Brain subject segmentation in MR image for classifying Alzheimer’s disease using adaboost with information fuzzy network classifier

Abstract

Alzheimer’s disease (AD) is a neurodegenerative brain disorder which develops gradually over several years of time period. It is not always understandable at initially because which starts with few symptoms can partly cover with some other disorders. In some case, it could be very difficult to differentiate Alzheimer’s from mild cognitive impairment which can be understood in normal aging. In clinical visualization of brain disorders, magnetic resonance imaging takes place an important role in diagnosis and period before a surgical operation planning. In order to extract the features from the MRI brain image, segmentation process has been performed to segment different brain matters. The segmentation task is executed with the help of patch-based clustering principle, and three different labels were assigned for grouping gray matter (GM), white matter (WM), and skull region. Various features which are chosen from the segmented brain GM and WM to feed as input to the AdaBoost with information fuzzy network classifier for classifying the stages of the AD/MCI.