Statistical brain mapping of 18F-FDG PET in Alzheimer's disease: validation of anatomic standardization for atrophied brains

Abstract

Despite the increased use of statistical mapping to detect brain functional changes in Alzheimer's disease (AD), potential artifacts introduced by stereotactic anatomic standardization of atrophied brains have not been examined carefully. We investigated the effects of anatomic standardization by Statistical Parametric Mapping (SPM) and NEUROSTAT.

Methods: First, 10 AD patients and 10 age-matched healthy volunteers underwent 18F-FDG brain PET imaging. Each image set was standardized to a stereotactic brain template using SPM or NEUROSTAT, followed by pixel normalization to the global or cerebellar activity. Within-group comparisons of standardized image sets by each method and a between-group comparison of healthy volunteers and AD patients were performed using the statistical analysis routines of SPM. Second, simulated PET image sets were generated from segmented MR image sets of 5 healthy volunteers and 5 AD patients. Using the anatomic standardization parameters estimated on the simulated image sets, original gray matter MR image sets were transformed to the stereotactic coordinate system. Between-group subtraction analyses of the transformed gray matter image sets between healthy volunteers and AD groups were performed to examine the accuracy of cortical gray matter matching.

Results: Between-group comparison by SPM or NEUROSTAT showed generally similar areas of hypometabolism in bilateral temporoparietal, posterior cingulate, and left frontal cortices. Both methods showed possible deformation artifacts in the anterior part of the corpus callosum. The localization of the peak hypometabolism varied considerably between the two methods when global normalization was applied. The use of a common brain template for standardization resulted in asymmetric differences in cortical margins, indicating systematic differences in the deformation algorithms. The realistic simulation study revealed gray matter mismatches to be 20% greater with SPM than with NEUROSTAT.

Conclusion: Although different statistical mapping methods may yield grossly similar patterns of hypometabolism in AD, the extent, severity, and peak location of metabolic changes can be inconsistent. Deformation accuracy appears to be more prone to atrophy. These limitations need to be considered carefully in the application and interpretation of brain mapping analysis in atrophied brains.