发表机构
App-In Club; Ryquo（App-In Club; Ryquo）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对扫描仪差异导致病理基础模型表示偏移的问题，提出SlideRuler方法，利用切片内区域作为内部对照进行单次扫描校准，显著降低嵌入距离，提升模型跨系统一致性。
AI 中文摘要
扫描仪的变化会改变病理学基础模型对同一组织的表示方式。我们引入了SlideRuler，它利用切片内的区域作为内部对照，来估计并校正其他区域中由采集引起的偏移。从配对重扫描中学习到的转移映射，使得在推理时仅凭单次扫描即可进行校准，同时保持基础模型固定不变。在两个编码器和五个SCORPION扫描仪上，与原始嵌入相比，学习到的转移将目标到源的嵌入距离平均降低了16.3%-38.5%。与无关的同扫描仪对照的比较显示，在所有四个评估设置（包括扫描仪留出）中，同一切片内对照均产生了正向贡献。一种源锚定变体相对于学习到的转移，将源特征位移降低了47.7%-83.6%，同时保留了其大部分对齐增益。通过从切片本身获取校准信息，SlideRuler为跨成像系统更一致地使用冻结的病理学模型提供了一条途径。
英文摘要
Scanner variation changes how pathology foundation models represent the same tissue. We introduce SlideRuler, which uses regions within a slide as internal controls to estimate and correct acquisition-induced shifts in other regions. A transfer map learned from paired rescans enables calibration from a single scan at inference while keeping the foundation model fixed. Across two encoders and five SCORPION scanners, learned transfer reduces mean target-to-source embedding distance by 16.3-38.5% relative to raw embeddings. Comparisons with unrelated same-scanner controls reveal a positive same-slide contribution across all four evaluation settings, including scanner holdout. A source-anchored variant reduces source-feature displacement by 47.7-83.6% relative to learned transfer while retaining most of its alignment gain. By drawing calibration information from the slide itself, SlideRuler offers a path toward more consistent use of frozen pathology models across imaging systems.
CommentsAccepted at the NeurIPS 2026 Workshop AI at Scale for Clinical Impact (ASCI): Cancer Pathology Foundation Models
