SAR2Net：学习空间锚定表征用于检索引导的跨染色对齐
SAR2Net: Learning Spatially Anchored Representations for Retrieval-Guided Cross-Stain Alignment
把跨模态配准从显式变换估计改写成区域级特征检索，用相对组织标志点的空间锚定特征做形变不变描述子，这一思路可迁移到多模态/多时相图像匹配与检索式配准任务。
原文依据 reformulates cross-stain alignment as a region-level feature retrieval problem
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论实现跨染色全切片图像（WSI）之间的空间对齐对于整合形态学与分子信息至关重要，然而由于极高的分辨率、组织碎片化以及大幅非线性形变，这一任务仍然充满挑战。传统的配准流程依赖全局预对齐与空间一致性，而在此类畸变下这些假设往往失效。我们提出 SAR2Net，一个学习空间锚定表征的框架，并将跨染色对齐重新表述为区域级特征检索问题。SAR2Net 不估计显式变换，而是学习逐点表征，编码相对于组织标志点的空间关系。给定标志点与任意坐标，它预测空间锚定特征，作为组织拓扑的形变不变描述子。随后，一个两阶段检索框架在切片之间建立对应关系，即使全局对齐不可行时也能奏效。在面向活检的 HE-IHC 数据集上的实验表明，SAR2Net 在严重组织畸变下实现了稳健的区域级对齐，优于以往方法。代码见 https://github.com/Shentl/SAR2Net。
英文原文摘要 1204 字符
Achieving spatial alignment between whole-slide images (WSIs) across stains is essential for integrating morphology and molecular information, yet it remains challenging due to extreme resolution, tissue fragmentation, and large nonlinear deformations. Conventional registration pipelines depend on global pre-alignment and spatial consistency, which often collapse under such distortions. We present SAR2Net, a framework that learns spatially anchored representations and reformulates cross-stain alignment as a region-level feature retrieval problem. Instead of estimating explicit transformations, SAR2Net learns pointwise representations encoding the relative spatial relationships to tissue landmarks. Given landmarks and arbitrary coordinates, it predicts spatially anchored features that serve as deformation-invariant descriptors of tissue topology. A two-stage retrieval framework then establishes correspondences between slides, even when global alignment is infeasible. Experiments on biopsy-oriented HE-IHC datasets show that SAR2Net achieves robust region-level alignment under severe tissue distortions, outperforming previous methods. Code is available at https://github.com/Shentl/SAR2Net