Automated diagnosis of Alzheimer´s disease using Gaussian mixture model based on cortical thickness

Research on neuropathology indicates that Alzheimer´s disease is characterized by loss of neurons and synapses in the cerebral cortex and other subregions, which can be measured by the thickness of cortex from the magnetic resonance imaging (MRI). A classification method based on Gaussian mixture model (GMM) under Bayesian framework is proposed to facilitate the automated diagnosis of Alzheimer´s disease based on the cortical thickness, and EM algorithm is employed to solve the parameters of Gaussian mixture model. The experiment shows that our method is outstanding over the common supervised learning methods.