Artificial intelligence and colon capsule endoscopy: automatic detection of blood in colon capsule endoscopy using a convolutional neural network

Colon capsule endoscopy is a non-invasive alternative to conventional colonoscopy. Nevertheless, this attribute is downsized by significant drawbacks, mainly the time required for reading the images. Automated tools are expected to mitigate these limitations. On the last issue of Endoscopy International Open, our group describe the development of a deep learning algorithm for automatic detection of colonic blood and hematic residues in colon capsule endoscopy. Our tool had a sensitivity of 100% and a specificity of 93% for the detection of blood in the lumen of the colon. This specific article was recommended by Faculty Opinions member Professor Marco Pennazio. This article paves the way for further development of artificial intelligence algorithms for application to colon capsule endoscopy, which may revolutionize its role in current everyday clinical practice. You can find the complete article here.

In Press // July 2021