Strategies for Training Stain Invariant CNNS - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Strategies for Training Stain Invariant CNNS

Résumé

An important part of Digital Pathology is the analysis of multiple digitised whole slide images from differently stained tissue sections. It is common practice to mount consecutive sections containing corresponding microscopic structures on glass slides, and to stain them differently to highlight specific tissue components. These multiple staining modalities result in very different images but include a significant amount of consistent image information. Deep learning approaches have recently been proposed to analyse these images in order to automatically identify objects of interest for pathologists. These supervised approaches require a vast amount of annotations, which are difficult and expensive to acquire-a problem that is multiplied with multiple stainings. This article presents several training strategies that make progress towards stain invariant networks. By training the network on one commonly used staining modality and applying it to images that include corresponding but differently stained tissue structures, the presented unsupervised strategies demonstrate significant improvements over standard training strategies.
Fichier principal
Vignette du fichier
main.pdf (1.24 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02283639 , version 1 (11-09-2019)

Identifiants

Citer

Thomas Lampert, Odyssée Merveille, Jessica Schmitz, Germain Forestier, Friedrich Feuerhake, et al.. Strategies for Training Stain Invariant CNNS. 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI), Apr 2019, Venise, Italy. pp.905-909, ⟨10.1109/ISBI.2019.8759266⟩. ⟨hal-02283639⟩
71 Consultations
58 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More