# Modelling the Ki67 Index in Synthetic HE-Stained Images Using Conditional StyleGAN Model

## TL;DR

This paper explores using a conditional StyleGAN model to generate HE-stained cancer images with varying Ki67 index values, aiming to improve explainability in cancer diagnostics.

## Contribution

The study extends a conditional StyleGAN model to generate HE-stained image sequences reflecting Ki67 index variations and validates their relevance with pathologists.

## Key findings

- The model successfully captures Ki67-related variations in HE-stained images.
- Generated sequences were evaluated by pathologists and found relevant for explaining predictive models.
- The approach shows potential for analyzing cancer progression using generative models.

## Abstract

Hematoxylin and Eosin (HE) staining is the gold standard in histopathological examination of cancer tissue, representing the first step towards cancer diagnosis. The second step is a series of immunohistochemical stainings, including cell proliferation markers called the Ki67 index. Deep learning models offer promising solutions for improving medical diagnostics, while generative models provide additional explainability of predictive models that is essential for their adoption in clinical practice. Our previous work introduced a novel approach that utilises a conditional StyleGAN model for generating HE-stained images conditioned on the Ki67 index. This study proposes to employ this model for generating sequences of HE-stained images reflecting varying Ki67 index values. Sequences enable exploration of hidden relationships between HE and Ki67 staining and can enhance the explainability of predictive models, e.g., by generating counterfactual examples. While our previous research focused on assessing the quality of generated HE images, this study extends that work by evaluating the model’s ability to capture Ki67-related variations in HE-stained images. Additionally, expert pathologists evaluated generated sequences and proposed criteria for assessing their relevance. Our findings demonstrate the potential of the conditional StyleGAN model as part of an explainable framework for analysing and predicting immunohistochemical information from HE-stained images. Results highlight the relevance of generative models in histopathology and their potential applications in cancer progression analysis.