AI tool aims to sharpen colonoscopy diagnoses
NCT ID NCT07470827
First seen Jun 27, 2026 · Last updated Jun 27, 2026
Summary
This study tests a computer program that analyzes colonoscopy images to help doctors decide if a growth (polyp) is an adenoma (pre-cancerous) or not. The software gives a probability score for each lesion. The trial involves 1,178 adults and compares the software's results to lab tissue analysis. The goal is to see if the AI can improve diagnostic accuracy.
This is an AI summary of the original study and may miss details. Read our disclaimer.
Study facts
What this study's own registry entry says, in plain language.
- Participants
-
About 1,178 people
The number the study aims to enrol. It can still change while the study runs.
- Started
-
Sep 2024
- Expected to finish
-
Dec 2026
An estimate. End dates often move.
- Lead sponsor
-
A company
The lead sponsor is a pharmaceutical, biotech, or medical-device company.
Who can take part
This study's own entry requirements. Only the study team can say for certain whether you qualify.
Who is studied
Colorectal endoscopic images from adult patients (≥19 years) who underwent colonoscopy and biopsy, with confirmed histopathology results for Adenoma or Non-Adenoma lesions.
- Ages
-
19 years and older
- Sex
-
Anyone
- Healthy volunteers
-
Not accepted
This study is not open to healthy volunteers. The entry requirements below say who it is open to.
Show the full entry requirements Hide the full entry requirements
Copied word for word from the study's registry entry, so the wording is the study team's rather than ours.
Inclusion Criteria: 1. Adult patients (≥19 years) with colorectal endoscopic images showing one lesion. 2. Histopathology confirming the lesion as Adenoma (colorectal cancer, adenoma) or Non-Adenoma (sessile serrated lesion, hyperplastic polyp). Exclusion Criteria: 1. Images previously used for training or internal validation of the investigational software. 2. History of colectomy. 3. Diagnosed with inflammatory bowel disease (e.g., ulcerative colitis, Crohn's disease) or neuroendocrine tumor. 4. Poor image quality (blurred, incomplete lesion capture). 5. Images with multiple lesions or fewer than two images per lesion. 6. Determined by the investigator to be inappropriate for inclusion.
Get updates
Get notified about this study
Sign up to get updates when this study changes or when new studies for Adenoma are added.
Genom att skicka in godkänner du våra Användarvillkor
Conditions
The condition(s) this trial relates to.
As listed by the trial registrant
The condition terms exactly as the trial's registrant entered them.
Contacts and locations
Locations
-
Yonsei University Gangnam Severance Hospital
Seoul, Gangnam, 06273, South Korea
More trials for these conditions
Other studies related to the condition(s) this trial covers.
- Gut bacteria may hold clues to why some cancer treatments work better
- Burning the edges: a new way to stop colon polyps from coming back
- Missed Follow-Up colonoscopies: do they raise the risk of advanced growths?
- A 2.2 mm scope could spot cancerous tissue in minutes, not days
- The gatekeepers of tumors: scientists probe how blood vessels let immune cells in
- New Antibody-Drug conjugate put to the test against Hard-to-Treat cancers