Comparison between PET template-based method and MRI-based method for cortical quantification of florbetapir (AV-45) uptake in vivo

Abstract

Purpose: Florbetapir (AV-45) has been shown to be a reliable tool for assessing in vivo amyloid load in patients with Alzheimer's disease from the early stages. However, nonspecific white matter binding has been reported in healthy subjects as well as in patients with Alzheimer's disease. To avoid this issue, cortical quantification might increase the reliability of AV-45 PET analyses. In this study, we compared two quantification methods for AV-45 binding, a classical method relying on PET template registration (route 1), and a MRI-based method (route 2) for cortical quantification.

Methods: We recruited 22 patients at the prodromal stage of Alzheimer's disease and 17 matched controls. AV-45 binding was assessed using both methods, and target-to-cerebellum mean global standard uptake values (SUVr) were obtained for each of them, together with SUVr in specific regions of interest. Quantification using the two routes was compared between the clinical groups (intragroup comparison), and between groups for each route (intergroup comparison). Discriminant analysis was performed.

Results: In the intragroup comparison, differences in uptake values were observed between route 1 and route 2 in both groups. In the intergroup comparison, AV-45 uptake was higher in patients than controls in all regions of interest using both methods, but the effect size of this difference was larger using route 2. In the discriminant analysis, route 2 showed a higher specificity (94.1 % versus 70.6 %), despite a lower sensitivity (77.3 % versus 86.4 %), and D-prime values were higher for route 2.

Conclusion: These findings suggest that, although both quantification methods enabled patients at early stages of Alzheimer's disease to be well discriminated from controls, PET template-based quantification seems adequate for clinical use, while the MRI-based cortical quantification method led to greater intergroup differences and may be more suitable for use in current clinical research.

Fig. 1

AV-45 quantification procedures: a cortical PET template-based (route 1) and b cortical MRI-based (route 2). a In route 1, AV-45 acquisitions were linearly registered onto a template from Avid (http://www.avidrp.com/), and regional uptake was quantified for each subject in the MNI space using the AAL atlas [24] that was masked with a grey matter probability map. Uptake values were collected using Matlab. b In route 2, for each subject, the CT scan acquired together with the AV-45 image was registered onto the MRI anatomical space defined by the T1 image of the subject concerned (1). The transformation matrix obtained was then applied to the AV-45 image of the subject so that the AV-45 image was in the T1 space (2). A binarized grey matter mask obtained from MRI segmentation was applied to the transformed AV-45 image (3). The AAL atlas was also registered onto each individual T1 space using the inverse of the transformation matrix from the T1 registration onto MNI space (4). Regional cortical uptake was collected for each subject using Matlab (5). Arrows represent transformation (Subj subject)

Fig. 2

Target-to-cerebellum cortical AV-45 uptake ratios using a route 1 (the PET template-based method) and b route 2 (the MRI-based method). Mean values in all ROIs are shown with associated standard deviations (red diamonds patients, green circles control subjects) *p < .05, **p < .01, ***p < .001. Cohen’s d values for each region are given in red characters

Fig. 3

Receiver operating characteristics curves for route 1 and route 2 (a orange curve route 1, green curve route 2). b–d D-prime values and the corresponding values of the bias measure C for three different SUVr values: b cut-off value for same sensitivity/specificity for route 1 and route 2, c cut-off value for best sensitivity/specificity for route 1, d cut-off value for best sensitivity/specificity for route 2