Endoscopy 2022; 54(11): 1124
DOI: 10.1055/a-1884-3297


Marco Spadaccini
1   Humanitas Clinical and Research Center, Digestive Endoscopy Unit, Division of Gastroenterology, Rozzano, Milan, Italy
2   Department of Biomedical Sciences, Humanitas University, Rozzano, Milan, Italy
Klaus Mönkemüller
3   Department of Gastroenterology, Ameos Klinikum University Teaching Hospital, Halberstadt, Germany
4   University of Belgrade, Belgrade, Serbia
5   Prof. Carolina Olano Gossweiler Clínica de Gastroenterología, Universidad de La República, Montevideo, Uruguay
› Author Affiliations

Artificial intelligence (AI) is assumed to improve the detection of colorectal lesions, thus helping to reduce the risk of interval cancer after screening colonoscopy [1] [2] [3]. However, endoscopists need to be aware that AI systems should be used to assist and not to replace them. As a matter of concrete experience, this video underlines the crucial role of the endoscopist, who is ultimately in charge and responsible for detecting lesions underrepresented in AI training datasets (i. e., flat lesions such as sessile serrated lesions, and nongranular laterally spreading lesions) by performing a thorough and methodical inspection, using both proper mucosal exposure and applying human visual detection skills. In the future, the capability of AI systems to detect flat and subtle lesions will likely be improved, hopefully minimizing the risk of missing important premalignant lesions; however, we do not envisage a day when the role of the endoscopist becomes negligible.

Publication History

Article published online:
27 October 2022

© 2022. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany