Alzheimer disease classification based on TSVM and Kernel SVM

Alzheimer disease (AD) is the most general cause of dementia, creates significant socioeconomic and health problems. It is the disease of progressive neurodegenerative disorder which causes the structural change in the brain, affects behavioral problems, cognitive acts, and memory despair. Structural brain imaging plays very important role to identify structural change inside brain associated with AD. We present a novel automated approach for classifying AD from HC (Healthy Controls) using dual-tree complex wavelet transforms (DTCWT) principal coefficients from the transaxial slices of MR images, kernel support vector machine, and twin support vector machine. The stratification result we have obtained using proposed method are similar or higher than those achieved by various conventional AD classification approaches mentioned in the paper.