Autonomous navigation of catheters and guidewires in mechanical thrombectomy using inverse reinforcement learning

TL;DR

This paper demonstrates the feasibility of autonomous catheter and guidewire navigation in mechanical thrombectomy using inverse reinforcement learning, achieving high success rates and emphasizing reward shaping for optimal performance.

Contribution

It introduces a novel application of inverse reinforcement learning for autonomous endovascular navigation, leveraging expert demonstrations to improve procedure success.

Findings

High success rates of 95-96% in navigation tasks.

Reward shaping significantly improved procedure time and success.

IRL-derived reward functions underperformed compared to reward shaping.

Abstract

Purpose: Autonomous navigation of catheters and guidewires can enhance endovascular surgery safety and efficacy, reducing procedure times and operator radiation exposure. Integrating tele-operated robotics could widen access to time-sensitive emergency procedures like mechanical thrombectomy (MT). Reinforcement learning (RL) shows potential in endovascular navigation, yet its application encounters challenges without a reward signal. This study explores the viability of autonomous navigation in MT vasculature using inverse RL (IRL) to leverage expert demonstrations. Methods: This study established a simulation-based training and evaluation environment for MT navigation. We used IRL to infer reward functions from expert behaviour when navigating a guidewire and catheter. We utilized soft actor-critic to train models with various reward functions and compared their performance in silico. Results: We demonstrated feasibility of navigation using IRL. When evaluating single versus dual device (i.e. guidewire versus catheter and guidewire) tracking, both methods achieved high success rates of 95% and 96%, respectively. Dual-tracking, however, utilized both devices mimicking an expert. A success rate of 100% and procedure time of 22.6 s were obtained when training with a reward function obtained through reward shaping. This outperformed a dense reward function (96%, 24.9 s) and an IRL-derived reward function (48%, 59.2 s). Conclusions: We have contributed to the advancement of autonomous endovascular intervention navigation, particularly MT, by employing IRL. The results underscore the potential of using reward shaping to train models, offering a promising avenue for enhancing the accessibility and precision of MT. We envisage that future research can extend our methodology to diverse anatomical structures to enhance generalizability.