A Computer Aided Diagnosis System for Identifying Alzheimer’s from MRI Scan using Improved Adaboost

• Published in: Journal of medical systems Vol. 43; no. 3; pp. 76 - 8
• Main Authors: Saravanakumar, S., Thangaraj, P.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2019; Springer Nature B.V
• Subjects: Abnormalities; Alzheimer's disease; Automatic control; Brain; Classifiers; Cognitive ability; Data analysis; Data collection; Data processing; Fitness; Genetic algorithms; Health Informatics; Health Sciences; Image & Signal Processing; Machine learning; Magnetic resonance imaging; Medical diagnosis; Medicine; Medicine & Public Health; Morphometry; Neuroimaging; NMR; Nuclear magnetic resonance; Permutations; Principal components analysis; Reproductive fitness; Statistics for Life Sciences; Substantia grisea; Upper bounds; Wearable Computing Techniques for Smart Health; Alzheimer’s Disease (AD); Principal Component Analysis (PCA); Magnetic Resonance Imaging (MRI); Voxel-Based Morphometry (VBM); Genetic Algorithms (GA) and Greedy Search
• ISSN: 0148-5598; 1573-689X; 1573-689X
• DOI: 10.1007/s10916-018-1147-7

The recent studies in Morphometric Magnetic Resonance Imaging (MRI) have investigated the abnormalities in the brain volume that have been associated diagnosing of the Alzheimer’s Disease (AD) by making use of the Voxel-Based Morphometry (VBM). The system permits the evaluation of the volumes of grey matter in subjects such as the AD or the conditions related to it and are compared in an automated manner with the healthy controls in the entire brain. The article also reviews the findings of the VBM that are related to various stages of the AD and also its prodrome known as the Mild Cognitive Impairment (MCI). For this work, the Ada Boost classifier has been proposed to be a good selector of feature that brings down the classification error’s upper bound. A Principal Component Analysis (PCA) had been employed for the dimensionality reduction and for improving efficiency. The PCA is a powerful, as well as a reliable, tool in data analysis. Calculating fitness scores will be an independent process. For this reason, the Genetic Algorithm (GA) along with a greedy search may be computed easily along with some high-performance systems of computing. The primary goal of this work was to identify better collections or permutations of the classifiers that are weak to build stronger ones. The results of the experiment prove that the GAs is one more alternative technique used for boosting the permutation of weak classifiers identified in Ada Boost which can produce some better solutions compared to the classical Ada Boost.