Safe Deep RL for Intraoperative Planning of Pedicle Screw Placement

TL;DR

This paper introduces a real-time, safe deep reinforcement learning method for intraoperative pedicle screw placement that guarantees safety and compensates for incomplete anatomical information, improving surgical accuracy.

Contribution

It presents the first safe DRL approach for orthopedic surgery, incorporating an uncertainty-aware safety filter and pre-trained anatomical knowledge for intraoperative planning.

Findings

Achieved 90% bone penetration compared to the gold standard.

Maintained safety under observation and motion uncertainty.

Demonstrated effectiveness on MRI-derived models.

Abstract

Spinal fusion surgery requires highly accurate implantation of pedicle screw implants, which must be conducted in critical proximity to vital structures with a limited view of anatomy. Robotic surgery systems have been proposed to improve placement accuracy, however, state-of-the-art systems suffer from the limitations of open-loop approaches, as they follow traditional concepts of preoperative planning and intraoperative registration, without real-time recalculation of the surgical plan. In this paper, we propose an intraoperative planning approach for robotic spine surgery that leverages real-time observation for drill path planning based on Safe Deep Reinforcement Learning (DRL). The main contributions of our method are (1) the capability to guarantee safe actions by introducing an uncertainty-aware distance-based safety filter; and (2) the ability to compensate for incomplete intraoperative anatomical information, by encoding a-priori knowledge about anatomical structures with a network pre-trained on high-fidelity anatomical models. Planning quality was assessed by quantitative comparison with the gold standard (GS) drill planning. In experiments with 5 models derived from real magnetic resonance imaging (MRI) data, our approach was capable of achieving 90% bone penetration with respect to the GS while satisfying safety requirements, even under observation and motion uncertainty. To the best of our knowledge, our approach is the first safe DRL approach focusing on orthopedic surgeries.