Investigating Robot Control Policy Learning for Autonomous X-ray-guided Spine Procedures

TL;DR

This study develops and evaluates imitation learning policies for robot-controlled spine procedures guided solely by bi-plane X-ray images, demonstrating promising simulation and preliminary real-world results with room for improvement.

Contribution

It introduces a realistic simulation environment and a dataset for training imitation policies for X-ray-guided spine procedures, highlighting their potential and current limitations.

Findings

Policy succeeded in 68.5% of simulated cases on first attempt

Generalized to complex anatomy including fractures

Produced plausible trajectories on real X-ray images

Abstract

Imitation learning-based robot control policies are enjoying renewed interest in video-based robotics. However, it remains unclear whether this approach applies to X-ray-guided procedures, such as spine instrumentation. This is because interpretation of multi-view X-rays is complex. We examine opportunities and challenges for imitation policy learning in bi-plane-guided cannula insertion. We develop an in silico sandbox for scalable, automated simulation of X-ray-guided spine procedures with a high degree of realism. We curate a dataset of correct trajectories and corresponding bi-planar X-ray sequences that emulate the stepwise alignment of providers. We then train imitation learning policies for planning and open-loop control that iteratively align a cannula solely based on visual information. This precisely controlled setup offers insights into limitations and capabilities of this method. Our policy succeeded on the first attempt in 68.5% of cases, maintaining safe intra-pedicular trajectories across diverse vertebral levels. The policy generalized to complex anatomy, including fractures, and remained robust to varied initializations. Rollouts on real bi-planar X-rays further suggest that the model can produce plausible trajectories, despite training exclusively in simulation. While these preliminary results are promising, we also identify limitations, especially in entry point precision. Full closed-look control will require additional considerations around how to provide sufficiently frequent feedback. With more robust priors and domain knowledge, such models may provide a foundation for future efforts toward lightweight and CT-free robotic intra-operative spinal navigation.