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

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.

[1]  Alexander Hammers,et al.  SPM-based count normalization provides excellent discrimination of mild Alzheimer's disease and amnestic mild cognitive impairment from healthy aging , 2009, NeuroImage.

[2]  R. Jaszczak,et al.  SPECT: Single Photon Emission Computed Tomography , 1980 .

[3]  H J Testa,et al.  Accuracy of single-photon emission computed tomography in differentiating frontotemporal dementia from Alzheimer’s disease , 2006, Journal of Neurology, Neurosurgery & Psychiatry.

[4]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[5]  J. Ashburner,et al.  Nonlinear spatial normalization using basis functions , 1999, Human brain mapping.

[6]  H J Testa,et al.  A clinical role for 99mTc-HMPAO SPECT in the investigation of dementia? , 1998, Journal of neurology, neurosurgery, and psychiatry.

[7]  Ingeborg Goethals,et al.  Brain SPET perfusion in early Alzheimer’s disease: where to look? , 2002, European Journal of Nuclear Medicine and Molecular Imaging.

[8]  Jian Zhou,et al.  Sequential weighted least squares algorithm for PET image reconstruction , 2006, Digit. Signal Process..

[9]  Paolo Vitali,et al.  Hippocampal perfusion in mild Alzheimer's disease , 2000, Psychiatry Research: Neuroimaging.

[10]  X. Wu,et al.  Individual patient diagnosis of AD and FTD via high-dimensional pattern classification of MRI , 2008, NeuroImage.

[11]  Nicholas Ayache.  Analyzing 3D Images of the Brain , 1996, NeuroImage.

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

[13]  P. Bruyant.  Analytic and iterative reconstruction algorithms in SPECT. , 2002, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[14]  Glenn Fung,et al.  SVM Feature Selection for Classification of SPECT Images of Alzheimer's Disease Using Spatial Information , 2005, ICDM.

[15]  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.

[16]  Scott T. Grafton,et al.  Automated image registration: I. General methods and intrasubject, intramodality validation. , 1998, Journal of computer assisted tomography.

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

[18]  R. Tibshirani,et al.  Improvements on Cross-Validation: The 632+ Bootstrap Method , 1997 .

[19]  N. Foster,et al.  Metabolic reduction in the posterior cingulate cortex in very early Alzheimer's disease , 1997, Annals of neurology.

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

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

[22]  Ron Brookmeyer,et al.  Modeling the Effect of Alzheimer's Disease on Mortality , 2007, The international journal of biostatistics.

[23]  R. V. Van Heertum,et al.  SPECT perfusion imaging in the diagnosis of Alzheimer’s disease , 2001, Neurology.

[24]  Fabian J. Theis,et al.  Effective Emission Tomography Image Reconstruction Algorithms for SPECT Data , 2008, ICCS.

[25]  R. English,et al.  Spect Single-Photon Emission Computed Tomography: A Primer , 1986 .