Neuroscience Letters 461 (2009) 293–297 Contents lists available at ScienceDirect Neuroscience Letters journal homepage: www.elsevier.com/locate/neulet SVM-based computer-aided diagnosis of the Alzheimer’s disease using t-test NMSE feature selection with feature correlation weighting R. Chaves, J. Ramírez ∗ , J.M. Górriz, M. López, D. Salas-Gonzalez, I. Álvarez, F. Segovia Department of Signal Theory, Networking and Communications, University of Granada, Spain article info Article history: Received 15 May 2009 Received in revised form 16 June 2009 Accepted 17 June 2009 Keywords: SPECT Brain Imaging Classification Computer-aided diagnosis Alzheimer’s disease Support Vector machine abstract This letter shows a computer-aided diagnosis (CAD) technique for the early detection of the Alzheimer’s disease (AD) based on single photon emission computed tomography (SPECT) image feature selection and a statistical learning theory classifier. The challenge of the curse of dimensionality is addressed by reducing the large dimensionality of the input data and defining normalized mean squared error features over regions of interest (ROI) that are selected by a t-test feature selection with feature correlation weighting. Thus, normalized mean square error (NMSE) features of cubic blocks located in the temporo- parietal brain region yields peak accuracy values of 98.3% for almost linear kernel support vector machine (SVM) defined over the 20 most discriminative features extracted. This new method outperformed recent developed methods for early AD diagnosis. © 2009 Elsevier Ireland Ltd. All rights reserved. Alzheimer’s disease (AD) is a progressive neurodegenerative disor- der first affecting memory functions and then gradually affecting all cognitive functions with behavioral impairments and eventu- ally causing death. According to the latest estimates, the global prevalence of AD will quadruple to 100 million by 2050. To date there is no single test or biomarker that can predict whether a particular person will develop the disease. Its diagnosis is based on the information provided by a careful clinical examination, a thorough interview of the patient and relatives, and a neuropsy- chological assessment. A regional cerebral blood flow (rCBF) study by means of single photon emission computed tomography (SPECT) is commonly used as a complimentary diagnostic tool in addition to the clinical findings [7]. However, in late-onset AD there are min- imal perfusion alterations in the mild stages of the disease, and age-related changes, which are frequently seen in healthy aged people, have to be discriminated from the minimal disease-specific changes. These minimal changes in the images make visual diag- nosis a difficult task that requires experienced explorers. Even with this problem still unsolved, the potential of computer-aided diag- nosis (CAD) has not been explored in depth [10,13,16,6]. Since their introduction in the late seventies, Support Vector Machines (SVMs) [17] marked the beginning of a new era in the learning from examples paradigm. Recent developments in defin- ing and training statistical classifiers make it possible to build ∗ Corresponding author at: Dpto. Teoría de la Se˜ nal, Telemática y Comunicaciones, Periodista Daniel Saucedo Aranda 18071, Granada, Spain. Tel.: +34 958 240842; fax: +34 958240831. E-mail address: javierrp@ugr.es (J. Ramírez). reliable classifiers in very small sample size problems [3] since pattern recognition systems based on SVM circumvent the curse of dimensionality, and even may find nonlinear decision boundaries for small training sets. This paper shows a new feature extraction and selection method for SVM-based classification of SPECT images and the design of an AD CAD system. The SPECT image acquisition and preprocessing and the statis- tical methods used for feature extraction and feature selection is presented in this article followed by the experiments that were conducted in order to evaluate the proposed methods and the con- clusions. Finally, basic notions of SVM are explained in Appendix A. The proposed CAD techniques were evaluated by means of a SPECT image database that was especially collected during a con- current study focussing on early AD diagnosis. Each patient was injected with a gamma emitting technetium-99m labeled ethyl cys- teinate dimer ( 99m Tc-ECD) radiopharmaceutical and the SPECT scan was acquired by means of a 3-head gamma camera Picker Prism 3000. Brain perfusion images were reconstructed from projection data by filtered backprojection (FBP) in combination with a Butter- worth noise filter. SPECT images were spatially normalized [12] in order to ensure that a given voxel in different images refers to the same anatomical position. This process was done by using Statisti- cal Parametric Mapping (SPM) [5] yielding 69 × 95 × 79 normalized SPECT images. The normalization method assumed a general affine model with 12 parameters and a cost function which presents an extreme value when the template and the image are matched together. Once the image is normalized by means of an affine trans- formation, it is registered using a more complex non-rigid spatial transformation model. Finally, intensity level is normalized to the 0304-3940/$ – see front matter © 2009 Elsevier Ireland Ltd. All rights reserved. doi:10.1016/j.neulet.2009.06.052