Improving CCE video review time with a model based on frame similarity
Pere Gilabert, Santi Seguí
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.
Friday 8th July
Poster Session 3.2 - onsite 11:00 - 12:00, virtual 15:20 - 16:20 (UTC+2)