Toward Safe Autonomous Robotic Endovascular Interventions using World Models

2026-04-21

AI Summary

This study addresses the challenges of autonomous mechanical thrombectomy, which include highly variable vascular geometries and the need for real-time precise control, where existing methods exhibit insufficient robustness across diverse patient anatomies and during long-range navigation. To overcome these limitations, this work introduces world models into the task for the first time, proposing a framework based on TD-MPC2 that integrates planning with learned dynamics to simultaneously preserve anatomical generalization and ensure operational safety. The approach leverages fluoroscopic guidance and is evaluated through simulation and ex vivo experiments on patient-specific vascular models. Results demonstrate a 58% success rate in simulation (compared to 36% for SAC) with an average contact force of 0.15 N, and a 68% success rate in ex vivo trials, significantly outperforming SAC in path efficiency.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• autonomous endovascular navigation
• mechanical thrombectomy
• vascular geometry variability
• real-time control
• robustness

Innovation

• world models
• model-based reinforcement learning
• autonomous endovascular navigation
• TD-MPC2
• mechanical thrombectomy