Comparison of Flat Colorectal Lesion Detection by Artificial Intelligence-assisted Colonoscopy Versus Endoscopists

Trial Title: Comparison of Flat Colorectal Lesion Detection by Artificial Intelligence-assisted Colonoscopy Versus Endoscopists

NCT ID: NCT05942677

Condition: Flat Colorectal Lesion

Conditions: Keywords:
detection
AI
CAD
colorectal cancer
LST
adenoma
SSL

Study type: Observational

Overall status: Active, not recruiting

Study design:

Time perspective: Prospective

Intervention:

Intervention type: Procedure
Intervention name: proportion of colorectal lesions
Description: Evaluation of the proportion of colorectal lesions detected by a computer-aided detection system (CADe) compared with experienced endoscopists.
Arm group label: Colorectal lesion diagnostic

Summary: The development of artificial intelligence (AI) systems in the field of colorectal endoscopy is currently booming, colorectal cancer being, by its frequency and severity, a real public health problem. In terms of image analysis, AI is indeed able to perform many tasks simultaneously (lesion detection, classification, and segmentation) and to combine them. Lesion detection is thus the starting point of the whole chain to choose at the end the most appropriate treatment for the patient. Large-scale studies have demonstrated the superiority of artificial intelligence-assisted detection over the usual detection by gastroenterologists, mainly for the detection of sub-centimeter polyps. However, the investigators have shown that a recent computer-aided detection system (CADe) such as the ENDO-AID software in combination with the EVIS X1 video column (Olympus, Tokyo, Japan) may present difficulties in the detection of flat lesions such as sessile serrated lesions (SSLs) and non-granular laterally spreading tumors (LST-NGs). This represents a major challenge because in addition to their shape being difficult to identify for the human eye in practice and where AI assistance would be of great value, these rare lesions are associated with advanced histology. In addition, the investigators recently described the case of a worrisome false negative of AI-assisted colonoscopy, which failed to detect a flat adenocarcinoma in the transverse colon. Therefore, it is important to measure the false negative rate of AI detection based on the macroscopic shape of the lesion. Comparing this rate to the human endoscopist's false negatives would improve the performance of AI for this specific lesion subtype in the future.

Criteria for eligibility:

Study pop:
Every patient referred to our center for colorectal endoscopy for investigation and/or resection of colorectal lesion can join the cohort of this study and will benefit from diagnosis and treatment by experienced endoscopists.

Sampling method: Probability Sample
Criteria:
Inclusion Criteria: - both gender patients even or older than 18 years old - patient with French Health Insurance coverage - obtaining of oral non opposition to research after loyal, clear and complete delivery of information - patients addressed to our center for colorectal lesion resection - patients presenting a colorectal lesion discovered during a diagnostic colonoscopy Exclusion Criteria: - patients with health disorders needing short procedure times - patients with no colorectal lesion - difficulty continuing colonoscopy due to poor sedation - difficulty continuing colonoscopy due to a serious adverse event - inappropriate participation after colonoscopy is completed - unwillingness to participate after colonoscopy is completed

Gender: All

Minimum age: 18 Years

Maximum age: N/A

Healthy volunteers: No

Locations:

Facility:
Name: Hôpital Edouard Herriot

Address:
City: Lyon
Zip: 69437
Country: France

Start date: January 1, 2022

Completion date: December 30, 2023

Lead sponsor:
Agency: Hospices Civils de Lyon
Agency class: Other

Source: Hospices Civils de Lyon

Record processing date: ClinicalTrials.gov processed this data on November 12, 2024

Source: ClinicalTrials.gov page: https://clinicaltrials.gov/ct2/show/NCT05942677