Identification of imaging biomarkers responsible for Alzheimer´s Disease using a McRBFN classifier

In this paper, we present an approach for Alzheimer´s Disease (AD) detection from magnetic resonance images using Meta-cognitive Radial Basis Function Network (McRBFN) classifier. We propose a Recursive Feature Elimination (RFE) approach with efficient classification method Projection based Learning-McRBFN (referred as PBL-McRBFN-RFE) to identify the most meaningful imaging biomarkers with a predictive power for AD detection in male persons. The study has been conducted using the well-known open access series of imaging studies data set. The performance results of the PBL-McRBFN-RFE classifier clearly indicates the better performance for AD detection. The proposed imaging biomarkers identification mechanism indicates that in male persons insula region may be responsible for the onset of AD.