The foundation for classification of AD is pathology with several subtypes being recognized [7].
While lauding a decade of efforts to delineate sub-classifications of AD, it is important to emphasize that AD remains a single disease entity throughout all its stages.
Biomarkers in cerebrospinal fluid or structural and functional neuroimaging are being used to assist in clinical classification of AD [ 11].
The combination of MFG PIB uptake and HIP MRglc improved the classification of AD and MCI to 83% (increment Χ[1] = 4.1, p < .01, SS = 82, SP = 85).
Comparing PIB-MFG and FDG-HIP, there was high diagnostic agreement for the classification of AD (94%) and NL (86%) subjects.
However, only three among these studies have a case number more than 80 [ 7, 22, 68] and all of them either include only mild-to-moderate AD [ 22, 68] or have clear severity-classification of AD [ 7].
The potential of cortical thickness for the classification of AD has already been proposed [ 47– 49], and thus it is of no surprise that such features could aid in the classification of HC and MCI subjects.
Furthermore, the classification of AD cases into subtypes and the resulting clinical phenotype is ultimately determined by the localization and distribution of tau pathology in the hippocampus and association cortices (6).
Accordingly, clinical classification of AD patients was defined by two or more deficits in cognition, progressive worsening of memory and other cognitive abilities [ 3], and onset age between 65 and 85 years.
This segmentation approach has been used for multivariate classification of AD and HC [ 17], MCI volumetric studies [ 9, 10], neuropsychological-image analysis [ 18, 19], imaging-genetic analysis [ 20, 21], and biomarker discovery [ 22].
