Automated Assessment of Kidney Ureteroscopy Exploration for Training

2026-02-17

AI Summary

Current training for renal ureteroscopy heavily relies on real-time expert supervision and lacks scalable, automated assessment tools. This work proposes the first purely video-driven, unsupervised evaluation framework capable of automatically detecting missed renal calyces using only ureteroscopic video footage. The method reconstructs a reference 3D pelvicaliceal model from prior exploration videos and identifies unvisited regions through real-time video registration and camera pose estimation. In experiments on 15 test videos, the system accurately detected 69 out of 74 calyces with a localization error under 4 mm, completing each assessment in approximately 10 minutes. This approach enables precise, expert-free feedback for ex vivo simulation training, significantly enhancing the accessibility and objectivity of procedural skill evaluation.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Video Understanding & Activity Analysis
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

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.

Problem

• ureteroscopy
• surgical training
• automated assessment
• phantom training
• kidney exploration

Innovation

• ureteroscopy
• video-based localization
• phantom training
• automated feedback
• camera pose estimation