Active Learning for Real Time Detection of Polyps in Videocolonoscopy

In this paper a method to perform real-time detection of polyps in videocolonoscopy is introduced. Polyps are at the origins of colorectal cancer which is one of the deadliest diseases in the world. Many methods to improve detection of polyps have been proposed so far. However performance of these methods strongly depends on the available computational resources and, until now, are not able to perform real-time detection during a standard examination. The proposed method, based on active learning, is able to solve these issues. Most precisely, this approach allows us to detect approximately 90% of polyps on a freely available database introduced to the community in 2012, for a F2 score of 65%, and matches real-time constraint by making possible the analysis of a frame in only 0.023s (average value) on a standard computer not necessarily dedicated to that kind of application.