Generation of H&E-Stained Histopathological Images Conditioned on Ki67 Index Using StyleGAN Model

Lucia Piatriková, Ivan Cimrák, Dominika Petríková

2024

Abstract

The analysis of tissue staining is a crucial aspect of cancer diagnosis. Hematoxylin and Eosin (H&E) staining captures fundamental morphological structures, while analysing Ki67-stained images provides deeper information about the tissue. However, this method is more expensive and time-consuming. Integrating machine learning techniques into pathologists’ workflow can save time and resources and provide reproducible results without intra- and inter-observer variability. However, the model must be explainable to be applicable in clinical practice. A generative model can add supplementary information that serves as an explanation for model predictions. This paper demonstrates the preliminary results of the conditional StyleGAN model trained on H&E-stained images conditioned on the corresponding Ki67 indexes. In our future research, StyleGAN will be part of a model for the estimation of Ki67 index from H&E staining and will generate explanations for the model’s predictions.

Paper Citation

in Harvard Style

Piatriková L., Cimrák I. and Petríková D. (2024). Generation of H&E-Stained Histopathological Images Conditioned on Ki67 Index Using StyleGAN Model. In Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOINFORMATICS; ISBN 978-989-758-688-0, SciTePress, pages 512-518. DOI: 10.5220/0012464200003657

in Bibtex Style

@conference{bioinformatics24,
author={Lucia Piatriková and Ivan Cimrák and Dominika Petríková},
title={Generation of H&E-Stained Histopathological Images Conditioned on Ki67 Index Using StyleGAN Model},
booktitle={Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOINFORMATICS},
year={2024},
pages={512-518},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012464200003657},
isbn={978-989-758-688-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOINFORMATICS
TI - Generation of H&E-Stained Histopathological Images Conditioned on Ki67 Index Using StyleGAN Model
SN - 978-989-758-688-0
AU - Piatriková L.
AU - Cimrák I.
AU - Petríková D.
PY - 2024
SP - 512
EP - 518
DO - 10.5220/0012464200003657
PB - SciTePress