Evaluation of Alzheimer’s Disease by Analysis of MR Images Using Multilayer Perceptrons, Polynomial Nets and Kohonen LVQ Classifiers

摘要: Alzheimer's disease is the most common cause of dementia, yet hard to diagnose precisely without invasive techniques, particularly at onset disease. This work approaches image analysis and classification synthetic multispectral images composed by diffusion-weighted magnetic resonance (MR) cerebral for evaluation cerebrospinal fluid area its correlation with advance The MR were acquired from an system a clinical 1.5 T tomographer. methods are based on multilayer perceptrons, polynomial nets Kohonen LVQ classifiers. results used improve usual apparent diffusion coefficient map.