Improving CCE video review time with a model based on frame similarity

Pere Gilabert, Santi Seguí

Abstract: Many advances have been made in the detection of pathologies through the use of the Colon Capsule Endoscopy (CCE), a non-invasive procedure that allows physicians to view the entire interior of a patient’s digestive system without the need for sedation. In this article we focus on the subsequent process, assuming that we already have a good model to detect a pathology (polyps in this case) and see how to improve the video review process by re-sorting the high score frames. With a simple sorting method, we obtain a 7% improvement compared to the linear method where the frames are reviewed in decreasing order of score. This accuracy boost occurs in the first 100 frames, which allows the videos to be reviewed more quickly and efficiently.

Registration: I acknowledge that acceptance of this work at MIDL requires at least one of the authors to register and present the work during the conference.

Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.

Paper Type: novel methodological ideas without extensive validation

Primary Subject Area: Detection and Diagnosis

Secondary Subject Area: Application: Other

Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.