Exploring Histopathological Image Augmentation Through StyleGAN2ADA: A Quantitative Analysis

Glenda P. Train, Johanna E. Rogalsky, Sergio O. Ioshii, Paulo M. Azevedo-Marques, Lucas F. Oliveira

2025

Abstract

Due to the rapid development of technology in the last decade, pathology has entered its digital era with the diffusion of WSIs. With this improvement, providing reliable automated diagnoses has become highly desirable to reduce the time and effort of experts in time-consuming and exhaustive tasks. However, with the scarcity of publicly labeled medical data and the imbalance between data classes, it is necessary to use various data augmentation techniques to mitigate these problems. This paper presents experiments that investigate the impact of adding synthetic IHC images on the classification of staining intensity levels of cancer cells with estrogen and progesterone biomarkers. We tested models SVM, CNN, DenseNet, and ViT, trained with and without images generated by StyleGAN2ADA and AutoAugment. The experiments covered class balancing and adding synthetic images to the training process, improving the classification F1-Score by up to 14 percentage points. In almost all experiments using StyleGAN2ADA images, the F1-Score was enhanced.

Paper Citation

in Harvard Style

Train G., Rogalsky J., Ioshii S., Azevedo-Marques P. and Oliveira L. (2025). Exploring Histopathological Image Augmentation Through StyleGAN2ADA: A Quantitative Analysis. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 839-846. DOI: 10.5220/0013382300003912

in Bibtex Style

@conference{visapp25,
author={Glenda Train and Johanna Rogalsky and Sergio Ioshii and Paulo Azevedo-Marques and Lucas Oliveira},
title={Exploring Histopathological Image Augmentation Through StyleGAN2ADA: A Quantitative Analysis},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={839-846},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013382300003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Exploring Histopathological Image Augmentation Through StyleGAN2ADA: A Quantitative Analysis
SN - 978-989-758-728-3
AU - Train G.
AU - Rogalsky J.
AU - Ioshii S.
AU - Azevedo-Marques P.
AU - Oliveira L.
PY - 2025
SP - 839
EP - 846
DO - 10.5220/0013382300003912
PB - SciTePress