Classification of Alzheimer's disease and prediction of mild cognitive impairment-to-Alzheimer's conversion from structural magnetic resource imaging using feature ranking and a genetic algorithm. (1st April 2017)

• Record Type: Journal Article
• Authors: Beheshti, Iman; Demirel, Hasan; Matsuda, Hiroshi
• Is Part Of: Computers in biology and medicine. Volume 83(2017)
• Page Start: 109
• Page End: 119
• Publication Date: 2017-04-01
• Subjects: Alzheimer's disease -- Mild cognitive impairment conversion -- Feature ranking -- Genetic algorithm; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2017.02.011
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: We developed a novel computer-aided diagnosis (CAD) system that uses feature-ranking and a genetic algorithm to analyze structural magnetic resonance imaging data; using this system, we can predict conversion of mild cognitive impairment (MCI)-to-Alzheimer's disease (AD) at between one and three years before clinical diagnosis. The CAD system was developed in four stages. First, we used a voxel-based morphometry technique to investigate global and local gray matter (GM) atrophy in an AD group compared with healthy controls (HCs). Regions with significant GM volume reduction were segmented as volumes of interest (VOIs). Second, these VOIs were used to extract voxel values from the respective atrophy regions in AD, HC, stable MCI (sMCI) and progressive MCI (pMCI) patient groups. The voxel values were then extracted into a feature vector. Third, at the feature-selection stage, all features were ranked according to their respective t -test scores and a genetic algorithm designed to find the optimal feature subset. The Fisher criterion was used as part of the objective function in the genetic algorithm. Finally, the classification was carried out using a support vector machine (SVM) with 10-fold cross validation. We evaluated the proposed automatic CAD system by applying it to baseline values from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset (160 AD, 162 HC, 65 sMCI and 71 pMCI subjects). The experimental results indicated that the proposed system is capable of distinguishing between sMCI and pMCI patients, and would be appropriate for practical use in a clinical setting. Graphical abstract: Highlights: A novel feature selection method using feature ranking and genetic algorithm is proposed. Fisher criterion is used as part of the objective function in the genetic algorithm. We use only baseline MRI data for proposed system. A standard SVM classifier is used to evaluate the performance. Combination of feature-ranking and genetic algorithm is a reliable technique for MCI conversion prediction and early detection of AD.