Multimodal artificial intelligence for subepithelial lesion classification and characterization: a multicenter comparative study (with video).
Authors
Affiliations (9)
Affiliations (9)
- Department of Gastroenterology, The Second Affiliated Hospital of Chongqing Medical University, Linjiang Road 76#, Chongqing, Yuzhong District, China.
- Department of Gastroenterology, Affiliated Hospital of Southwest Jiaotong University, The Third People's Hospital of Chengdu, Qinglong Street 82#, Chengdu, Sichuan, China.
- Department of Gastroenterology, The Suining Central Hospital, Sunning, China.
- Department of Gastroenterology, The First People's Hospital of Liangshan Yi Autonomous Prefecture, Xichang, China.
- Department of Gastroenterology, The First People's Hospital of Chengdu, Chengdu, China.
- Department of Gastroenterology, Sichuan Mianyang 404 Hospital, Mianyang, China.
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China.
- Department of Gastroenterology, Affiliated Hospital of Southwest Jiaotong University, The Third People's Hospital of Chengdu, Qinglong Street 82#, Chengdu, Sichuan, China. [email protected].
- Department of Gastroenterology, The Second Affiliated Hospital of Chongqing Medical University, Linjiang Road 76#, Chongqing, Yuzhong District, China. [email protected].
Abstract
Subepithelial lesions (SELs) present significant diagnostic challenges in gastrointestinal endoscopy, particularly in differentiating malignant types, such as gastrointestinal stromal tumors (GISTs) and neuroendocrine tumors, from benign types like leiomyomas. Misdiagnosis can lead to unnecessary interventions or delayed treatment. To address this challenge, we developed ECMAI-WME, a parallel fusion deep learning model integrating white light endoscopy (WLE) and microprobe endoscopic ultrasonography (EUS), to improve SEL classification and lesion characterization. A total of 523 SELs from four hospitals were used to develop serial and parallel fusion AI models. The Parallel Model, demonstrating superior performance, was designated as ECMAI-WME. The model was tested on an external validation cohort (n = 88) and a multicenter test cohort (n = 274). Diagnostic performance, lesion characterization, and clinical decision-making support were comprehensively evaluated and compared with endoscopists' performance. The ECMAI-WME model significantly outperformed endoscopists in diagnostic accuracy (96.35% vs. 63.87-86.13%, p < 0.001) and treatment decision-making accuracy (96.35% vs. 78.47-86.13%, p < 0.001). It achieved 98.72% accuracy in internal validation, 94.32% in external validation, and 96.35% in multicenter testing. For distinguishing gastric GISTs from leiomyomas, the model reached 91.49% sensitivity, 100% specificity, and 96.38% accuracy. Lesion characteristics were identified with a mean accuracy of 94.81% (range: 90.51-99.27%). The model maintained robust performance despite class imbalance, confirmed by five complementary analyses. Subgroup analyses showed consistent accuracy across lesion size, location, or type (p > 0.05), demonstrating strong generalizability. The ECMAI-WME model demonstrates excellent diagnostic performance and robustness in the multiclass SEL classification and characterization, supporting its potential for real-time deployment to enhance diagnostic consistency and guide clinical decision-making.