# Stain-invariant self supervised learning for histopathology image analysis

arXiv: https://arxiv.org/abs/2211.07590 · HTML: https://mlsanity.com/paper/2211.07590/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 14 Nov 2022.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology](https://mlsanity.com/paper/1902.06543/) (2019)
- [Self supervised contrastive learning for digital histopathology](https://mlsanity.com/paper/2011.13971/) (2020)
- [BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images](https://mlsanity.com/paper/2111.04740/) (2021)
- [Hierarchical Graph Representations in Digital Pathology](https://mlsanity.com/paper/2102.11057/) (2021)
- [Structure-Preserving Multi-Domain Stain Color Augmentation using Style-Transfer with Disentangled Representations](https://mlsanity.com/paper/2107.12357/) (2021)
- [Deep Multi-Magnification Networks for Multi-Class Breast Cancer Image Segmentation](https://mlsanity.com/paper/1910.13042/) (2019)
- [Adversarial learning of cancer tissue representations](https://mlsanity.com/paper/2108.02223/) (2021)
- [Multimarginal Wasserstein Barycenter for Stain Normalization and Augmentation](https://mlsanity.com/paper/2006.14566/) (2020)

## Built on by (most cited first, 4 of 4)

- [One-Shot Neural Architecture Search with Network Similarity Directed Initialization for Pathological Image Classification](https://mlsanity.com/paper/2506.14176/) (2025)
- [Understanding Stain Separation Improves Cross-Scanner Adenocarcinoma Segmentation with Joint Multi-Task Learning](https://mlsanity.com/paper/2409.13246/) (2024)
- [Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Images](https://mlsanity.com/paper/2503.10731/) (2025)
- [Histopathology Image Normalization via Latent Manifold Compaction](https://mlsanity.com/paper/2602.24251/) (2026)

## Abstract (arXiv)

We present a self-supervised algorithm for several classification tasks within hematoxylin and eosin (H&E) stained images of breast cancer. Our method is robust to stain variations inherent to the histology images acquisition process, which has limited the applicability of automated analysis tools. We address this problem by imposing constraints a learnt latent space which leverages stain normalization techniques during training. At every iteration, we select an image as a normalization target and generate a version of every image in the batch normalized to that target. We minimize the distance between the embeddings that correspond to the same image under different staining variations while maximizing the distance between other samples. We show that our method not only improves robustness to stain variations across multi-center data, but also classification performance through extensive experiments on various normalization targets and methods. Our method achieves the state-of-the-art performance on several publicly available breast cancer datasets ranging from tumor classification (CAMELYON17) and subtyping (BRACS) to HER2 status classification and treatment response prediction.