GANs vs. Diffusion Models for virtual staining with the HER2match dataset

TL;DR

This paper introduces the HER2match dataset for virtual staining of breast cancer tissue, compares GANs and Diffusion Models for H&E-HER2 translation, and finds GANs generally outperform DMs, with data alignment being crucial.

Contribution

It provides the first public HER2match dataset and offers a comprehensive comparison of generative models for virtual tissue staining.

Findings

GANs outperform DMs overall

BBDM achieves comparable results to GANs

Data alignment significantly improves model quality

Abstract

Virtual staining is a promising technique that uses deep generative models to recreate histological stains, providing a faster and more cost-effective alternative to traditional tissue chemical staining. Specifically for H&E-HER2 staining transfer, despite a rising trend in publications, the lack of sufficient public datasets has hindered progress in the topic. Additionally, it is currently unclear which model frameworks perform best for this particular task. In this paper, we introduce the HER2match dataset, the first publicly available dataset with the same breast cancer tissue sections stained with both H&E and HER2. Furthermore, we compare the performance of several Generative Adversarial Networks (GANs) and Diffusion Models (DMs), and implement a novel Brownian Bridge Diffusion Model for H&E-HER2 translation. Our findings indicate that, overall, GANs perform better than DMs, with only the BBDM achieving comparable results. Furthermore, we emphasize the importance of data alignment, as all models trained on HER2match produced vastly improved visuals compared to the widely used consecutive-slide BCI dataset. This research provides a new high-quality dataset ([available upon publication acceptance]), improving both model training and evaluation. In addition, our comparison of frameworks offers valuable guidance for researchers working on the topic.