# H&E-adversarial network: a convolutional neural network to learn stain-invariant features through Hematoxylin & Eosin regression

arXiv: https://arxiv.org/abs/2201.06329 · HTML: https://mlsanity.com/paper/2201.06329/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 45 references that are in the map.
- First posted on arXiv 17 Jan 2022.

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

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (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)
- [Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images](https://mlsanity.com/paper/2001.01599/) (2020)
- [CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation](https://mlsanity.com/paper/1908.10555/) (2019)
- [StainGAN: Stain Style Transfer for Digital Histological Images](https://mlsanity.com/paper/1804.01601/) (2018)
- [Going Deeper through the Gleason Scoring Scale: An Automatic end-to-end System for Histology Prostate Grading and Cribriform Pattern Detection](https://mlsanity.com/paper/2105.10490/) (2021)
- [UniToPatho, a labeled histopathological dataset for colorectal polyps classification and adenoma dysplasia grading](https://mlsanity.com/paper/2101.09991/) (2021)
- [StainNet: a fast and robust stain normalization network](https://mlsanity.com/paper/2012.12535/) (2020)
- [The importance of stain normalization in colorectal tissue classification with convolutional networks](https://mlsanity.com/paper/1702.05931/) (2017)
- [Neural Stain-Style Transfer Learning using GAN for Histopathological Images](https://mlsanity.com/paper/1710.08543/) (2017)
- [Towards Histopathological Stain Invariance by Unsupervised Domain Augmentation using Generative Adversarial Networks](https://mlsanity.com/paper/2012.12413/) (2020)

## Built on by (most cited first, 5 of 5)

- [H&E Stain Normalization using U-Net](https://mlsanity.com/paper/2211.05420/) (2022)
- [Improving Stain Invariance of CNNs for Segmentation by Fusing Channel Attention and Domain-Adversarial Training](https://mlsanity.com/paper/2304.11445/) (2023)
- [Stain Consistency Learning: Handling Stain Variation for Automatic Digital Pathology Segmentation](https://mlsanity.com/paper/2311.06552/) (2023)
- [Automatic Labels are as Effective as Manual Labels in Biomedical Images Classification with Deep Learning](https://mlsanity.com/paper/2406.14351/) (2024)
- [Semi-Supervised Domain Adaptation with Latent Diffusion for Pathology Image Classification](https://mlsanity.com/paper/2601.17228/) (2026)

## Abstract (arXiv)

Computational pathology is a domain that aims to develop algorithms to automatically analyze large digitized histopathology images, called whole slide images (WSI). WSIs are produced scanning thin tissue samples that are stained to make specific structures visible. They show stain colour heterogeneity due to different preparation and scanning settings applied across medical centers. Stain colour heterogeneity is a problem to train convolutional neural networks (CNN), the state-of-the-art algorithms for most computational pathology tasks, since CNNs usually underperform when tested on images including different stain variations than those within data used to train the CNN. Despite several methods that were developed, stain colour heterogeneity is still an unsolved challenge that limits the development of CNNs that can generalize on data from several medical centers. This paper aims to present a novel method to train CNNs that better generalize on data including several colour variations. The method, called H&E-adversarial CNN, exploits H&E matrix information to learn stain-invariant features during the training. The method is evaluated on the classification of colon and prostate histopathology images, involving eleven heterogeneous datasets, and compared with five other techniques used to handle stain colour heterogeneity. H&E-adversarial CNNs show an improvement in performance compared to the other algorithms, demonstrating that it can help to better deal with stain colour heterogeneous images.