# Reinforcement Learning for Safe Autonomous Two Device Navigation of Cerebral Vessels in Mechanical Thrombectomy

arXiv: https://arxiv.org/abs/2503.24140 · HTML: https://mlsanity.com/paper/2503.24140/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in RL for clinical treatment and surgery, one of 15 directions in Deep reinforcement learning methods.
- Builds on 6 of its 35 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Placed in

- Deep reinforcement learning methods / [RL for clinical treatment and surgery](https://mlsanity.com/deeprl/rl-for-clinical-treatment-and-surgery/)

## Builds on (most cited first, 6 of 6)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Deep reinforcement learning for guidewire navigation in coronary artery phantom](https://mlsanity.com/paper/2110.01840/) (2021)
- [Artificial Intelligence in the Autonomous Navigation of Endovascular Interventions: A Systematic Review](https://mlsanity.com/paper/2405.03305/) (2024)
- [Autonomous navigation of catheters and guidewires in mechanical thrombectomy using inverse reinforcement learning](https://mlsanity.com/paper/2406.12499/) (2024)
- [Learning-Based Autonomous Navigation, Benchmark Environments and Simulation Framework for Endovascular Interventions](https://mlsanity.com/paper/2410.01956/) (2024)
- [A Zero-Shot Reinforcement Learning Strategy for Autonomous Guidewire Navigation](https://mlsanity.com/paper/2403.02777/) (2024)

## Built on by (most cited first, 6 of 6)

- [World Model for AI Autonomous Navigation in Mechanical Thrombectomy](https://mlsanity.com/paper/2509.25518/) (2025)
- [DARIL: When Imitation Learning outperforms Reinforcement Learning in Surgical Action Planning](https://mlsanity.com/paper/2507.05011/) (2025)
- [Toward AI Autonomous Navigation for Mechanical Thrombectomy using Hierarchical Modular Multi-agent Reinforcement Learning (HM-MARL)](https://mlsanity.com/paper/2602.18663/) (2026)
- [Towards Real-Time Autonomous Navigation: Transformer-Based Catheter Tip Tracking in Fluoroscopy](https://mlsanity.com/paper/2605.14253/) (2026)
- [TransForSeg: A Multitask Stereo ViT for Joint Stereo Segmentation and 3D Force Estimation in Catheterization](https://mlsanity.com/paper/2509.01605/) (2025)
- [Autonomous Robotic Navigation for Endovascular Brain-Computer Interface Access](https://mlsanity.com/paper/2610.03537/) (2026)

## Abstract (arXiv)

Purpose: Autonomous systems in mechanical thrombectomy (MT) hold promise for reducing procedure times, minimizing radiation exposure, and enhancing patient safety. However, current reinforcement learning (RL) methods only reach the carotid arteries, are not generalizable to other patient vasculatures, and do not consider safety. We propose a safe dual-device RL algorithm that can navigate beyond the carotid arteries to cerebral vessels. Methods: We used the Simulation Open Framework Architecture to represent the intricacies of cerebral vessels, and a modified Soft Actor-Critic RL algorithm to learn, for the first time, the navigation of micro-catheters and micro-guidewires. We incorporate patient safety metrics into our reward function by integrating guidewire tip forces. Inverse RL is used with demonstrator data on 12 patient-specific vascular cases. Results: Our simulation demonstrates successful autonomous navigation within unseen cerebral vessels, achieving a 96% success rate, 7.0s procedure time, and 0.24 N mean forces, well below the proposed 1.5 N vessel rupture threshold. Conclusion: To the best of our knowledge, our proposed autonomous system for MT two-device navigation reaches cerebral vessels, considers safety, and is generalizable to unseen patient-specific cases for the first time. We envisage future work will extend the validation to vasculatures of different complexity and on in vitro models. While our contributions pave the way towards deploying agents in clinical settings, safety and trustworthiness will be crucial elements to consider when proposing new methodology.