Volume of interest-based [18F]fluorodeoxyglucose PET discriminates MCI converting to Alzheimer's disease from healthy controls. A European Alzheimer's Disease Consortium (EADC) study

Abstract

An emerging issue in neuroimaging is to assess the diagnostic reliability of PET and its application in clinical practice. We aimed at assessing the accuracy of brain FDG-PET in discriminating patients with MCI due to Alzheimer's disease and healthy controls. Sixty-two patients with amnestic MCI and 109 healthy subjects recruited in five centers of the European AD Consortium were enrolled. Group analysis was performed by SPM8 to confirm metabolic differences. Discriminant analyses were then carried out using the mean FDG uptake values normalized to the cerebellum computed in 45 anatomical volumes of interest (VOIs) in each hemisphere (90 VOIs) as defined in the Automated Anatomical Labeling (AAL) Atlas and on 12 meta-VOIs, bilaterally, obtained merging VOIs with similar anatomo-functional characteristics. Further, asymmetry indexes were calculated for both datasets. Accuracy of discrimination by a Support Vector Machine and the AAL VOIs was tested against a validated method (PALZ). At the voxel level SMP8 showed a relative hypometabolism in the bilateral precuneus, and posterior cingulate, temporo-parietal and frontal cortices. Discriminant analysis classified subjects with an accuracy ranging between .91 and .83 as a function of data organization. The best values were obtained from a subset of 6 meta-VOIs plus 6 asymmetry values reaching an area under the ROC curve of .947, significantly larger than the one obtained by the PALZ score. High accuracy in discriminating MCI converters from healthy controls was reached by a non-linear classifier based on SVM applied on predefined anatomo-functional regions and inter-hemispheric asymmetries. Data pre-processing was automated and simplified by an in-house created Matlab-based script encouraging its routine clinical use. Further validation toward nonconverter MCI patients with adequately long follow-up is needed.

Keywords: Discriminant analysis; EADC; FDG-PET; MCI; Volume of interest.

Fig. 1

Metabolic differences between healthy controls and MCI patients converting to AD. Tree-dimensional rendering of SPM analysis showing those regions in which ¹⁸F-FDG uptake was significantly lower in MCI-converters(n = 62) than in healthy controls (n = 109) (threshold p < 0.05, corrected for multiple comparisons with the family-wise error (FWE) option). Top row left: medial left view; top row right: medial right view; second row left: posterior view; second row right: frontal view; third row left: right-side view; third row right: left-side view; bottom row left: view from below; and bottom row right: view from above. Talairach coordinates and further details are provided in Supplementary Table e1.

Fig. 2

Receiver Operating Characteristic curves: classifier comparisons. Receiver operating characteristic (ROC) curves obtained by PALZ discrimination tool and by Support Vector Machine classifier as applied to 3 different datasets drawn from the same set of neuroimages: 90R: 90 AAL regions; 24R: 24 anatomo-functional meta-regions; and 6R + 6A: 6 meta-regions and 6 inter-hemispheric asymmetries drawn from step-wise backward selection. The best classification, marked by an asterisk, was obtained by a subset of 6 meta-regions and 6 asymmetry values, yielding 92% sensitivity and 91% specificity. Both 6R + 6A and 90R performed significantly better than PALZ-score (6R + 6A: p < 0.02; 90R: p < 0.05).