Self-Supervised Polyp Re-Identification in Colonoscopy
This addresses the need for robust polyp tracking in colonoscopy to improve computer-aided diagnosis and reporting, though it is incremental as it builds on existing detection methods.
The paper tackles the problem of tracking polyps across multiple frames in colonoscopy videos, which is needed for downstream tasks like polyp characterization, by proposing a self-supervised re-identification method based on visual appearance, and demonstrates its value with quantitative evaluation for CADx.
Computer-aided polyp detection (CADe) is becoming a standard, integral part of any modern colonoscopy system. A typical colonoscopy CADe detects a polyp in a single frame and does not track it through the video sequence. Yet, many downstream tasks including polyp characterization (CADx), quality metrics, automatic reporting, require aggregating polyp data from multiple frames. In this work we propose a robust long term polyp tracking method based on re-identification by visual appearance. Our solution uses an attention-based self-supervised ML model, specifically designed to leverage the temporal nature of video input. We quantitatively evaluate method's performance and demonstrate its value for the CADx task.