Artificial intelligence for small bowel lesions at endoscopy
Research type
Research Study
Full title
Development and Validation of an Artificial Intelligence System for Detection and Characterization of Small Bowel Mucosal Atrophy in Coeliac Disease and Non-Coeliac Enteropathies: A Multicentre International Observational Study
IRAS ID
355623
Contact name
Reena Sidhu
Contact email
Sponsor organisation
Sheffield Teaching Hospitals NHS Foundation Trust, Clinical Research Office
Duration of Study in the UK
2 years, 6 months, 1 days
Research summary
Small bowel mucosal atrophy is a key feature in coeliac disease. Atrophy can have a patchy distribution and the extent of disease cannot be assessed by means of standard endoscopy (oesophago-gastro-duodenoscopy) The reason is that this only examines up to the proximal duodenum. Capsule endoscopy allows for the visualization of the mucosa of the small bowel in its entire length. However, the reporting can be subjective.
The development of objective, reproducible, and accurate diagnostic tools is essential to improve the detection and characterization of small intestinal mucosal lesions in coeliac disease and non-coeliac enteropathies.
The application of artificial intelligence to small intestine endoscopic imaging promises to improve the detection and evaluation of mucosal lesions in these conditions by providing objective and reproducible findings. This will reduce the reader bias and improve diagnostic accuracy.
This is an international study, involving several capsule reading centres in Europe and the UK, that aims to develop and validate a prototype artificial intelligence system for the detection and characterization of small intestinal mucosal atrophy and other pathological findings of the intestine.REC name
London - Bloomsbury Research Ethics Committee
REC reference
25/PR/1242
Date of REC Opinion
20 Oct 2025
REC opinion
Further Information Favourable Opinion