Machine learning-based colorectal cancer detection

Abstract

Colorectal capsule endoscopy (CCE) is a potentially valuable patient-friendly technique for colorectal cancer screening in large populations. However, before it can be widely applied, significant research priorities need to be addressed. In this study, we present an innovative machine learning-based algorithm which can considerably improve acquisition and analysis of relevant data on colorectal polyps obtained from capsule endoscopy. The algorithm is to match CCE and colonoscopy polyps, based on objective measures of similarity between polyps. our matching algorithm is able to objectively quantify the similarity between CCE and colonoscopy polyps based on their size, morphology and location, and provides a one-to-one unequivocal match between CCE and colonoscopy polyps.