H&E Stain Normalization using U-Net

Chi Chen Lee*, Po Tsun Paul Kuo*, Chi Han Peng*

*此作品的通信作者

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

We propose a novel hematoxylin and eosin (H&E) stain normalization method based on a modified U-Net neural network architecture. Unlike previous deep-learning methods that were often based on generative adversarial networks (GANs), we take a teacher-student approach and use paired datasets generated by a trained CycleGAN to train a U-Net to perform the stain normalization task. Through experiments, we compared our method to two recent competing methods, CycleGAN and StainNet, a lightweight approach also based on the teacher-student model. We found that our method is faster and can process larger images with better quality compared to CycleGAN. We also compared to StainNet and found that our method delivered quantitatively and qualitatively better results.

原文English
主出版物標題Proceedings - IEEE 22nd International Conference on Bioinformatics and Bioengineering, BIBE 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面29-32
頁數4
ISBN(電子)9781665484879
DOIs
出版狀態Published - 2022
事件22nd IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2022 - Virtual, Online, 台灣
持續時間: 7 11月 20229 11月 2022

出版系列

名字Proceedings - IEEE 22nd International Conference on Bioinformatics and Bioengineering, BIBE 2022

Conference

Conference22nd IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2022
國家/地區台灣
城市Virtual, Online
期間7/11/229/11/22

指紋

深入研究「H&E Stain Normalization using U-Net」主題。共同形成了獨特的指紋。

引用此