Development and application of an artificial intelligence-assisted endoscopic system for automatic and accurate diagnosis of colorectal ulcers.

OBJECTIVES: Crohn's disease (CD), ulcerative colitis (UC), intestinal Behçet's disease (BD), intestinal tuberculosis (ITB), and primary intestinal lymphoma (PIL) are major intestinal disorders that frequently present with mucosal ulceration. Accurate differentiation among these conditions is challenging due to overlapping clinical, endoscopic, and imaging characteristics. Accordingly, this study aimed to develop an artificial intelligence (AI)-assisted endoscopic diagnostic system to accurately identify these five diseases.

METHODS: This multicenter prospective study used endoscopic images from patients diagnosed with pathologically confirmed CD, UC, BD, ITB, and PIL to develop an AI system that uses convolutional neural networks (CNNs) and transformer architectures. It was validated across multiple centers compared with endoscopist performance, and assessed prospectively. In addition, clinical data were integrated to construct a comprehensive diagnostic model.

RESULTS: Internal validation revealed that the AI system achieved an accuracy of 96.8%, with sensitivities for the five ulcerative diseases ranging from 76.9% to 97.8%. In the multicenter test (Test A&#x2009;+&#x2009;Test B3), diagnostic accuracy reached 83.4%, outperforming endoscopists. Prospective evaluation revealed that AI system demonstrated significantly higher accuracy than senior endoscopists (83.4% versus 59.4%, P&#x2009;<&#x2009;0.001). Moreover, the optimal comprehensive model, which combined clinical and endoscopic data, achieved an accuracy of 76.3%.

CONCLUSIONS: An AI-assisted endoscopic diagnostic system that accurately differentiates CD, UC, BD, ITB, and PIL was developed, which may contribute to improving diagnostic precision for colorectal ulcerative diseases.