A Laplacian Pyramid Based Generative H&E Stain Augmentation Network
IEEE Transactions on Medical Imaging · 2024-02 · 43 (2) · 701-713
DOI: 10.1109/tmi.2023.3317239 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2024-02. Verfasst von Fangda Li und 3 weiteren Autor:innen. Hauptthemen laut MEDLINE: Machine Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 45 Literaturangaben.
Abstract (Originalsprache)
Hematoxylin and Eosin (H&E) staining is a widely used sample preparation procedure for enhancing the saturation of tissue sections and the contrast between nuclei and cytoplasm in histology images for medical diagnostics. However, various factors, such as the differences in the reagents used, result in high variability in the colors of the stains actually recorded. This variability poses a challenge in achieving generalization for machine-learning based computer-aided diagnostic tools. To desensitize the learned models to stain variations, we propose the Generative Stain Augmentation Network (G-SAN) - a GAN-based framework that augments a collection of cell images with simulated yet realistic stain variations. At its core, G-SAN uses a novel and highly computationally efficient Laplacian Pyramid (LP) based generator architecture, that is capable of disentangling stain from cell morphology. Through the task of patch classification and nucleus segmentation, we show that using G-SAN-augmented training data provides on average 15.7% improvement in F1 score and 7.3% improvement in panoptic quality, respectively. Our code is available at https://github.com/lifangda01/GSAN-Demo.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Zitieren
APA
Li, F., Hu, Z., Chen, W., & Kak, A. (2024). A Laplacian Pyramid Based Generative H&E Stain Augmentation Network. IEEE Transactions on Medical Imaging, 43(2), 701-713. https://doi.org/10.1109/tmi.2023.3317239
Vancouver
Li F, Hu Z, Chen W, Kak A. A Laplacian Pyramid Based Generative H&E Stain Augmentation Network. IEEE Transactions on Medical Imaging. 2024;43(2):701-713. doi:10.1109/tmi.2023.3317239
BibTeX
@article{Li2024,
author = {Li, Fangda and Hu, Zhiqiang and Chen, Wen and Kak, Avinash},
title = {A Laplacian Pyramid Based Generative H&E Stain Augmentation Network},
journal = {IEEE Transactions on Medical Imaging},
year = {2024},
volume = {43},
number = {2},
pages = {701--713},
doi = {10.1109/tmi.2023.3317239}
}
EUVIMED