用蛇形窗口建模血管连续性，提升医学图像分割精度
SWinMamba: Serpentine Window State Space Model for Vascular Segmentation
- 引入蛇形窗口序列，自适应捕捉血管长程依赖
- 在三个数据集上实现完整连贯的血管分割结果
- 适合需要高精度血管结构建模的研究与临床应用
医学图像中的血管分割对疾病诊断和手术导航至关重要。然而，由于血管细长特性及先验建模不足，分割结果常出现断裂。本文提出一种新型蛇形窗口状态空间模型（SWinMamba），通过在双向状态空间模型中引入蛇形窗口序列，有效建模细长血管的连续性。蛇形窗口序列可自适应引导全局视觉上下文建模至血管结构。具体地，蛇形窗口分词器（SWToken）利用重叠的蛇形窗口序列对输入图像进行自适应划分，实现灵活的感受野（RFs）以支持血管结构建模；双向聚合模块（BAM）整合感受野内的相干局部特征，用于血管连续性表征。此外，设计了空间-频率融合单元（SFFU）的双域学习机制，增强血管结构特征表达。在三个具有挑战性的数据集上的大量实验表明，所提SWinMamba在血管完整性与连通性方面均达到更优性能。
原文摘要 · Abstract (English)
Vascular segmentation in medical images is crucial for disease diagnosis and surgical navigation. However, the segmented vascular structure is often discontinuous due to its slender nature and inadequate prior modeling. In this paper, we propose a novel Serpentine Window Mamba (SWinMamba) to achieve accurate vascular segmentation. The proposed SWinMamba innovatively models the continuity of slender vascular structures by incorporating serpentine window sequences into bidirectional state space models. The serpentine window sequences enable efficient feature capturing by adaptively guiding global visual context modeling to the vascular structure. Specifically, the Serpentine Window Tokenizer (SWToken) adaptively splits the input image using overlapping serpentine window sequences, enabling flexible receptive fields (RFs) for vascular structure modeling. The Bidirectional Aggregation Module (BAM) integrates coherent local features in the RFs for vascular continuity representation. In addition, dual-domain learning with Spatial-Frequency Fusion Unit (SFFU) is designed to enhance the feature representation of vascular structure. Extensive experiments on three challenging datasets demonstrate that the proposed SWinMamba achieves superior performance with complete and connected vessels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。