Artificial intelligence for characterization of colorectal polyps: Prospective multicenter study

• Published in: Endoscopy International Open 2024-03, Vol.12 (3), p.E413-E418
• Main Authors: De Lange, Glenn, Prouvost, Victor, Rahmi, Gabriel, Vanbiervliet, Geoffroy, Le Berre, Catherine, Mack, Sahar, Koessler, Thibaud, Coron, Emmanuel
• Format: Article
• Language: English
• Subjects: Colorectal cancer; CRC screening; Endoscopy Lower GI Tract; Original article; Polyps / adenomas
• ISSN: 2364-3722; 2196-9736
• DOI: 10.1055/a-2261-2711

Background and study aims Optical diagnosis poses challenges to implementation of "resect and discard" strategies. This study aimed to assess the feasibility and performance of a new commercially available system for colorectal polyps. Patients and methods Nine expert endoscopists in three centers performed colonoscopies using artificial intelligence-equipped colonoscopes (CAD EYE, Fujifilm). Histology and predictions were compared, with hyperplastic polyps and sessile serrated lesions grouped for analysis. Results Overall, 253 polyps in 119 patients were documented (n=152 adenomas, n=78 hyperplastic polyps, n=23 sessile serrated lesions). CAD EYE detected polyps before endoscopists in 81 of 253 cases (32%). The mean polyp size was 5.5 mm (SD 0.6 mm). Polyp morphology was Paris Ip (4 %), Is (28 %), IIa (60 %), and IIb (8 %). CAD EYE achieved a sensitivity of 80%, specificity of 83%, positive predictive value (PPV) of 96%, and negative predictive value (NPV) of 72%. Expert endoscopists had a sensitivity of 88%, specificity of 83%, PPV of 96%, and NPV of 72%. Diagnostic accuracy was similar between CAD EYE (81%) and endoscopists (86%). However, sensitivity was greater with endoscopists as compared with CAD EYE (P