Gorriz, J. M. and Segovia, F. and Ramirez, J. and Lassl, A. and Salas-Gonzalez, D. (2011) GMM based SPECT image classification for the diagnosis of Alzheimer's disease. APPLIED SOFT COMPUTING, 11 (2). pp. 2313-2325. ISSN 1568-4946, 1872-9681
Full text not available from this repository. (Request a copy)Abstract
We present a novel classification method of SPECT images based on Gaussian mixture models (GMM) for the diagnosis of Alzheimer's disease. The aims of the model-based approach for density estimation is to automatically select regions of interest (ROIs) and to effectively reduce the dimensionality of the problem. The resulting Gaussians are constructed according to a maximum likelihood criterion employing the Expectation Maximization (EM) algorithm. By considering only the intensity levels inside the Gaussians, the resulting feature space has a significantly reduced dimensionality with respect to former approaches using the voxel intensities directly as features (VAF). With this feature extraction method one relieves the effects of the so-called small sample size problem and nonlinear classifiers may be used to distinguish between the brain images of normal and Alzheimer patients. Our results show that for various classifiers the GMM-based method yields higher accuracy rates than the classification considering all voxel values. (C) 2010 Elsevier B.V. All rights reserved.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | SUPPORT VECTOR MACHINES; EM ALGORITHM; BRAIN; MODEL; RECOGNITION; INFORMATION; PATTERN; HMPAO; SPECT; Alzheimer's disease; Gaussian mixture model; EM algorithm; Support vector machines (SVMs) |
Subjects: | 500 Science > 570 Life sciences |
Divisions: | Biology, Preclinical Medicine > Institut für Biophysik und physikalische Biochemie > Prof. Dr. Elmar Lang |
Depositing User: | Dr. Gernot Deinzer |
Date Deposited: | 25 Jun 2020 07:36 |
Last Modified: | 25 Jun 2020 07:36 |
URI: | https://pred.uni-regensburg.de/id/eprint/21228 |
Actions (login required)
View Item |