Computer-Aided Diagnosis System for Alzheimer’s Disease Using Different Discrete Transform Techniques

• Published in: American journal of Alzheimer's disease and other dementias Vol. 31; no. 3; pp. 282 - 293
• Main Authors: Dessouky, Mohamed M., Elrashidy, Mohamed A., Taha, Taha E., Abdelkader, Hatem M.
• Format: Journal Article
• Language: English
• Published: Los Angeles, CA SAGE Publications 01.05.2016
• Subjects: Algorithms; Alzheimer Disease - diagnosis; Current Topics in Research; Data Interpretation, Statistical; Diagnosis, Computer-Assisted - methods; Humans; Support Vector Machine; magnetic resonance imaging (MRI); Alzheimer’s disease (AD); feature extraction; discrete transforms; computer-aided diagnosis (CAD)
• ISSN: 1533-3175; 1938-2731; 1938-2731
• DOI: 10.1177/1533317515603957

The different discrete transform techniques such as discrete cosine transform (DCT), discrete sine transform (DST), discrete wavelet transform (DWT), and mel-scale frequency cepstral coefficients (MFCCs) are powerful feature extraction techniques. This article presents a proposed computer-aided diagnosis (CAD) system for extracting the most effective and significant features of Alzheimer’s disease (AD) using these different discrete transform techniques and MFCC techniques. Linear support vector machine has been used as a classifier in this article. Experimental results conclude that the proposed CAD system using MFCC technique for AD recognition has a great improvement for the system performance with small number of significant extracted features, as compared with the CAD system based on DCT, DST, DWT, and the hybrid combination methods of the different transform techniques.