Subscribe to RSS
The recent explosion of artificial intelligence (AI) technologies gives us cause for optimism about the adoption of AI in colonoscopy. The use of AI for polyp detection is reported to increase the adenoma detection rate by roughly 50 % . However, to benefit from AI improvements in polyp detection, the endoscopist must successfully expose the mucosal surface. McGill et al. have tackled this operator-dependent barrier by using an AI-based 3-dimensional reconstruction model to identify blind spots during colonoscopy . This will lead to significant clinical gains, because endoscopists will potentially improve mucosal surface inspection in real time using this technology and, after a colonoscopy, will have feedback about the proportion of the mucosa that was actually exposed. Another author group in China has shown actual clinical benefits from using a similar technology . Revolution in colonoscopy never ceases!
24 November 2021 (online)
© 2021. Thieme. All rights reserved.
Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany
- 1 Barua I, Vinsard DG, Jodal HC. et al. Artificial intelligence for polyp detection during colonoscopy: a systematic review and meta-analysis. Endoscopy 2021; 53: 277-284
- 2 McGill SK, Rosenman J, Wang R. et al. Artificial intelligence identifies and quantifies colonoscopy blind spots. Endoscopy 2021; DOI: 10.1055/a-1346-7455.
- 3 Gong D, Wu L, Zhang J. et al. Detection of colorectal adenomas with a real-time computer-aided system (ENDOANGEL): a randomised controlled study. Lancet Gastroenterol Hepatol 2020; 5: 352-361