Toward Safe Autonomous Robotic Endovascular Interventions using World Models

TL;DR

This paper introduces a world-model-based reinforcement learning framework for autonomous endovascular navigation, demonstrating improved success rates and safety in simulation and in vitro experiments for robotic thrombectomy.

Contribution

It presents the first validation of autonomous thrombectomy navigation using world models across diverse patient-specific vasculatures in both simulation and in vitro settings.

Findings

TD-MPC2 outperforms SAC in success rate (58% vs. 36%) in simulation.

TD-MPC2 maintains low tip contact forces below rupture threshold.

In vitro, TD-MPC2 achieves comparable success rates with better path efficiency.

Abstract

Autonomous mechanical thrombectomy (MT) presents substantial challenges due to highly variable vascular geometries and the requirements for accurate, real-time control. While reinforcement learning (RL) has emerged as a promising paradigm for the automation of endovascular navigation, existing approaches often show limited robustness when faced with diverse patient anatomies or extended navigation horizons. In this work, we investigate a world-model-based framework for autonomous endovascular navigation built on TD-MPC2, a model-based RL method that integrates planning and learned dynamics. We evaluate a TD-MPC2 agent trained on multiple navigation tasks across hold out patient-specific vasculatures and benchmark its performance against the state-of-the-art Soft Actor-Critic (SAC) algorithm agent. Both approaches are further validated in vitro using patient-specific vascular phantoms under fluoroscopic guidance. In simulation, TD-MPC2 demonstrates a significantly higher mean success rate than SAC (58% vs. 36%, p < 0.001), and mean tip contact forces of 0.15 N, well below the proposed 1.5 N vessel rupture threshold. Mean success rates for TD-MPC2 (68%) were comparable to SAC (60%) in vitro, but TD-MPC2 achieved superior path ratios (p = 0.017) at the cost of longer procedure times (p < 0.001). Together, these results provide the first demonstration of autonomous MT navigation validated across both hold out in silico data and fluoroscopy-guided in vitro experiments, highlighting the promise of world models for safe and generalizable AI-assisted endovascular interventions.