mlsanityData to 14 Oct 2026

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

arXiv 2512.03577 ↗First posted 3 Dec 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 41 references that are in the map. First posted on arXiv 3 Dec 2025.

Builds on

21 of 41 references.

References · 21

  1. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  2. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  3. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  4. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
  5. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
  6. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 359
  7. 2023Artificial Intelligence for Digital and Computational Pathologycited by 108
  8. 2022BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pixcited by 61
  9. 2023Attention-Challenging Multiple Instance Learning for Whole Slide Image Classificationcited by 61
  10. 2021Multiple Instance Captioning: Learning Representations from Histopathology Textbooks and Articlescited by 58
  11. 2024Transcriptomics-guided Slide Representation Learning in Computational Pathologycited by 51
  12. 2021Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slidescited by 43
9 more
  1. 2024Multistain Pretraining for Slide Representation Learning in Pathologycited by 28
  2. 2022Giga-SSL: Self-Supervised Learning for Gigapixel Imagescited by 24
  3. 2025Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentationcited by 17
  4. 2025Multimodal Cancer Survival Analysis via Hypergraph Learning with Cross-Modality Rebalancecited by 11
  5. 2022ACROBAT -- a multi-stain breast cancer histological whole-slide-image data set from routine diagnostics for computational pathologycited by 10
  6. 2024RegWSI: Whole Slide Image Registration using Combined Deep Feature- and Intensity-Based Methods: Winner of the ACROBAT 2023 Challengecited by 7
  7. 2025Hypergraph Tversky-Aware Domain Incremental Learning for Brain Tumor Segmentation with Missing Modalitiescited by 7
  8. 2022Feature Re-calibration based Multiple Instance Learning for Whole Slide Image Classificationcited by 4
  9. 2025Memory-Augmented Incomplete Multimodal Survival Prediction via Cross-Slide and Gene-Attentive Hypergraph Learningcited by 4

Built on by

Not cited yet.