Computer, Shahrood University of Tech.
Alzheimer's disease is characterized by impaired glucose metabolism and demonstration of amyloid plaques. Individual positron emission tomography tracers may reveal specific signs of pathology that is not readily apparent on inspection of another one. Combination of multitracer positron emission tomography imaging yields promising results. In this paper, 57 Alzheimer's disease neuroimaging initiative subjects that had FDG and PiB-positron emission tomography neuroimaging scans at the same time were used for development of proposed multitracer classification method. The subject’s brain image was automatically parcellated into 48 pre-defined regions of interest. Then 96 features are extracted for each subject. The principal features are extracted using principal component analysis, then they are combined based on intersection strategy. Finally, a support vector machine is adopted to evaluate the classification accuracy. Combination of two tracers with positron emission tomography scan yielded a higher diagnostic accuracy in Alzheimer's disease compared to individual tracer and other combination methods.