Inverse Reinforcement Learning Intra-Operative Path Planning for Steerable Needle.

Abstract

This paper presentsa safe and effective keyhole neurosurgery intra-operative planning framework for flexible neurosurgical robots. The framework is intended to support neurosurgeons during the intra-operative procedure to react to a dynamic environment. The proposed system integrates inverse reinforcement learning path planning algorithm combined with 1) a pre-operative path planning framework for fast and intuitive user interaction, 2) a realistic, time-bounded simulator based on Position-based Dynamics (PBD) simulation that mocks brain deformations due to catheter insertion and 3) a simulated robotic system. Simulation results performed on a human brain dataset show that the inverse reinforcement learning intra-operative planning method can guide a steerable needle with bounded curvature to a predefined target pose with an average targeting error of 1.34 ± 0.52 (25 ^th = 1.02, 75 ^th = 1.36) mm in position and 3.16 ± 1.06 (25 ^th = 2, 75 ^th = 4.94) degrees in orientation under a deformable simulated environment, with a re-planning time of 0.02 sec and a success rate of 100%. With this work, we demonstrate that the presented intra-operative steerable needle path planner is able to avoid anatomical obstacles while optimising surgical criteria. The results demonstrate that the proposed method is fast and can securely steer flexible needles with high accuracy and robustness.