Date created: | Last Updated:

Category: Project

Description: Alzheimer’s disease (AD) is the most prevalent form of dementia, with biomarkers including gray matter atrophy. The accurate diagnosis of AD, especially in the early phases is very important for timely therapy, disease modifying drug development, and possible delay of the disease. It has been suggested that brain atrophy as measured with structural magnetic resonance imaging (sMRI) can be an efficacy marker of neurodegeneration. We computed brain areas’ volume and thickness in cortical and subcortical brain regions from T1-weighted magnetic resonance imaging (T1-MRI) data acquired by the Alzheimer’s disease Neuroimaging Initiative (ADNI). Participants included 54 patients with early mild cognitive impairment (EMCI) and 56 cognitively normal (CN) subjects. The data was processed to obtain volumetry data of the whole brain and in particular subfields of the hippocampus using three automated segmentation methods (CAT, volBrain and HIPS). Statistical method and Particle swarm optimization (PSO) algorithm were used to select features that could discriminate between early MCI patients from CN using an artificial neural network (ANN) classifier. While statistical method achieved a maximum accuracy of 87%, the PSO optimization method achieved classification accuracy of 96%. The classification accuracy achieved using PSO is higher than the previously suggested methods of classification of CN and EMCI using a single modality of imaging data. Our results show that biomarkers based on MRI hold promise for early detection and differential diagnosis of the early stages of AD.