SPIRONet: Spatial-Frequency Learning and Topological Channel Interaction Network for Vessel Segmentation

TL;DR

SPIRONet introduces a novel vessel segmentation approach combining spatial-frequency learning and topological channel interaction, achieving state-of-the-art accuracy and real-time inference speed suitable for interventional navigation systems.

Contribution

The paper proposes SPIRONet, a new network integrating dual encoders, cross-attention fusion, and graph neural networks for improved vessel segmentation in challenging intraoperative images.

Findings

Achieves state-of-the-art segmentation accuracy on multiple datasets.

Operates at 21 FPS, exceeding real-time clinical requirements.

Effectively filters task-irrelevant responses using graph neural networks.

Abstract

Automatic vessel segmentation is paramount for developing next-generation interventional navigation systems. However, current approaches suffer from suboptimal segmentation performances due to significant challenges in intraoperative images (i.e., low signal-to-noise ratio, small or slender vessels, and strong interference). In this paper, a novel spatial-frequency learning and topological channel interaction network (SPIRONet) is proposed to address the above issues. Specifically, dual encoders are utilized to comprehensively capture local spatial and global frequency vessel features. Then, a cross-attention fusion module is introduced to effectively fuse spatial and frequency features, thereby enhancing feature discriminability. Furthermore, a topological channel interaction module is designed to filter out task-irrelevant responses based on graph neural networks. Extensive experimental results on several challenging datasets (CADSA, CAXF, DCA1, and XCAD) demonstrate state-of-the-art performances of our method. Moreover, the inference speed of SPIRONet is 21 FPS with a 512x512 input size, surpassing clinical real-time requirements (6~12FPS). These promising outcomes indicate SPIRONet's potential for integration into vascular interventional navigation systems. Code is available at https://github.com/Dxhuang-CASIA/SPIRONet.