SVM-based CAD system for early detection of the Alzheimer's disease using kernel PCA and LDA

Single-photon emission tomography (SPECT) imaging has been widely used to guide clinicians in the early Alzheimer's disease (AD) diagnosis challenge. However, AD detection still relies on subjective steps carried out by clinicians, which entail in some way subjectivity to the final diagnosis. In this work, kernel principal component analysis (PCA) and linear discriminant analysis (LDA) are applied on functional images as dimension reduction and feature extraction techniques, which are subsequently used to train a supervised support vector machine (SVM) classifier. The complete methodology provides a kernel-based computer-aided diagnosis (CAD) system capable to distinguish AD from normal subjects with 92.31% accuracy rate for a SPECT database consisting of 91 patients. The proposed methodology outperforms voxels-as-features (VAF) that was considered as baseline approach, which yields 80.22% for the same SPECT database.

[1]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[2]  V. Vapnik.  Estimation of Dependences Based on Empirical Data , 2006 .

[3]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[4]  Juan Manuel Górriz,et al.  Improved Gauss-Newton optimisation methods in affine registration of SPECT brain images , 2008 .

[5]  Hanqing Lu,et al.  Solving the small sample size problem of LDA , 2002, Object recognition supported by user interaction for service robots.

[6]  Glenn Fung,et al.  SVM feature selection for classification of SPECT images of Alzheimer's disease using spatial information , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[7]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[8]  A. Lassl,et al.  Automatic computer aided diagnosis tool using component-based SVM , 2008, 2008 IEEE Nuclear Science Symposium Conference Record.

[9]  J. Ramírez,et al.  SVM-based computer-aided diagnosis of the Alzheimer's disease using t-test NMSE feature selection with feature correlation weighting , 2009, Neuroscience Letters.

[10]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[11]  A. Andersen,et al.  Principal component analysis of the dynamic response measured by fMRI: a generalized linear systems framework. , 1999, Magnetic resonance imaging.

[12]  Barry Horwitz,et al.  An Automatic Threshold-Based Scaling Method for Enhancing the Usefulness of Tc-HMPAO SPECT in the Diagnosis of Alzheimer's Disease , 1998, MICCAI.

[13]  T. Ohnishi,et al.  Longitudinal Evaluation of Early Alzheimer's Disease Using Brain Perfusion Spect the Recruitment Was For , 2000 .

[14]  Yaakov Stern,et al.  Multivariate and univariate neuroimaging biomarkers of Alzheimer's disease , 2008, NeuroImage.

[15]  Juan Manuel Górriz,et al.  Alzheimer's diagnosis using eigenbrains and support vector machines , 2009 .

[16]  Juan Manuel Górriz,et al.  Automatic tool for Alzheimer's disease diagnosis using PCA and Bayesian classification rules , 2009 .

[17]  Karl J. Friston,et al.  Statistical parametric mapping , 2013 .

[18]  Paul D. Townsend,et al.  Rayleigh backscattering impairments in access networks with centralised light source , 2006 .

[19]  Juan Manuel Górriz,et al.  SVM-based speech endpoint detection using contextual speech features , 2006 .

[20]  J. Baron,et al.  Efficient principal component analysis for multivariate 3D voxel‐based mapping of brain functional imaging data sets as applied to FDG‐PET and normal aging , 2003, Human brain mapping.

[21]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[22]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[23]  Yaakov Stern,et al.  Covariance PET patterns in early Alzheimer's disease and subjects with cognitive impairment but no dementia: utility in group discrimination and correlations with functional performance , 2004, NeuroImage.

[24]  Karl J. Friston,et al.  A multivariate analysis of PET activation studies , 1996, Human brain mapping.