Disentangled Autoencoder for Cross-Stain Feature Extraction in Pathology Image Analysis
| Autoři | |
|---|---|
| Rok publikování | 2020 |
| Druh | Článek v odborném periodiku |
| Časopis / Zdroj | Applied Sciences |
| Fakulta / Pracoviště MU | |
| Citace | |
| www | https://doi.org/10.3390/app10186427 |
| Doi | http://dx.doi.org/10.3390/app10186427 |
| Klíčová slova | digital pathology; image registration; deep learning; disentangled autoencoder |
| Přiložené soubory | |
| Popis | 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. |
| Související projekty: |