Automated detection of Alzheimer?s disease using bi-directional empirical model decomposition

The build-up of beta-amyloid and rapid spread of tau proteins in the brain cause the death of neurons, leading to Alzheimer's disease (AD). AD is a form of dementia, and the symptoms include memory loss and decision-making difficulties. Current advanced diagnostic modalities are costly or unable to detect the histopathological features of AD. Hence a computational intelligence tool (CIT) for AD diagnosis is proposed in this study. The magnetic resonance images (MRI) of the brain are pre-processed using an adaptive histogram, and decomposed into four IMFS using bidirectional empirical mode decomposition (BEMD). Local binary patterns (LBP) are then computed per IMF, and the histograms are concatenated. Adaptive synthetic sampling (ADASYN) is applied to balance the dataset and Student's t-test is utilized for selection of highly significant features, within each fold for ten-fold validation. Amongst other classifiers, SVM-Poly 1 and random forest(RF) were employed for classification, yielding the highest accuracy of 93.9% each. Our study concludes that the recommended CIT is useful for the automatic classification of AD versus normal MRI imagery in hospitals. © 2020