MRI white matter lesion segmentation using an ensemble of neural networks and overcomplete patch-based voting

Abstract : Accurate quantification of white matter hyperintensities (WMH) from Magnetic Resonance Imaging (MRI) is a valuable tool for the analysis of normal brain ageing or neurodegeneration. Reliable automatic extraction of WMH lesions is challenging due to their heterogeneous spatial occurrence, their small size and their diffuse nature. In this paper, we present an automatic method to segment these lesions based on an ensemble of overcomplete patch-based neural networks. The proposed method successfully provides accurate and regular segmentations due to its overcomplete nature while minimizing the segmentation error by using a boosted ensemble of neural networks. The proposed method compared favourably to state of the art techniques using two different neurodegenerative datasets.
Type de document :
Article dans une revue
Computerized Medical Imaging and Graphics, Elsevier, In press, 〈10.1016/j.compmedimag.2018.05.001〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01808412
Contributeur : Pierrick Coupé <>
Soumis le : mardi 5 juin 2018 - 16:13:06
Dernière modification le : jeudi 28 juin 2018 - 01:03:52
Document(s) archivé(s) le : jeudi 6 septembre 2018 - 18:39:39

Fichier

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

Identifiants

Collections

Citation

José Manjón, Pierrick Coupé, Parnesh Raniga, Ying Xia, Patricia Desmond, et al.. MRI white matter lesion segmentation using an ensemble of neural networks and overcomplete patch-based voting. Computerized Medical Imaging and Graphics, Elsevier, In press, 〈10.1016/j.compmedimag.2018.05.001〉. 〈hal-01808412〉

Partager

Métriques

Consultations de la notice

74

Téléchargements de fichiers

74