Video-Based Detection and Analysis of Errors in Robotic Surgical Training

2025-04-28

AI Summary

Automated detection of collision errors remains a critical challenge in objective assessment of dry-lab robotic surgical training. Method: This study proposes a video-based error detection and skill evolution analysis framework, integrating computer vision, motion trajectory modeling, and temporal error annotation to achieve fully automated identification of collisions during the ring-transfer task. Contribution/Results: The framework achieves ≈95% accuracy in collision detection—the first such automated solution for this task—and uncovers synergistic evolutionary patterns among training duration, error frequency, and task completion time, yielding a quantifiable dynamic model of surgical skill acquisition. Over a six-month longitudinal study, it successfully tracked concurrent reductions in error rate and task completion time across trainees, empirically validating a measurable skill progression pathway. By enabling objective, data-driven evaluation of procedural competence, this framework establishes a novel paradigm for standardized, evidence-based surgical training assessment.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Motion & Tracking
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Robot-assisted minimally invasive surgeries offer many advantages but require complex motor tasks that take surgeons years to master. There is currently a lack of knowledge on how surgeons acquire these robotic surgical skills. To help bridge this gap, we previously followed surgical residents learning complex surgical training dry-lab tasks on a surgical robot over six months. Errors are an important measure for self-training and for skill evaluation, but unlike in virtual simulations, in dry-lab training, errors are difficult to monitor automatically. Here, we analyzed the errors in the ring tower transfer task, in which surgical residents moved a ring along a curved wire as quickly and accurately as possible. We developed an image-processing algorithm to detect collision errors and achieved detection accuracy of ~95%. Using the detected errors and task completion time, we found that the surgical residents decreased their completion time and number of errors over the six months. This analysis provides a framework for detecting collision errors in similar surgical training tasks and sheds light on the learning process of the surgical residents.

Problem

• Detecting collision errors in robotic surgical training tasks
• Analyzing skill acquisition of surgical residents over time
• Developing image-processing for automated error monitoring in dry-lab

Innovation

• Video-based error detection in robotic surgery
• Image-processing algorithm for collision errors
• 95% accuracy in error detection