MCP-Net enhances real-time navigation of coronary guidewires in robotic surgery
MCP-Net: Real-Time Coronary Perception Network and Topological Analysis for Robotic Guidewire Navigation
Computer Vision and Pattern RecognitionRobotics
Summary
During heart procedures, doctors guide tiny wires through blood vessels using X-ray images to open blocked arteries. The authors present MCP-Net, a system that helps robots understand these X-ray images by identifying vessels, the wire tip, and narrowing spots all at once. They use realistic simulated images to train their system to then build a detailed map of the vessels and critical points. This map helps robots navigate precisely inside the coronary arteries during surgery.
What this means in practice
- •For robotic surgery teams: Improve robotic guidewire navigation by providing real-time vessel maps and lesion locations from X-ray images during coronary interventions.
- •For medical imaging software developers: Create advanced fluoroscopy imaging tools that jointly segment vessels and detect guidewire position and blockages for enhanced procedural support.
Authors
Sahar Nasirihaghighi, Tianyuan Wang, Kenan Niu, Stefano Stramigioli
Abstract
Coronary guidewire navigation during percutaneous coronary intervention requires continuous interpretation of vessel anatomy, guidewire position, and target stenosis under two-dimensional X-ray fluoroscopy. While existing approaches commonly address vessel segmentation or device localization as separate tasks, a robotic system requires a more structured perception of the coronary scene to support downstream navigation. In this work, we present a simulation-driven framework centered on a Multi-Task Coronary Perception Network (MCP-Net) for robotic guidewire navigation, integrating coronary vessel segmentation, vascular topology extraction, and roadmap generation. Starting from three-dimensional coronary CT angiography, we generate simulated fluoroscopy images containing vascular structures, simulated guidewires, stenotic lesions with varying severity, and diverse vascular geometries, together with simulation-derived ground truth. MCP-Net jointly performs coronary vessel segmentation, guidewire-tip localization, and stenosis localization from a single fluoroscopic frame. These predictions are subsequently converted into a structured vascular graph containing centerlines, bifurcations, endpoints, branch directions, and branch angles. By associating the predicted stenosis with this graph, the framework generates a roadmap from the automatically selected graph root toward the target lesion. The results demonstrate that the proposed framework can jointly recover coronary perception targets and transform them into an interpretable vascular representation suitable for downstream robotic navigation.