Analysis of SPECT brain images for the diagnosis of Alzheimer's disease using moments and support vector machines

Neurosci Lett. 2009 Sep 11;461(1):60-4. doi: 10.1016/j.neulet.2009.05.056. Epub 2009 May 27.

Abstract

This paper presents a computer-aided diagnosis technique for improving the accuracy of diagnosing the Alzheimer's type dementia. The proposed methodology is based on the calculation of the skewness for each m-by-m-by-m sliding block of the SPECT brain images. The center pixel in this m-by-m-by-m block is replaced by the skewness value to build a new 3-D brain image which is used for classification purposes. After that, voxels which present a Welch's t-statistic between classes, Normal and Alzheimer's images, higher (or lower) than a threshold are selected. The mean, standard deviation, skewness and kurtosis are calculated for these selected voxels and they are subjected as features to linear kernel based support vector machine classifier. The proposed methodology reaches accuracy higher than 99% in the classification task.

MeSH terms

  • Alzheimer Disease / diagnostic imaging*
  • Brain / diagnostic imaging*
  • Cysteine / analogs & derivatives
  • Humans
  • Image Interpretation, Computer-Assisted*
  • Organotechnetium Compounds
  • Radiopharmaceuticals
  • Tomography, Emission-Computed, Single-Photon

Substances

  • Organotechnetium Compounds
  • Radiopharmaceuticals
  • technetium Tc 99m bicisate
  • Cysteine