Use of SVM Methods with Surface-Based Cortical and Volumetric Subcortical Measurements to Detect Alzheimer's Disease

Abstract

Here, we examine morphological changes in cortical thickness of patients with Alzheimer's disease (AD) using image analysis algorithms for brain structure segmentation and study automatic classification of AD patients using cortical and volumetric data. Cortical thickness of AD patients (n=14) was measured using MRI cortical surface-based analysis and compared with healthy subjects (n=20). Data was analyzed using an automated algorithm for tissue segmentation and classification. A Support Vector Machine (SVM) was applied over the volumetric measurements of subcortical and cortical structures to separate AD patients from controls. The group analysis showed cortical thickness reduction in the superior temporal lobe, parahippocampal gyrus, and enthorhinal cortex in both hemispheres. We also found cortical thinning in the isthmus of cingulate gyrus and middle temporal gyrus at the right hemisphere, as well as a reduction of the cortical mantle in areas previously shown to be associated with AD. We also confirmed that automatic classification algorithms (SVM) could be helpful to distinguish AD patients from healthy controls. Moreover, the same areas implicated in the pathogenesis of AD were the main parameters driving the classification algorithm. While the patient sample used in this study was relatively small, we expect that using a database of regional volumes derived from MRI scans of a large number of subjects will increase the SVM power of AD patient identification.

Characterization of major depressive disorder using a multiparametric classification approach based on high resolution structural images

“…19 Support vector machine (SVM) 20,21 is a multivariate pattern analysis technique that has emerged as a powerful tool in a wide range of biomedical applications owing to its ability to learn to categorize complex, high-dimensional training data and generalize the learned classification rules to unseen data. 22 In recent years it has been widely used to classify various neuropsychiatric and neurologic disorders, such as Alzheimer disease, 23 autism 24 and schizophrenia 25 (see the review article by Orrù and colleagues 20 ). Support vector machine typically involves a training phase and a testing phase.…”

Can neuroimaging be used as a support to diagnosis of borderline personality disorder? An approach based on computational neuroanatomy and machine learning

“…This progress motivated the investigation of the clinical value of these innovative technologies (Davatzikos et al, 2005), such as the automated quantitative morphological analysis implemented in freesurfer package (Ecker et al, 2010;Oliveira et al, 2010). The extraction of anatomical information from segmented brain regions is an attractive tool, since it is not subjective or user-dependent as conventional visual inspection, which can only be carried out by trained radiologists (Klöppel et al, 2008).…”

“…Kasparek et al (2011) have applied the maximum linear discriminant analysis (regularized LDA) to gray-matter coefficients of VBM analysis in order to classify schizophrenic patients from healthy controls (overall accuracy of 72%). Oliveira et al (2010) used radial basis function SVM classification to distinguish patients with Alzheimer's disease from healthy controls based on volumetric measurements of subcortical and cortical structures (accuracy of 88.2%). More recently, Sato et al (2011) have explored the clinical applications of classifiers to discriminate antisocial personality disorder subjects from controls, achieving an overall accuracy of 80%.…”

Multivariate Analysis of Single-Sweep Evoked Brain Potentials for Pharmaco-Electroencephalography

“…A similar strategy may be applicable to pharmaco-EEG, since the common waveforms before and after drug administration are thought to reflect the pain response. Amplitudes may then be classified by machine-learning methods such as the support vector machine (SVM), which has been successfully applied in many other biomedical applications [14,15,16,17]. One advantage of the SVM is that it does not require a priori information to calculate an optimal hyperplane to separate conditions and hence is capable of detecting an unbiased decision rule [18,19].…”