Automated Assessment of Kidney Ureteroscopy Exploration for Training

TL;DR

A novel, purely ureteroscope video-based scope localization framework that automatically identifies calyces missed by the trainee in a phantom kidney exploration and shows its ability as a valid tool that enables out-of-OR training without requiring supervision from an expert.

Abstract

Purpose: Kidney ureteroscopic navigation is challenging with a steep learning curve. However, current clinical training has major deficiencies, as it requires one-on-one feedback from experts and occurs in the operating room (OR). Therefore, there is a need for a phantom training system with automated feedback to greatly \revision{expand} training opportunities. Methods: We propose a novel, purely ureteroscope video-based scope localization framework that automatically identifies calyces missed by the trainee in a phantom kidney exploration. We use a slow, thorough, prior exploration video of the kidney to generate a reference reconstruction. Then, this reference reconstruction can be used to localize any exploration video of the same phantom. Results: In 15 exploration videos, a total of 69 out of 74 calyces were correctly classified. We achieve < 4mm camera pose localization error. Given the reference reconstruction, the system takes 10 minutes to generate the results for a typical exploration (1-2 minute long). Conclusion: We demonstrate a novel camera localization framework that can provide accurate and automatic feedback for kidney phantom explorations. We show its ability as a valid tool that enables out-of-OR training without requiring supervision from an expert.

Figures (5)

• Figure 1: The overall workflow of the framework. In stage one, a reference reconstruction is generated and registered to the CT segmentation. This reconstruction is then reused for all query exploration videos, which are localized in stage two. For each video, calyces are marked as visited/not visited.
• Figure 2: The accuracy of the SfM reconstruction point cloud compared to the CT volume. The violin plot is plotted with the 99 percentile data, as the outliers, though numerically extreme, has almost no impact on the CT registration and the subsequent pose localization.
• Figure 3: A random selection of rendered vs real ureteroscope image Pairs. (Note: the kidney stones are not in the CT view)
• Figure 4: Five example cases where the framework accurately identifies visited/missed calyces
• Figure 5: Example cases where the framework misidentified one calyx in each case. A: Phantom 2. B: Phantom 3. C: Phantom 4.