Cross-Stain Contrastive Learning for Paired Immunohistochemistry and Histopathology Slide Representation Learning

TL;DR

This paper introduces Cross-Stain Contrastive Learning (CSCL), a novel framework that enhances multi-stain slide representations by aligning features across different immunohistochemistry and histopathology stains, improving downstream pathology tasks.

Contribution

We curated a multi-stain dataset and developed a two-stage pretraining framework with contrastive alignment and attention-based fusion for better cross-stain slide representations.

Findings

Improved cancer subtype classification accuracy

Enhanced IHC biomarker status prediction

Better survival prediction performance

Abstract

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.