Extracting 2D Shape Features for Early Detection of Alzheimers disease

AD is a progressive disease which in its early stages, memory loss is mild, but in severe stage, patients lose the ability to speak and respond to their environment as a result of the brain tissue degeneration The diagnosis of Alzheimer Disease (AD) in its earlier stage is very important. Because early diagnosis is used to prevent a patient from death. The proposed system helps to diagnosis accurate detection of Alzheimer’s disease. In this paper, the input Magnetic Resonance Image (MRI) is preprocessed using median filters and then segmented into Grey Matter (GM), White Matter (WM) and Ventricle. The useful and informative features like shape features are extracted from segmented MRI images for early detection of AD. Finally, a linear Support Vector machine (SVM) is implemented to differentiate AD subjects with normal subjects. Experimental results are shown to demonstrate the accuracy of the proposed method.