants were histologically diagnosed (36 GISTs, 44 GILs, and 52 other types of SELs) among 508 consecutive subjects. Through joint diagnoses, the total accuracy of endosonographers in diagnosing the 132 histologically confirmed participants increased from 69.7 % (95 % confidence interval [CI] 61.4 %-76.9 %) to 78.8 % (95 %CI 71.0 %-84.9 %; P = 0.01). The accuracy of endosonographers in diagnosing the 80 participants with GISTs or GILs increased from 73.8 % (95 %CI 63.1 %-82.2 %) to 88.8 % (95 %CI 79.8 %-94.2 %; P = 0.01). CONCLUSIONS: We developed an AI-based EUS diagnostic system that can effectively distinguish GISTs from GILs and improve the diagnostic accuracy of SELs. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany.
BACKGROUND: Gastrointestinal stromal tumors (GISTs) and gastrointestinal leiomyomas (GILs) are the most common subepithelial lesions (SELs). All GISTs have malignant potential; however, GILs are considered benign. Current imaging cannot effectively distinguish GISTs from GILs. We aimed to develop an artificial intelligence (AI) system to differentiate these tumors using endoscopic ultrasonography (EUS). METHODS: The AI system was based on EUS images of patients with histologically confirmed GISTs or GILs. Participants from four centers were collected to develop and retrospectively evaluate the AI-based system. The system was used when endosonographers considered SELs to be GISTs or GILs. It was then used in a multicenter prospective diagnostic test to clinically explore whether joint diagnoses by endosonographers and the AI system can distinguish between GISTs and GILs to improve the total diagnostic accuracy for SELs. RESULTS: The AI system was developed using 10 439 EUS images from 752 participants with GISTs or GILs. In the prospective test, 132 participants were histologically diagnosed (36 GISTs, 44 GILs, and 52 other types of SELs) among 508 consecutive subjects. Through joint diagnoses, the total accuracy of endosonographers in diagnosing the 132 histologically confirmed participants increased from 69.7 % (95 % confidence interval [CI] 61.4 %-76.9 %) to 78.8 % (95 %CI 71.0 %-84.9 %; P = 0.01). The accuracy of endosonographers in diagnosing the 80 participants with GISTs or GILs increased from 73.8 % (95 %CI 63.1 %-82.2 %) to 88.8 % (95 %CI 79.8 %-94.2 %; P = 0.01). CONCLUSIONS: We developed an AI-based EUS diagnostic system that can effectively distinguish GISTs from GILs and improve the diagnostic accuracy of SELs. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany.