SplineFormer: An Explainable Transformer-Based Approach for Autonomous Endovascular Navigation

2025-01-08

AI Summary

Real-time, geometrically interpretable prediction of guidewire dynamic deformation remains challenging in minimally invasive vascular interventions. Method: This paper proposes an end-to-end framework integrating Transformer-based sequential modeling with B-spline parameterization to achieve high-accuracy, smooth, and geometrically interpretable continuous prediction of guidewire shape. It is the first work to deploy this architecture on a physical robotic platform, establishing a vision-deformation co-learning closed loop enabling autonomous vascular catheterization. Contribution/Results: Evaluated on brachiocephalic artery cannulation, the method achieves a 50% success rate—substantially outperforming conventional image-segmentation-based approaches. By unifying data-driven learning with explicit geometric representation, this work establishes a new paradigm for explainable and deployable intravascular robotic navigation.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Segmentation
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Endovascular navigation is a crucial aspect of minimally invasive procedures, where precise control of curvilinear instruments like guidewires is critical for successful interventions. A key challenge in this task is accurately predicting the evolving shape of the guidewire as it navigates through the vasculature, which presents complex deformations due to interactions with the vessel walls. Traditional segmentation methods often fail to provide accurate real-time shape predictions, limiting their effectiveness in highly dynamic environments. To address this, we propose SplineFormer, a new transformer-based architecture, designed specifically to predict the continuous, smooth shape of the guidewire in an explainable way. By leveraging the transformer's ability, our network effectively captures the intricate bending and twisting of the guidewire, representing it as a spline for greater accuracy and smoothness. We integrate our SplineFormer into an end-to-end robot navigation system by leveraging the condensed information. The experimental results demonstrate that our SplineFormer is able to perform endovascular navigation autonomously and achieves a 50% success rate when cannulating the brachiocephalic artery on the real robot.

Problem

• intravascular navigation
• robotics
• wire shape prediction

Innovation

• SplineFormer
• Transformer-based method
• Intravascular navigation