期刊
APPLIED SCIENCES-BASEL
卷 10, 期 18, 页码 -出版社
MDPI
DOI: 10.3390/app10186427
关键词
digital pathology; image registration; deep learning; disentangled autoencoder
类别
资金
- Czech Ministry of Education, Youth and Sports [LM2018121, 02.1.01/0.0/0.0/18_046/0015975]
- CETOCOEN EXCELLENCE Teaming 2 project - Horizon2020 [857560]
Featured Application The method described can be applied for stain-independent pathology image registration and content summarization. A novel deep autoencoder architecture is proposed for the analysis of histopathology images. Its purpose is to produce a disentangled latent representation in which the structure and colour information are confined to different subspaces so that stain-independent models may be learned. For this, we introduce two constraints on the representation which are implemented as a classifier and an adversarial discriminator. We show how they can be used for learning a latent representation across haematoxylin-eosin and a number of immune stains. Finally, we demonstrate the utility of the proposed representation in the context of matching image patches for registration applications and for learning a bag of visual words for whole slide image summarization.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据