Toward Safe Autonomous Robotic Endovascular Interventions using World Models

• URL: http://arxiv.org/abs/2604.20151v1
• Date: Wed, 22 Apr 2026 03:32:18 GMT
• Title: Toward Safe Autonomous Robotic Endovascular Interventions using World Models
• Abstract summary: We investigate a world-model-based framework for autonomous endovascular navigation built on TD-MPC2.<n>We evaluate a TD-MPC2 agent trained on multiple navigation across hold out patient-specific vasculatures.<n>We benchmark its performance against the state-of-the-art Soft Actor-Critic (SAC) algorithm agent.
• Score: 34.54099310430464
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Progressive Experience Fusion for Multi-Task World Model Control in Endovascular Navigation [37.517747868704184]
  This study investigates Progressive Experience Fusion (PEF) to train a multi-stage TD-MPC2 controller.<n>We additionally evaluate a plan that changes the Model Predictive Path Integral planning horizon using residual action-sequence dispersion, and fine-tuning in a patient-specific simulation.
  arXiv  Detail & Related papers  (2026-08-19T07:51:50Z)
• Anatomical Landmark-Guided Deep Reinforcement Learning for Autonomous Gastric Navigation [9.172107354380117]
  Wireless capsule endoscopy (WCE) enables painless visualization of the gastrointestinal tract.<n>We propose a transferable, anatomical landmarkguided deep reinforcement learning framework for autonomous gastric navigation.
  arXiv  Detail & Related papers  (2026-05-08T03:11:21Z)
• Toward AI Autonomous Navigation for Mechanical Thrombectomy using Hierarchical Modular Multi-agent Reinforcement Learning (HM-MARL) [57.65363326406228]
  We propose a Hierarchical Modular Multi-Agent Reinforcement Learning framework for autonomous two-device navigation in vitro.<n>HM-MARL was developed to autonomously navigate a guide catheter and guidewire from the femoral artery to the internal carotid artery (ICA)<n>A modular multi-agent approach was used to decompose the complex navigation task into specialized subtasks, each trained using Soft Actor-Critic RL.<n>In vitro, both HM-MARL models successfully navigated 100% of trials from the femoral artery to the right common carotid artery and 80% to the right ICA but failed on the left-side vessel challenge
  arXiv  Detail & Related papers  (2026-02-20T23:50:35Z)
• Stage-Specific Benchmarking of Deep Learning Models for Glioblastoma Follow-Up MRI [1.1458853556386799]
  We present the first stage-specific, cross-sectional benchmarking of deep learning models for follow-up MRI.<n>We analyze different post-RT scans independently to test whether architecture performance depends on time-point.<n>These results establish a stage-aware benchmark and motivate future work incorporating longitudinal modeling, multi-sequence MRI, and larger multi-center cohorts.
  arXiv  Detail & Related papers  (2025-11-23T19:38:03Z)
• World Model for AI Autonomous Navigation in Mechanical Thrombectomy [39.51808126417126]
  We propose a world model for autonomous endovascular navigation using TD-MPC2, a model-based RL algorithm.<n>We trained a single RL agent across multiple endovascular navigation tasks in ten real patient vasculatures, comparing performance against the state-of-the-art Soft Actor-Critic (SAC) method.<n>Results indicate that TD-MPC2 significantly outperforms SAC in multi-task learning, achieving a 65% mean success rate compared to SAC's 37%, with notable improvements in path ratio.
  arXiv  Detail & Related papers  (2025-09-29T21:21:30Z)
• Organ-Agents: Virtual Human Physiology Simulator via LLMs [66.40796430669158]
  Organ-Agents is a multi-agent framework that simulates human physiology via LLM-driven agents.<n>We curated data from 7,134 sepsis patients and 7,895 controls, generating high-resolution trajectories across 9 systems and 125 variables.<n>Organ-Agents achieved high simulation accuracy on 4,509 held-out patients, with per-system MSEs 0.16 and robustness across SOFA-based severity strata.
  arXiv  Detail & Related papers  (2025-08-20T01:58:45Z)
• A Novel Attention-Augmented Wavelet YOLO System for Real-time Brain Vessel Segmentation on Transcranial Color-coded Doppler [49.03919553747297]
  We propose an AI-powered, real-time CoW auto-segmentation system capable of efficiently capturing cerebral arteries.<n>No prior studies have explored AI-driven cerebrovascular segmentation using Transcranial Color-coded Doppler (TCCD)<n>The proposed AAW-YOLO demonstrated strong performance in segmenting both ipsilateral and contralateral CoW vessels.
  arXiv  Detail & Related papers  (2025-08-19T14:41:22Z)
• Reinforcement Learning for Safe Autonomous Two Device Navigation of Cerebral Vessels in Mechanical Thrombectomy [38.51304071363744]
  Current reinforcement learning methods only reach the carotid arteries.<n>We propose a safe dual-device RL algorithm that can navigate beyond the carotid arteries to cerebral vessels.
  arXiv  Detail & Related papers  (2025-03-31T14:25:46Z)
• Multiple Time Series Fusion Based on LSTM An Application to CAP A Phase Classification Using EEG [56.155331323304]
  Deep learning based electroencephalogram channels' feature level fusion is carried out in this work. Channel selection, fusion, and classification procedures were optimized by two optimization algorithms.
  arXiv  Detail & Related papers  (2021-12-18T14:17:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.