Towards Real-Time Polyp Detection in Colonoscopy Videos: Adapting Still Frame-Based Methodologies for Video Sequences Analysis.

International audienceColorectal cancer is the second cause of cancer death inUnited States: precursor lesions (polyps) detection is key for patientsurvival. Though colonoscopy is the gold standard screening tool, somepolyps are still missed. Several computational systems have been pro-posed but none of them are used in the clinical room mainly due to com-putational constraints. Besides, most of them are built over still framedatabases, decreasing their performance on video analysis due to the lackof output stability and not coping with associated variability on imagequality and polyp appearance. We propose a strategy to adapt thesemethods to video analysis by adding a spatio-temporal stability mod-ule and studying a combination of features to capture polyp appearancevariability. We validate our strategy, incorporated on a real-time detec-tion method, on a public video database. Resulting method detects allpolyps under real time constraints, increasing its performance due to ouradaptation strategy