Toward AI Autonomous Navigation for Mechanical Thrombectomy using Hierarchical Modular Multi-agent Reinforcement Learning (HM-MARL)

• URL: http://arxiv.org/abs/2602.18663v1
• Date: Fri, 20 Feb 2026 23:50:35 GMT
• Title: Toward AI Autonomous Navigation for Mechanical Thrombectomy using Hierarchical Modular Multi-agent Reinforcement Learning (HM-MARL)
• Authors: Harry Robertshaw, Nikola Fischer, Lennart Karstensen, Benjamin Jackson, Xingyu Chen, S. M. Hadi Sadati, Christos Bergeles, Alejandro Granados, Thomas C Booth,
• Abstract summary: 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
• Score: 57.65363326406228
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mechanical thrombectomy (MT) is typically the optimal treatment for acute ischemic stroke involving large vessel occlusions, but access is limited due to geographic and logistical barriers. Reinforcement learning (RL) shows promise in autonomous endovascular navigation, but generalization across 'long' navigation tasks remains challenging. We propose a Hierarchical Modular Multi-Agent Reinforcement Learning (HM-MARL) framework for autonomous two-device navigation in vitro, enabling efficient and generalizable navigation. HM-MARL was developed to autonomously navigate a guide catheter and guidewire from the femoral artery to the internal carotid artery (ICA). A modular multi-agent approach was used to decompose the complex navigation task into specialized subtasks, each trained using Soft Actor-Critic RL. The framework was validated in both in silico and in vitro testbeds to assess generalization and real-world feasibility. In silico, a single-vasculature model achieved 92-100% success rates on individual anatomies, while a multi-vasculature model achieved 56-80% across multiple patient anatomies. 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 superhuman challenge due to the anatomy and catheter type used in navigation. This study presents the first demonstration of in vitro autonomous navigation in MT vasculature. While HM-MARL enables generalization across anatomies, the simulation-to-real transition introduces challenges. Future work will refine RL strategies using world models and validate performance on unseen in vitro data, advancing autonomous MT towards clinical translation.

Related papers

• MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning [53.37068897861388]
  MedSAM-Agent is a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process.<n>We develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification.<n>Experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-03T09:47:49Z)
• DINO-CVA: A Multimodal Goal-Conditioned Vision-to-Action Model for Autonomous Catheter Navigation [0.33727511459109777]
  This work moves towards autonomous catheter navigation by introducing DINO-CVA, a multimodal goal-conditioned behavior cloning framework.<n>The proposed model fuses visual observations and joystick kinematics into a joint embedding space, enabling policies that are both vision-aware and kinematic-aware.<n>Results show that DINO-CVA achieves high accuracy in predicting actions, matching the performance of a kinematics-only baseline.
  arXiv  Detail & Related papers  (2025-10-19T22:59:32Z)
• Autonomous Soft Robotic Guidewire Navigation via Imitation Learning [3.1381624795986345]
  In endovascular surgery, interventionists push a thin tube called a catheter, guided by a thin wire to a treatment site inside the patient's blood vessels.<n>Guidewires with robotic tips can enhance maneuverability, but they present challenges in modeling and control.<n>We develop a transformer-based imitation learning framework with goal conditioning, relative action outputs, and automatic contrast dye injections.
  arXiv  Detail & Related papers  (2025-10-10T15:57:09Z)
• 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)
• 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)
• Autonomous navigation of catheters and guidewires in mechanical thrombectomy using inverse reinforcement learning [39.70065117918227]
  Autonomous navigation of catheters and guidewires can enhance endovascular surgery safety and efficacy, reducing procedure times and operator radiation exposure. This study explores the viability of autonomous navigation in MT vasculature using inverse RL (IRL) to leverage expert demonstrations.
  arXiv  Detail & Related papers  (2024-06-18T11:00:55Z)
• Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation [113.5002649181103]
  Training open-source small multimodal models (SMMs) to bridge competency gaps for unmet clinical needs in radiology. For training, we assemble a large dataset of over 697 thousand radiology image-text pairs. For evaluation, we propose CheXprompt, a GPT-4-based metric for factuality evaluation, and demonstrate its parity with expert evaluation. The inference of LlaVA-Rad is fast and can be performed on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.
  arXiv  Detail & Related papers  (2024-03-12T18:12:02Z)
• Towards Autonomous Atlas-based Ultrasound Acquisitions in Presence of Articulated Motion [48.52403516006036]
  This paper proposes a vision-based approach allowing autonomous robotic US limb scanning. To this end, an atlas MRI template of a human arm with annotated vascular structures is used to generate trajectories. In all cases, the system can successfully acquire the planned vascular structure on volunteers' limbs.
  arXiv  Detail & Related papers  (2022-08-10T15:39:20Z)
• Building Brains: Subvolume Recombination for Data Augmentation in Large Vessel Occlusion Detection [56.67577446132946]
  A large training data set is required for a standard deep learning-based model to learn this strategy from data. We propose an augmentation method that generates artificial training samples by recombining vessel tree segmentations of the hemispheres from different patients. In line with the augmentation scheme, we use a 3D-DenseNet fed with task-specific input, fostering a side-by-side comparison between the hemispheres.
  arXiv  Detail & Related papers  (2022-05-05T10:31:57Z)

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.