Artificial intelligence for dysplasia detection during surveillance colonoscopy in patients with ulcerative colitis: A cross-sectional, non-inferiority, diagnostic test comparison study

Background and study aim: High-definition virtual chromoendoscopy, along with targeted biopsies, is recommended for dysplasia surveillance in ulcerative colitis patients at risk for colorectal cancer. Computer-aided detection (CADe) systems aim to improve colonic adenoma detection, however their efficacy in detecting polyps and adenomas in this context remains unclear. This study evaluates the CADe DiscoveryTM system's effectiveness in detecting colonic dysplasia in ulcerative colitis patients at risk for colorectal cancer. Patients and methods: A prospective cross-sectional, non-inferiority, diagnostic test comparison study was conducted on ulcerative colitis patients undergoing colorectal cancer surveillance colonoscopy between January 2021 and April 2021. Patients underwent virtual chromoendoscopy (VCE) with iSCAN 1 and 3 with optical enhancement. One endoscopist, blinded to CADe DiscoveryTM system results, examined colon sections, while a second endoscopist concurrently reviewed CADe images. Suspicious areas detected by both techniques underwent resection. Proportions of dysplastic lesions and patients with dysplasia detected by VCE or CADe were calculated. Results: Fifty-two patients were included, and 48 lesions analyzed. VCE and CADe each detected 9 cases of dysplasia (21.4% and 20.0%, respectively; p = 0.629) in 8 patients and 7 patients (15.4% vs. 13.5%, respectively; p = 0.713). Sensitivity, specificity, positive and negative predictive values, and diagnostic accuracy for dysplasia detection using VCE or CADe were 90% and 90%, 13% and 5%, 21% and 2%, 83% and 67%, and 29.2% and 22.9%, respectively. Conclusions: The CADe DiscoveryTM system shows similar diagnostic performance to VCE with iSCAN in detecting colonic dysplasia in ulcerative colitis patients at risk for colorectal cancer. (c) 2024 Elsevier Espana, S.L.U. All rights are reserved, including those for text and data mining, AI training, and similar technologies.