Relationship Induced Multi – template Learning for Diagnosis of Alzheimer’s Disease and Mild Cognitive Impairment

Abstract— based on multiple templates usually achieve better performance, compared to those using only a single template for rocessing medical images. However, most existing multi-template based methods simply average or concatenate multiple sets of features extracted from different templates, which potentially ignoring important structural information contained in the multi-template data. Accordingly, in his paper, we propose a novel relationship induced multi-template learning method for automatic diagnosis of Alzheimer’s disease(AD) and ts prodromal stage, i.e., mild cognitive impairment (MCI), by explicitly modeling structural information in the multi-template data. Specifically, we first nonlinearly register each brain’s magnetic resonance (MR) image separately onto multiple pre-selected templates, and then extract multiple sets of features for this MR image. Next, we develop a novel feature selection algorithm by introducing two egularization terms to model the relationships among templates and among individual subjects. Using these selected features Corresponding to multiple templates, we then construct multiple support vector machine (SVM) classifiers. Finally, an ensemble classification is used to Combine outputs of all SVM classifiers, for achieving the final result. We evaluate our proposed method with 459 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, including 97 AD patients, 128 normal controls (NC), 117 progressive MCI (pMCI) atients, and 117 stable MCI (sMCI) patients. The experimental results demonstrate promising classification performance, ompared < final year projects >