Deep Reinforcement Learning for Small Bowel Path Tracking using Different Types of Annotations
This work addresses the challenge of reducing annotation costs for small bowel path tracking in medical imaging, but it appears incremental as it adapts existing deep reinforcement learning techniques to a specific domain problem.
The paper tackled the problem of small bowel path tracking in 3D CT scans, which is costly due to the need for ground-truth annotations, by proposing a deep reinforcement learning method that uses datasets with different annotation types, resulting in a method that can utilize weakly annotated scans to reduce annotation costs.
Small bowel path tracking is a challenging problem considering its many folds and contact along its course. For the same reason, it is very costly to achieve the ground-truth (GT) path of the small bowel in 3D. In this work, we propose to train a deep reinforcement learning tracker using datasets with different types of annotations. Specifically, we utilize CT scans that have only GT small bowel segmentation as well as ones with the GT path. It is enabled by designing a unique environment that is compatible for both, including a reward definable even without the GT path. The performed experiments proved the validity of the proposed method. The proposed method holds a high degree of usability in this problem by being able to utilize the scans with weak annotations, and thus by possibly reducing the required annotation cost.