发表机构
Seoul National University; Seoul National University Hospital; Yonsei University; Korea University（首尔大学; 首尔大学医院; 延世大学; 高丽大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对细曲线结构分割中跨模态域偏移导致的拓扑连通性失效问题，提出SGP-TTA方法，通过ProgBN和CSR实现自适应，在拓扑连通性上优于现有TTA方法。
AI 中文摘要
细曲线结构的精确分割对从血管分析到道路提取等多种实际应用至关重要。然而其复杂的几何结构使得即使是微小的像素级误差也足以破坏全局拓扑，这种结构脆弱性会将严重的域偏移转化为灾难性失败。在跨模态间隙下，源域与目标域之间的成像过程存在根本差异，该问题最为突出。虽然测试时自适应（TTA）提供了一种实用的无源解决方案，但现有方法仅自适应特征统计和置信度，均未对连通性进行约束，因此在这种极端间隙下性能会下降。为解决该问题，我们提出了骨架引导的渐进式测试时自适应方法（SGP-TTA）。渐进式批归一化（ProgBN）根据样本计数调度，将归一化从冻结的源域统计量转向当前目标域估计，使源-目标平衡随自适应阶段变化而非固定系数。共识骨架召回（CSR）则从几何对齐的多视图预测中推导结构目标，且仅更新批归一化仿射参数以保留连通结构。大量实验表明，SGP-TTA在拓扑连通性上始终优于现有TTA方法，在跨模态偏移下优势最为显著。项目页面可访问此https URL。
英文摘要
Accurate segmentation of thin curvilinear structures is vital for various real-world applications, from vessel analysis to road extraction. Yet their intricate geometry makes even minor pixel-wise errors enough to break the global topology, and this structural fragility turns severe domain shifts into catastrophic failures. The difficulty is most acute under cross-modality gaps, where the imaging process itself differs fundamentally between source and target. While test-time adaptation (TTA) offers a practical source-free remedy, existing methods adapt feature statistics and confidence, neither of which constrains connectivity, and thus degrade under such extreme gaps. To address this, we propose Skeleton-Guided Progressive Test-Time Adaptation (SGP-TTA). Progressive Batch Normalization (ProgBN) shifts normalization from frozen source statistics toward current target estimates under a sample-count schedule, so that the source-target balance follows the stage of adaptation rather than a fixed coefficient. Consensus Skeleton Recall (CSR) then derives a structural target from geometrically aligned multi-view predictions and updates only the BN affine parameters to preserve connected structures. Extensive experiments show that SGP-TTA consistently outperforms existing TTA methods in topological connectivity, with the largest margins under cross-modality shift. The project page is available at https://boa-jang.github.io/SGP-TTA.
Comments9 pages, 6 figures
