基于Patch级和WSI级对比学习的病理图像分割领域泛化
Domain Generalization of Pathological Image Segmentation by Patch-Level and WSI-Level Contrastive Learning
AI总结：
针对病理图像院内域偏移问题，提出通过聚类非肿瘤区域WSI级特征构建域，并采用WSI级和patch级两阶段对比学习来减少特征差距，实现无需多医院数据的领域泛化。
摘要：
本文通过关注全切片图像（WSIs）内部的域偏移（如患者特征和组织厚度）而非医院间的偏移，来解决病理图像中的域偏移问题。传统方法依赖多医院数据，但数据收集挑战常使其难以实现。因此，所提领域泛化方法通过对非肿瘤区域的WSI级特征进行聚类，并将这些聚类视为域，从而捕获并利用院内域偏移。为缓解域偏移，我们应用对比学习来减少来自不同聚类的WSI对之间的特征差距。所提方法引入两阶段对比学习——WSI级和patch级对比学习，以有效最小化这些差距。
英文摘要：
In this paper, we address domain shifts in pathological images by focusing on shifts within whole slide images~(WSIs), such as patient characteristics and tissue thickness, rather than shifts between hospitals. Traditional approaches rely on multi-hospital data, but data collection challenges often make this impractical. Therefore, the proposed domain generalization method captures and leverages intra-hospital domain shifts by clustering WSI-level features from non-tumor regions and treating these clusters as domains. To mitigate domain shift, we apply contrastive learning to reduce feature gaps between WSI pairs from different clusters. The proposed method introduces a two-stage contrastive learning approach WSI-level and patch-level contrastive learning to minimize these gaps effectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
