Unsupervised Odometry and Depth Learning for Endoscopic Capsule Robots
This work addresses the challenge of intuitive disease detection and operations in minimally invasive medical robotics, representing an incremental advancement in unsupervised learning for specific domain applications.
The paper tackled the problem of enabling endoscopic capsule robots to perform motion estimation and depth recovery in the gastrointestinal tract by introducing an unsupervised, real-time odometry and depth learning method, achieving effectiveness validated on ex-vivo porcine stomach datasets.
In the last decade, many medical companies and research groups have tried to convert passive capsule endoscopes as an emerging and minimally invasive diagnostic technology into actively steerable endoscopic capsule robots which will provide more intuitive disease detection, targeted drug delivery and biopsy-like operations in the gastrointestinal(GI) tract. In this study, we introduce a fully unsupervised, real-time odometry and depth learner for monocular endoscopic capsule robots. We establish the supervision by warping view sequences and assigning the re-projection minimization to the loss function, which we adopt in multi-view pose estimation and single-view depth estimation network. Detailed quantitative and qualitative analyses of the proposed framework performed on non-rigidly deformable ex-vivo porcine stomach datasets proves the effectiveness of the method in terms of motion estimation and depth recovery.