跨染色对比学习用于配对免疫组化和病理切片的表示学习
Cross-Stain Contrastive Learning for Paired Immunohistochemistry and Histopathology Slide Representation Learning
AI总结：
本文提出CSCL方法，通过跨染色对比学习提升H&E与IHC特征的兼容性，实现高质量的切片级表示学习。
摘要：
通用、可转移的整张切片图像（WSI）表示是计算病理学的核心。结合多种标记（如免疫组化，IHC）与H&E丰富H&E基于的特征，具有多样、生物上有意义的信息。然而，进展受限于多染色数据集的稀缺性。不同染色之间的错位会将对应的组织在切片上移动，阻碍一致的块级特征，并降低切片级嵌入的质量。为了解决这个问题，我们整理了一个滑动级别的对齐五染色数据集（H&E、HER2、KI67、ER、PGR），以实现配对的H&E-IHC学习和稳健的跨染色表示。利用此数据集，我们提出了跨染色对比学习（CSCL），一种两阶段预训练框架，具有轻量级的适配器，通过块级对比对齐进行训练，以提高H&E特征与相应IHC衍生上下文线索的兼容性，并通过多实例学习（MIL）进行切片级表示学习，该方法使用跨染色注意力融合模块来整合染色特定的块特征，并使用跨染色全局对齐模块来强制不同染色之间切片级嵌入的一致性。在癌症亚型分类、IHC生物标志物状态分类和生存预测实验中，显示出一致的提升，产生高质量、可转移的H&E切片级表示。代码和数据可在https://github.com/lily-zyz/CSCL上获得。
英文摘要：
Universal, transferable whole-slide image (WSI) representations are central to computational pathology. Incorporating multiple markers (e.g., immunohistochemistry, IHC) alongside H&E enriches H&E-based features with diverse, biologically meaningful information. However, progress is limited by the scarcity of well-aligned multi-stain datasets. Inter-stain misalignment shifts corresponding tissue across slides, hindering consistent patch-level features and degrading slide-level embeddings. To address this, we curated a slide-level aligned, five-stain dataset (H&E, HER2, KI67, ER, PGR) to enable paired H&E-IHC learning and robust cross-stain representation. Leveraging this dataset, we propose Cross-Stain Contrastive Learning (CSCL), a two-stage pretraining framework with a lightweight adapter trained using patch-wise contrastive alignment to improve the compatibility of H&E features with corresponding IHC-derived contextual cues, and slide-level representation learning with Multiple Instance Learning (MIL), which uses a cross-stain attention fusion module to integrate stain-specific patch features and a cross-stain global alignment module to enforce consistency among slide-level embeddings across different stains. Experiments on cancer subtype classification, IHC biomarker status classification, and survival prediction show consistent gains, yielding high-quality, transferable H&E slide-level representations. The code and data are available at https://github.com/lily-zyz/CSCL.
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。
