# H&E Stain Normalization using U-Net

arXiv: https://arxiv.org/abs/2211.05420 · HTML: https://mlsanity.com/paper/2211.05420/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 10 Nov 2022.

## Builds on (most cited first, 8 of 8)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019)
- [StainGAN: Stain Style Transfer for Digital Histological Images](https://mlsanity.com/paper/1804.01601/) (2018)
- [Structure-Preserving Multi-Domain Stain Color Augmentation using Style-Transfer with Disentangled Representations](https://mlsanity.com/paper/2107.12357/) (2021)
- [StainNet: a fast and robust stain normalization network](https://mlsanity.com/paper/2012.12535/) (2020)
- [H&E-adversarial network: a convolutional neural network to learn stain-invariant features through Hematoxylin & Eosin regression](https://mlsanity.com/paper/2201.06329/) (2022)

## Abstract (arXiv)

We propose a novel hematoxylin and eosin (H&E) stain normalization method based on a modified U-Net neural network architecture. Unlike previous deep-learning methods that were often based on generative adversarial networks (GANs), we take a teacher-student approach and use paired datasets generated by a trained CycleGAN to train a U-Net to perform the stain normalization task. Through experiments, we compared our method to two recent competing methods, CycleGAN and StainNet, a lightweight approach also based on the teacher-student model. We found that our method is faster and can process larger images with better quality compared to CycleGAN. We also compared to StainNet and found that our method delivered quantitatively and qualitatively better results.