Principal component analysis-based techniques and supervised classification schemes for the early detection of Alzheimer's disease

  • Authors:

  • M. López;J. Ramírez;J. M. Górriz;I. Álvarez;D. Salas-Gonzalez;F. Segovia;R. Chaves;P. Padilla;M. Gómez-Río

  • Affiliations:

  • Department of Signal Theory, Networking and Communications, University of Granada, Spain;Department of Signal Theory, Networking and Communications, University of Granada, Spain;Department of Signal Theory, Networking and Communications, University of Granada, Spain;Department of Signal Theory, Networking and Communications, University of Granada, Spain;Department of Signal Theory, Networking and Communications, University of Granada, Spain;Department of Signal Theory, Networking and Communications, University of Granada, Spain;Department of Signal Theory, Networking and Communications, University of Granada, Spain;Department of Signal Theory, Networking and Communications, University of Granada, Spain;Department of Nuclear Medicine, Hospital Universitario Virgen de las Nieves, Granada, Spain

  • Venue:
  • Neurocomputing
  • Year:
  • 2011

Quantified Score

Hi-index 0.02

Visualization

Abstract

In Alzheimer's disease (AD) diagnosis process, functional brain image modalities such as Single-Photon Emission Computed Tomography (SPECT) and Positron Emission Tomography (PET) have been widely used to guide the clinicians. However, the current evaluation of these images entails a succession of manual reorientations and visual interpretation steps, which attach in some way subjectivity to the diagnostic. In this work, a complete computer aided diagnosis (CAD) system for an automatic evaluation of the neuroimages is presented. Principal component analysis (PCA)-based methods are proposed as feature extraction techniques, enhanced by other linear approaches such as linear discriminant analysis (LDA) or the measure of the Fisher discriminant ratio (FDR) for feature selection. The final features allow to face up the so-called small sample size problem and subsequently they are used for the study of neural networks (NN) and support vector machine (SVM) classifiers. The combination of the presented methods achieved accuracy results of up to 96.7% and 89.52% for SPECT and PET images, respectively, which means a significant improvement over the results obtained by the classical voxels-as-features (VAF) reference approach.