Artificial Intelligence for Real-time Detection and Monitoring of Colorectal Polyps

Official Title

Artificial Intelligence for Real-time Detection and Monitoring of Colorectal Polyps


The investigators hypothesize that the clinical implementation of an AI system is an optimal tool to monitor, audit and improve the detection and classification of polyps during colonoscopy. The objectives of this study are to generate preliminary data to evaluate the effectiveness of AI-assisted colonoscopy on: a) the rate of detection of adenomas; b) the histological classification of polyps (which would reduce the need for pathological evaluation of polyps); c) the automatic evaluation of the quality of colonoscopy.

Trial Description

Primary Outcome:

  • Number of adenomas detected
  • Evaluation of the automatic report of the colonoscopy quality indicators
Secondary Outcome:
  • Polyp miss rate (PMR)
  • prediction of polyp histology
In this trial, the investigators aim to evaluate the followings: 1. the accuracy of automatic detection of important anatomical landmarks (i.e., ileocecal valve, appendiceal orifice); 2. the accuracy of automatic detection of polyps/adenomas (PDR/ADR); 3. the accuracy of computer-assissted optical diagnosis of polyps size 1-10 mm compared to the results of the histopathological examinations of the polyps as the reference standard, and to the endocopists' prediction of polyps' histology; 4. the polyp miss rate (PMR) through verifying the short video sequences of the polyps identified by the AI machine by the expert endoscopist(s); 5. the accuracy of automatic calculation of withdrawal time by the AI machine compared to the reported withdrawal time by the endoscopists.

View this trial on

Interested in this trial?

Print this page and take it to your doctor to discuss your eligibilty and treatment options. Only your doctor can refer you to a clinical trial.


Canadian Cancer Society

These resources are provided in partnership with the Canadian Cancer Society