Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions
Cet article passe en revue les études mettant en évidence la possibilité d'utiliser en pratique clinique l'informatique et l'intelligence artificielle pour faciliter l'interprétation des images obtenues lors d'une coloscopie et établir un diagnostic précis
Computer-aided diagnosis offers a promising solution to reduce variation in colonoscopy performance. Pooled miss rates for polyps are as high as 22%, and associated interval colorectal cancers after colonoscopy are of concern. Optical biopsy, whereby in-vivo classification of polyps based on enhanced imaging replaces histopathology, has not been incorporated into routine practice because it is limited by interobserver variability and generally only meets accepted standards in expert settings. Real-time decision-support software has been developed to detect and characterise polyps, and also to offer feedback on the technical quality of inspection. Some of the current algorithms, particularly with recent advances in artificial intelligence techniques, match human expert performance for optical biopsy. In this Review, we summarise the evidence for clinical applications of computer-aided diagnosis and artificial intelligence in colonoscopy.
The Lancet Gastroenterology & Hepatology , résumé, 2017