SPECTRAL CLUSTERING BASED PARCELLATION OF FETAL BRAIN MRI - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2015

SPECTRAL CLUSTERING BASED PARCELLATION OF FETAL BRAIN MRI

Résumé

Many neuroimaging studies are based on the idea that there are distinct brain regions that are functionally or micro-anatomically homogeneous. Obtaining such regions in an au-tomatic way is a challenging task for fetal data due to the lack of strong and consistent anatomical features at the early stages of brain development. In this paper we propose the use of an automatic approach for parcellating fetal cerebral hemi-spheric surfaces into K regions via spectral clustering. Unlike previous methods, our technique has the crucial advantage of only relying on intrinsic geometrical properties of the corti-cal surface and thus being unsupervised. Results on a data-set of fetal brain MRI acquired in utero demonstrated a convinc-ing parcellation reproducibility of the cortical surfaces across fetuses with varying gestational ages and folding magnitude.
Fichier principal
Vignette du fichier
pepe_isbi_2015.pdf (371.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01114989 , version 1 (10-02-2015)

Identifiants

  • HAL Id : hal-01114989 , version 1

Citer

Antonietta Pepe, Guillaume Auzias, François de Guio, François Rousseau, David Germanaud, et al.. SPECTRAL CLUSTERING BASED PARCELLATION OF FETAL BRAIN MRI. 2015. ⟨hal-01114989⟩
599 Consultations
264 Téléchargements

Partager

Gmail Facebook X LinkedIn More