A new color augmentation method for deep learning segmentation of histological images - Mines Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

A new color augmentation method for deep learning segmentation of histological images

Résumé

This paper addresses the problem of labeled data insufficiency in neural network training for semantic segmentation of color-stained histological images acquired via Whole Slide Imaging. It proposes an efficient image augmentation method to alleviate the demand for a large amount of labeled data and improve the network's generalization capacity. Typical image augmentation in bioimaging involves geometric transformation. Here, we propose a new image augmentation technique by combining the structure of one image with the color appearance of another image to construct augmented images on-the-fly for each training iteration. We show that it improves performance in the segmentation of histological images of human skin, and also offers better results when combined with geometric transformation .
Fichier principal
Vignette du fichier
Paper_v2.pdf (2.38 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02167903 , version 1 (28-06-2019)

Identifiants

  • HAL Id : hal-02167903 , version 1

Citer

Yang Xiao, Etienne Decencière, Santiago Velasco-Forero, Hélène Burdin, Thomas Bornschlögl, et al.. A new color augmentation method for deep learning segmentation of histological images. 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI), Apr 2019, Venise, France. ⟨hal-02167903⟩
482 Consultations
3324 Téléchargements

Partager

Gmail Facebook X LinkedIn More