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

arXiv: https://arxiv.org/abs/2501.04515 · HTML: https://mlsanity.com/paper/2501.04515/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 62 references that are in the map.
- First posted on arXiv 8 Jan 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [CPTR: Full Transformer Network for Image Captioning](https://mlsanity.com/paper/2101.10804/) (2021)
- [MultiSpeech: Multi-Speaker Text to Speech with Transformer](https://mlsanity.com/paper/2006.04664/) (2020)
- [End-to-End Real-time Catheter Segmentation with Optical Flow-Guided Warping during Endovascular Intervention](https://mlsanity.com/paper/2006.09117/) (2020)
- [Self-Supervised Depth Estimation in Laparoscopic Image using 3D Geometric Consistency](https://mlsanity.com/paper/2208.08407/) (2022)
- [Fully Automatic and Real-Time Catheter Segmentation in X-Ray Fluoroscopy](https://mlsanity.com/paper/1707.05137/) (2017)
- [CathSim: An Open-source Simulator for Endovascular Intervention](https://mlsanity.com/paper/2208.01455/) (2022)
- [Deep reinforcement learning for guidewire navigation in coronary artery phantom](https://mlsanity.com/paper/2110.01840/) (2021)
- [Automatic catheter detection in pediatric X-ray images using a scale-recurrent network and synthetic data](https://mlsanity.com/paper/1806.00921/) (2018)
- [Shape-Sensitive Loss for Catheter and Guidewire Segmentation](https://mlsanity.com/paper/2311.11205/) (2023)
- [Autonomous Catheterization with Open-source Simulator and Expert Trajectory](https://mlsanity.com/paper/2401.09059/) (2024)
- [Real-time guidewire tracking and segmentation in intraoperative x-ray](https://mlsanity.com/paper/2404.08805/) (2024)
- [Improving Catheter Segmentation & Localization in 3D Cardiac Ultrasound Using Direction-Fused FCN](https://mlsanity.com/paper/1902.05582/) (2019)

## Abstract (arXiv)

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.