Sub-cortical brain structure segmentation using F-CNN's

Abstract : In this paper we propose a deep learning approach for segmenting sub-cortical structures of the human brain in Magnetic Resonance (MR) image data. We draw inspiration from a state-of-the-art Fully-Convolutional Neural Network (F-CNN) architecture for semantic segmentation of objects in natural images, and adapt it to our task. Unlike previous CNN-based methods that operate on image patches, our model is applied on a full blown 2D image, without any alignment or registration steps at testing time. We further improve segmentation results by interpreting the CNN output as potentials of a Markov Random Field (MRF), whose topology corresponds to a volumetric grid. Alpha-expansion is used to perform approximate inference imposing spatial volumetric homogeneity to the CNN priors. We compare the performance of the proposed pipeline with a similar system using Random Forest-based priors, as well as state-of-art segmentation algorithms, and show promising results on two different brain MRI datasets.
Type de document :
Communication dans un congrès
ISBI 2016: International Symposium on Biomedical Imaging, 2016, Prague, Czech Republic. ISBI 2016: International Symposium on Biomedical Imaging, 2016, 〈http://biomedicalimaging.org/2016/〉
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01265500
Contributeur : Enzo Ferrante <>
Soumis le : vendredi 5 février 2016 - 14:10:14
Dernière modification le : vendredi 12 janvier 2018 - 11:00:15
Document(s) archivé(s) le : vendredi 11 novembre 2016 - 23:04:40

Fichiers

isbi2016_final.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité - Pas d'utilisation commerciale - Pas de modification 4.0 International License

Identifiants

  • HAL Id : hal-01265500, version 1
  • ARXIV : 1602.02130

Citation

Mahsa Shakeri, Stavros Tsogkas, Enzo Ferrante, Sarah Lippe, Samuel Kadoury, et al.. Sub-cortical brain structure segmentation using F-CNN's. ISBI 2016: International Symposium on Biomedical Imaging, 2016, Prague, Czech Republic. ISBI 2016: International Symposium on Biomedical Imaging, 2016, 〈http://biomedicalimaging.org/2016/〉. 〈hal-01265500〉

Partager

Métriques

Consultations de la notice

758

Téléchargements de fichiers

1055