Published online Dec 21, 2020. doi: 10.3748/wjg.v26.i47.7436
Peer-review started: October 13, 2020
First decision: November 13, 2020
Revised: November 18, 2020
Accepted: November 29, 2020
Article in press: November 29, 2020
Published online: December 21, 2020
Artificial intelligence (AI) systems, especially after the successful application of Convolutional Neural Networks, are revolutionizing modern medicine. Gastrointestinal Endoscopy has shown to be a fertile terrain for the development of AI systems aiming to aid endoscopists in various aspects of their daily activity. Lesion detection can be one of the two main aspects in which AI can increase diagnostic yield and abilities of endoscopists. In colonoscopy, it is well known that a substantial rate of missed neoplasia is still present, representing the major cause of interval cancer. In addition, an extremely high variability in adenoma detection rate, the main key quality indicator in colonoscopy, has been extensively reported. The other domain in which AI is believed to have a considerable impact on everyday clinical practice is lesion characterization and aid in “optical diagnosis”. By predicting in vivo histology, such pathology costs may be averted by the implementation of two separate but synergistic strategies, namely the “leave-in-situ” strategy for < 5 mm hyperplastic lesions in the rectosigmoid tract, and “resect and discard” for the other diminutive lesions. In this opinion review we present current available evidence regarding the role of AI in improving lesions’ detection and characterization during colonoscopy.
Core Tip: Artificial intelligence systems using deep learning techniques are constantly developing in all fields of medicine including diagnostic colonoscopy. They aim to become part of daily routine and eliminate inherent examination’s shortcomings and lead to a higher level of provided health services. In this opinion review we present the existing evidence regarding the impact of artificial intelligence systems on the improvement of colonoscopy’s outcomes, namely adenoma detection rate and adenoma miss rate, focusing mainly on clinical trials and meta-analyses evaluating real-time computer aided detection and characterization.