Title :
Identification of imaging biomarkers responsible for Alzheimer´s Disease using a McRBFN classifier
Author :
Mahanand, B.S. ; Babu, G. Sateesh ; Suresh, S. ; Sundararajan, N.
Author_Institution :
Dept. of Inf. Sci. & Eng., Sri Jayachamarajendra Coll. of Eng., Mysore, India
Abstract :
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.
Keywords :
biomedical MRI; diseases; image classification; medical image processing; radial basis function networks; AD detection; Alzheimer´s disease detection; McRBFN classifier; PBL-McRBFN-RFE classifier; RFE approach; biomarker responsible imaging; magnetic resonance image; meta-cognitive radial basis function network classifier; projection-based learning-McRBFN; recursive feature elimination approach; Alzheimer´s disease; Biomarkers; Feature extraction; Magnetic resonance imaging; Training;
Conference_Titel :
Cognitive Computing and Information Processing (CCIP), 2015 International Conference on
Conference_Location :
Noida
DOI :
10.1109/CCIP.2015.7100723