Decision-making systems trained on structural magnetic resonance imaging data of subjects affected by the Alzheimer's disease (AD) and healthy controls (CTRL) are becoming widespread prognostic tools for subjects with mild cognitive impairment (MCI). This study compares the performances of three classification methods based on support vector machines (SVMs), using as initial sets of brain voxels (ie, features): (1) the segmented grey matter (GM); (2) regions of interest (ROIs) by voxel-wise t-test filtering; (3) parceled ROIs, according to prior knowledge. The recursive feature elimination (RFE) is applied in all cases to investigate whether feature reduction improves the classification accuracy. We analyzed more than 600 AD Neuroimaging Initiative (ADNI) subjects, training the SVMs on the AD/CTRL dataset, and evaluating them on a trial MCI dataset. The classification performance, evaluated as the area under the receiver operating characteristic curve (AUC), reaches AUC = (88.9 ± .5)% in 20-fold cross-validation on the AD/CTRL dataset, when the GM is classified as a whole. The highest discrimination accuracy between MCI converters and nonconverters is achieved when the SVM-RFE is applied to the whole GM: with AUC reaching (70.7 ± .9)%, it outperforms both ROI-based approaches in predicting the AD conversion.

Predictive models based on Support Vector Machines: whole-brain versus regional analysis of structural MRI in the Alzheimer’s disease

FANTACCI, MARIA EVELINA
Ultimo
2015-01-01

Abstract

Decision-making systems trained on structural magnetic resonance imaging data of subjects affected by the Alzheimer's disease (AD) and healthy controls (CTRL) are becoming widespread prognostic tools for subjects with mild cognitive impairment (MCI). This study compares the performances of three classification methods based on support vector machines (SVMs), using as initial sets of brain voxels (ie, features): (1) the segmented grey matter (GM); (2) regions of interest (ROIs) by voxel-wise t-test filtering; (3) parceled ROIs, according to prior knowledge. The recursive feature elimination (RFE) is applied in all cases to investigate whether feature reduction improves the classification accuracy. We analyzed more than 600 AD Neuroimaging Initiative (ADNI) subjects, training the SVMs on the AD/CTRL dataset, and evaluating them on a trial MCI dataset. The classification performance, evaluated as the area under the receiver operating characteristic curve (AUC), reaches AUC = (88.9 ± .5)% in 20-fold cross-validation on the AD/CTRL dataset, when the GM is classified as a whole. The highest discrimination accuracy between MCI converters and nonconverters is achieved when the SVM-RFE is applied to the whole GM: with AUC reaching (70.7 ± .9)%, it outperforms both ROI-based approaches in predicting the AD conversion.
2015
Retico, A; Bosco, P; Cerello, P; Fiorina, E; Chincarini, A; Fantacci, MARIA EVELINA
File in questo prodotto:
File Dimensione Formato  
Predictive Models Based on Support Vector Machines.pdf

solo utenti autorizzati

Licenza: Importato da Ugov Ricerca - Accesso privato/ristretto
Dimensione 894.5 kB
Formato Adobe PDF
894.5 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
nihms622110.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.81 MB
Formato Adobe PDF
1.81 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/518074
Citazioni
  • ???jsp.display-item.citation.pmc??? 14
  • Scopus 35
  • ???jsp.display-item.citation.isi??? 32
social impact