Multi-Feature Kernel Discriminant Dictionary Learning for Classification in Alzheimer's Disease

Abstract

Classification of Alzheimer 's disease (AD) from normal control (NC) is important for disease abnormality identification and intervention. The current study focused on distinguishing AD from NC based on the multi-feature kernel supervised within- class-similarity discriminative dictionary learning algorithm (MKSCDDL) we introduced previously, which has been derived outperformance in face recognition. Structural magnetic resonance imaging (sMRI), fluorodeoxyglucose (FDG) positron emission tomography (PET) and florbetapir-PET data from the Alzheimer's disease Neuroimaging Initiative (ADNI) database were adopted for classification between AD and NC. Adopting MKSCDDL, not only the classification accuracy achieved 98.18% for AD vs. NC, which were superior to the results of some other state-of-the-art approaches (MKL, JRC, and mSRC), but also testing time achieved outperforming results. The MKSCDDL procedure was a promising tool in assisting early diseases diagnosis using neuroimaging data.