Performance of artificial intelligence for detection of subtle and advanced colorectal neoplasia

• Published in: Digestive endoscopy Vol. 34; no. 4; pp. 862 - 869
• Main Authors: Ahmad, Omer F., González‐Bueno Puyal, Juana, Brandao, Patrick, Kader, Rawen, Abbasi, Faisal, Hussein, Mohamed, Haidry, Rehan J., Toth, Daniel, Mountney, Peter, Seward, Ed, Vega, Roser, Stoyanov, Danail, Lovat, Laurence B.
• Format: Journal Article
• Language: English
• Published: Australia 01.05.2022
• Subjects: Algorithms; Artificial Intelligence; colonic polyps; Colonic Polyps - diagnosis; Colonic Polyps - pathology; Colonoscopy; colorectal neoplasms; Colorectal Neoplasms - diagnosis; Colorectal Neoplasms - pathology; deep learning; Humans; deep learning; colonoscopy; colorectal neoplasms; artificial intelligence; colonic polyps
• ISSN: 0915-5635; 1443-1661
• DOI: 10.1111/den.14187

Objectives There is uncertainty regarding the efficacy of artificial intelligence (AI) software to detect advanced subtle neoplasia, particularly flat lesions and sessile serrated lesions (SSLs), due to low prevalence in testing datasets and prospective trials. This has been highlighted as a top research priority for the field. Methods An AI algorithm was evaluated on four video test datasets containing 173 polyps (35,114 polyp‐positive frames and 634,988 polyp‐negative frames) specifically enriched with flat lesions and SSLs, including a challenging dataset containing subtle advanced neoplasia. The challenging dataset was also evaluated by eight endoscopists (four independent, four trainees, according to the Joint Advisory Group on gastrointestinal endoscopy [JAG] standards in the UK). Results In the first two video datasets, the algorithm achieved per‐polyp sensitivities of 100% and 98.9%. Per‐frame sensitivities were 84.1% and 85.2%. In the subtle dataset, the algorithm detected a significantly higher number of polyps (P < 0.0001), compared to JAG‐independent and trainee endoscopists, achieving per‐polyp sensitivities of 79.5%, 37.2% and 11.5%, respectively. Furthermore, when considering subtle polyps detected by both the algorithm and at least one endoscopist, the AI detected polyps significantly faster on average. Conclusions The AI based algorithm achieved high per‐polyp sensitivities for advanced colorectal neoplasia, including flat lesions and SSLs, outperforming both JAG independent and trainees on a very challenging dataset containing subtle lesions that could have been overlooked easily and contribute to interval colorectal cancer. Further prospective trials should evaluate AI to detect subtle advanced neoplasia in higher risk populations for colorectal cancer.