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.

翻译：血管自动分割对于开发新一代介入导航系统至关重要。然而，由于术中图像存在显著挑战（即低信噪比、细小血管以及强干扰），现有方法的分割性能欠佳。本文提出一种新颖的空间-频率学习与拓扑通道交互网络（SPIRONet）以解决上述问题。具体而言，网络采用双编码器全面捕获局部空间与全局频率的血管特征。随后，引入交叉注意力融合模块以有效融合空间与频率特征，从而增强特征判别力。此外，设计了一种基于图神经网络的拓扑通道交互模块，用于滤除与任务无关的响应。在多个具有挑战性的数据集（CADSA、CAXF、DCA1 和 XCAD）上的大量实验结果证明了本方法的先进性能。此外，SPIRONet 在输入尺寸为 512x512 时的推理速度达到 21 FPS，超越了临床实时性要求（6~12 FPS）。这些令人鼓舞的结果表明 SPIRONet 具备集成到血管介入导航系统中的潜力。代码发布于 https://github.com/Dxhuang-CASIA/SPIRONet。