Song Lai1, John Lackey1, Jianrong Shi1
A novel data-driven volumetric imaging statistical analysis methodology was developed for accurate differential diagnosis in individual subjects of Alzheimer's Disease (AD). This research explored the use of the unique datasets in the Alzheimer's Disease Neuroimaging Initiative (ADNI) to develop methodologies for identification of MRI biomarkers for differential diagnosis of AD and MCI in individual subjects. The rich ADNI MRI database were used to train models that recognize the structural differences between groups in comparison (i.e., normal vs. AD, MCI vs. AD, and normal vs. MCI). Preliminary study showed high diagnostic accuracy on individual subjects.