VascularPilot3D: Toward a 3D fully autonomous navigation for endovascular robotics

TL;DR

VascularPilot3D is a pioneering fully autonomous 3D navigation system for endovascular robots, integrating advanced perception, planning, and navigation modules to enhance clinical procedures and reduce surgeon workload.

Contribution

It introduces a complete autonomous navigation system combining novel modules for perception, planning, and control, advancing endovascular robotics toward clinical autonomy.

Findings

Achieved 100% success rate in ex-vivo trials

Reduced surgeon control loops by 18.38%

Compatible with most endovascular robots

Abstract

This research reports VascularPilot3D, the first 3D fully autonomous endovascular robot navigation system. As an exploration toward autonomous guidewire navigation, VascularPilot3D is developed as a complete navigation system based on intra-operative imaging systems (fluoroscopic X-ray in this study) and typical endovascular robots. VascularPilot3D adopts previously researched fast 3D-2D vessel registration algorithms and guidewire segmentation methods as its perception modules. We additionally propose three modules: a topology-constrained 2D-3D instrument end-point lifting method, a tree-based fast path planning algorithm, and a prior-free endovascular navigation strategy. VascularPilot3D is compatible with most mainstream endovascular robots. Ex-vivo experiments validate that VascularPilot3D achieves 100% success rate among 25 trials. It reduces the human surgeon's overall control loops by 18.38%. VascularPilot3D is promising for general clinical autonomous endovascular navigations.