Superiority of 3-dimensional stereotactic surface projection analysis over visual inspection in discrimination of patients with very early Alzheimer's disease from controls using brain perfusion SPECT

In Alzheimer's disease (AD), regional cerebral blood flow (rCBF) in the posterior cingulate gyri and precunei has been reported to decrease even at a very early stage. It may be helpful to use statistical image analysis to distinguish slight decreases in rCBF in this area. We compared a 3-dimensional stereotactic surface projection (3D-SSP) technique with visual inspection in the discrimination of patients with very early AD from age-matched controls using brain perfusion SPECT. Methods: SPECT was obtained in 38 patients with probable AD at a very early stage and after a mean interval of 15 mo and in 76 age-matched healthy volunteers. We randomly divided these subjects into 2 groups. The first group was used to identify the areas with significant decreases of rCBF in patients compared with healthy control subjects based on the voxel-based analysis using 3D-SSP. The second group was used to compare the discrimination ability between patients and control subjects by 3D-SSP with that by visual inspection. In the second group, a Z-score map for a SPECT image of a subject was obtained by comparison with mean and SD SPECT images of control subjects for each voxel after anatomic standardization and voxel normalization to reference regions. Receiver operating characteristic (ROC) curves for a Z-score discriminating patients with AD from control subjects were analyzed in areas with significant decreases of rCBF identified in the first group. For visual inspection, 6 physicians graded the rCBF decrease on SPECT images for ROC curves. They inspected the images twice at an interval of >2 wk, and intra- and interobserver reliabilities were determined. Results: Visual inspection showed fair-to-excel lent intra- and interobserver reliabilities. The 3D-SSP demonstrated an accuracy of 86.2% for discriminating patients with AD from control subjects when analyzing the posterior cingulate gyri and precunei with global mean normalization. In contrast, visual inspection did not show an accuracy of >74.0% for this discrimination. Conclusion: The ability of 3D-SSP to discriminate patients with very early AD from control subjects is superior to that of visual inspection. It is clinically useful and reliable to adopt the use of 3D-SSP as an adjunct to visual interpretation.