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

Sponsor

Centre hospitalier de l'Université de Montréal (CHUM) (Other)

Overall Status

Recruiting

CT.gov ID

NCT04586556

Collaborator

(none)

600

Enrollment

Locations

Arm

22.4

Anticipated Duration (Months)

200

Patients Per Site

8.9

Patients Per Site Per Month

Study Details

Study Description

Brief Summary

The investigators hypothesize that the clinical implementation of a deep learning AI system is an optimal tool to monitor, audit and improve the detection and classification of polyps and other anatomical landmarks 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 automatic detection of the anatomical landmarks (i.e., ileocecal valve and appendiceal orifice).

Condition or Disease	Intervention/Treatment	Phase
Adenomatous Polyps	Diagnostic Test: Polyps detection by Artificial Intelligence	N/A

Detailed Description

In this trial, the investigators aim to evaluate the followings:

the accuracy of automatic detection of important anatomical landmarks (i.e., ileocecal valve, appendiceal orifice);
the accuracy of automatic detection of polyps/adenomas (PDR/ADR);

Study Design

Study Type:

Interventional

Anticipated Enrollment :

600 participants

Allocation:

N/A

Intervention Model:

Single Group Assignment

Intervention Model Description:

prospective, multi-endoscopist, single center, clinical study at tertiary referral center (CHUM)prospective, multi-endoscopist, single center, clinical study at tertiary referral center (CHUM)

Masking:

None (Open Label)

Primary Purpose:

Diagnostic

Official Title:

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

Actual Study Start Date :

Dec 18, 2020

Anticipated Primary Completion Date :

Nov 1, 2022

Anticipated Study Completion Date :

Nov 1, 2022

Arms and Interventions

Arm	Intervention/Treatment
Experimental: Artificial intelligence for real-time detection and monitoring of colorectal polyps A standard colonoscopy will be performed according to the standard of routine care. All optically diagnosed polyps will be removed and sent to the CHUM pathology laboratory for histopathological evaluation according to institutional standards. The AI system will capture video of the procedure in real time, and provide additional information on the detection of polyps, follow-up and prediction of pathology. The full-length colonoscopy videos will be annotated for the exact time of the identification of the anatomical landmarks, polyps, also for polyp- and procedural-related characteristics.	Diagnostic Test: Polyps detection by Artificial Intelligence The AI system will capture the live video of the procedure and the AI feedback (polyp detection, tracking, and pathology prediction) will be shown on a second screen installed next to the regular endoscopy screen. Screen A will show the regular endoscopy image and screen B will show the regular endoscopy image together with the areas that might harbor a polyp or the information to predict pathology

Arm

Intervention/Treatment

Experimental: Artificial intelligence for real-time detection and monitoring of colorectal polyps

A standard colonoscopy will be performed according to the standard of routine care. All optically diagnosed polyps will be removed and sent to the CHUM pathology laboratory for histopathological evaluation according to institutional standards. The AI system will capture video of the procedure in real time, and provide additional information on the detection of polyps, follow-up and prediction of pathology. The full-length colonoscopy videos will be annotated for the exact time of the identification of the anatomical landmarks, polyps, also for polyp- and procedural-related characteristics.

Diagnostic Test: Polyps detection by Artificial Intelligence

The AI system will capture the live video of the procedure and the AI feedback (polyp detection, tracking, and pathology prediction) will be shown on a second screen installed next to the regular endoscopy screen. Screen A will show the regular endoscopy image and screen B will show the regular endoscopy image together with the areas that might harbor a polyp or the information to predict pathology

Outcome Measures

Primary Outcome Measures

Number of polyps detected [Day 1]
Efficacy of AI assisted colonoscopy to detect the proportion of patients with at least 1 polyp. Polyp detection rate with an AI.
Evaluation of the automatic report of the colonoscopy quality indicators [Day 1]
Compare of the automatic detection of the ileocecal valve, appendiceal orifice, and the automatic calculation of the withdrawal time with manual detection

Eligibility Criteria

Criteria

Ages Eligible for Study:

45 Years to 80 Years

Sexes Eligible for Study:

All

Accepts Healthy Volunteers:

Inclusion Criteria :

Signed informed consent
Age 45-80 years
Indication to undergo a lower GI endoscopy.

Exclusion Criteria :

Coagulopathy
Poor general health, defined as an American Society of Anesthesiologists (ASA) physical status class >3
Emergency colonoscopies
Hospitalized patients
Known inflammatory bowel disease (IBD)
Patients currently in the emergency room

Contacts and Locations

Locations

	Site	City	State	Country	Postal Code
1	Université de Montréal	Montréal	Quebec	Canada	QC H3T 1J4
2	Centre Hospitalier Universitaire de Montréal	Montréal	Quebec	Canada
3	IHU Strasbourg	Strasbourg		France	67000