UNIGE document Professional Article
previous document  unige:114056  next document
add to browser collection

Automated voxel-by-voxel tissue classification for hippocampal segmentation: methods and validation

Tangaro, S
Amoroso, N
Boccardi, M
Bruno, S
Chincarini, A
Ferraro, G
Maglietta, R
show hidden authors show all authors [1 - 12]
Published in Physica Medica. 2014, vol. 30, no. 8, p. 878-887
Abstract The hippocampus is an important structural biomarker for Alzheimer's disease (AD) and has a primary role in the pathogenesis of other neurological and psychiatric diseases. This study presents a fully automated pattern recognition system for an accurate and reproducible segmentation of the hippocampus in structural Magnetic Resonance Imaging (MRI). The method was validated on a mixed cohort of 56 T1-weighted structural brain images, and consists of three processing levels: (a) Linear registration: all brain images were registered to a standard template and an automated method was applied to capture the global shape of the hippocampus. (b) Feature extraction: all voxels included in the previously selected volume were characterized by 315 features computed from local information. (c) Voxel classification: a Random Forest algorithm was used to classify voxels as belonging or not belonging to the hippocampus. In order to improve the classification performance, an adaptive learning method based on the use of the Pearson's correlation coefficient was developed. The segmentation results (Dice similarity index = 0.81 ± 0.03) compare well with other state-of-the art approaches. A validation study was conducted on an independent dataset of 100 T1-weighted brain images, achieving significantly better results than those obtained with FreeSurfer.
Keywords AgedAged, 80 and overAlgorithmsAlzheimer Disease/pathologyBrain Mapping/methodsDatabases, FactualElectronic Data ProcessingFemaleHippocampus/pathologyHumansLinear ModelsMagnetic Resonance ImagingMaleMiddle AgedPattern Recognition, AutomatedReproducibility of ResultsSignal Processing, Computer-AssistedSoftware
PMID: 25018049
Full text
Article (Published version) (1.1 MB) - document accessible for UNIGE members only Limited access to UNIGE
Research group Troubles de mémoire et maladie d'Alzeimer (935)
(ISO format)
TANGARO, S et al. Automated voxel-by-voxel tissue classification for hippocampal segmentation: methods and validation. In: Physica Medica, 2014, vol. 30, n° 8, p. 878-887. doi: 10.1016/j.ejmp.2014.06.044 https://archive-ouverte.unige.ch/unige:114056

239 hits

0 download


Deposited on : 2019-02-08

Export document
Format :
Citation style :