Teaching doctors to tell Paris-class polyps apart using real and AI-generated colon images
Training Physicians to Differentiate the Paris Classification Using Artificial Colon Polyp Images
NA · Wuerzburg University Hospital · NCT06550908
This trial tests if training doctors with AI-generated colon polyp images helps them learn to classify polyps by the Paris system better than training with real images.
Quick facts
| Phase | NA |
|---|---|
| Study type | Interventional |
| Enrollment | 70 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Wuerzburg University Hospital (other) |
| Locations | 1 site (Würzburg) |
| Trial ID | NCT06550908 on ClinicalTrials.gov |
What this trial studies
Investigators will train physicians using the Lutetia Training Platform with either collections of real colon polyp images or AI-generated (synthetic) images and then compare classification performance for the Paris system. The generative AI images are designed to be realistic, compliant with data protection rules, and can be modified to show different precancerous stages in the same lesion. Participants include physicians with and without colonoscopy experience who complete the image-based training at the University Hospital Würzburg. The primary comparison is which image source leads to more accurate polyp classification after the training.
Who should consider this trial
Good fit: Physicians, with or without prior colonoscopy experience, who can attend and complete the image-based training sessions at the University Hospital Würzburg are ideal candidates.
Not a fit: Individual patients will not directly benefit from this educational intervention, and clinicians who do not perform endoscopy or cannot apply the training in practice are unlikely to gain practical benefit.
Why it matters
Potential benefit: If successful, this approach could improve clinicians' ability to detect and correctly classify precancerous colon polyps earlier, potentially improving colorectal cancer prevention.
How similar studies have performed: Previous work shows image-based and AI-assisted training can improve polyp recognition, but using fully synthetic, generative images for clinician training is a relatively new approach.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Physicians with or without experience in colonoscopy
Where this trial is running
Würzburg
- University hospital Würzburg — Würzburg, Germany (RECRUITING)
Study contacts
- Principal investigator: Alexander Hann — Wuerzburg University Hospital
- Study coordinator: Alexander Hann, MD
- Email: hann_a@ukw.de
- Phone: 0049931201
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions: Colonic Polyp, Colon Adenoma, Colonoscopy