H&E Stain Normalization using U-Net

TL;DR

This paper introduces a U-Net based stain normalization method for H&E images that outperforms existing GAN-based and lightweight models in speed and quality, using a teacher-student training approach with paired datasets.

Contribution

The paper presents a novel U-Net based stain normalization technique trained via a teacher-student approach, offering improved speed and quality over prior GAN and lightweight methods.

Findings

Faster processing of larger images compared to CycleGAN.

Superior quantitative and qualitative results over StainNet.

Effective stain normalization using paired datasets generated by CycleGAN.

Abstract

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.