Simultaneous super-resolution and segmentation using a generative adversarial network: Application to neonatal brain MRI

Abstract : The analysis of clinical neonatal brain MRI remains challenging due to low anisotropic resolution of the data. In most pipelines, images are first re-sampled using interpolation or single image super-resolution techniques and then segmented using (semi-)automated approaches. Image reconstruction and segmentation are then performed separately. In this paper, we propose an end-to-end generative adversarial network for simultaneous high-resolution reconstruction and segmentation of brain MRI data. This joint approach is first assessed on the simulated low-resolution images of the high-resolution neonatal dHCP dataset. Then, the learned model is used to enhance and segment real clinical low-resolution images. Results demonstrate the potential of our proposed method with respect to practical medical applications.
Type de document :
Communication dans un congrès
International Symposium on Biomedical Imaging (ISBI), 2019, Venice, Italy
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01895163
Contributeur : Nicolas Passat <>
Soumis le : lundi 14 janvier 2019 - 07:54:36
Dernière modification le : mardi 26 février 2019 - 11:38:05

Fichier

Pham ISBI 2019.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01895163, version 1

Citation

Chi-Hieu Pham, Carlos Tor-Díez, Hélène Meunier, Nathalie Bednarek, Ronan Fablet, et al.. Simultaneous super-resolution and segmentation using a generative adversarial network: Application to neonatal brain MRI. International Symposium on Biomedical Imaging (ISBI), 2019, Venice, Italy. 〈hal-01895163〉

Partager

Métriques

Consultations de la notice

252

Téléchargements de fichiers

32