Endoluminal Image Analysis with the Wireless Capsule Endoscopy



Wireless Capsule Endoscopy (WCE) is a clinically viable and cost-effective alternative to traditional imaging methods of the gastrointestinal tract. CCE provides several benefits to patients, clinicians, and the healthcare system, including adding urgently needed capacity to markedly strained services. Analysing CCE videos, however, is resource intensive, represents a time-consuming workload for clinicians, and slows the roll-out of CCE due to staffing constraints.

The main objective of this research project is the development of tools to support the diagnosis of different pathologies through the use of Artificial Intelligence techniques and Machine Learning techniques.



News: The National Institute of Health Research (NHIR) has funded a £1.3bn (1,54M€) clinical trial to validate an artificial intelligence system for detecting bowel polyps using an endoscopic capsule. The system based on a deep learning model developed at our lab, is able to reduce the time needed to review images by up to 80% and it improves the accuracy of experts.



This video shows how the AI system works:




Members

Pere Gilabert

Pablo Laiz

Guillem Pascual

Santi Seguí

Jordi Vitrià



Publications