Reproducibility of automated simplified voxel-based analysis of PET amyloid ligand [11C]PIB uptake using 30-min scanning data

Abstract

Purpose: Positron emission tomography (PET) with 11C-labelled Pittsburgh compound B ([11C]PIB) enables the quantitation of beta-amyloid accumulation in the brain of patients with Alzheimer's disease (AD). Voxel-based image analysis techniques conducted in a standard brain space provide an objective, rapid and fully automated method to analyze [11C]PIB PET data. The purpose of this study was to evaluate both region- and voxel-level reproducibility of automated and simplified [11C]PIB quantitation when using only 30 min of imaging data.

Methods: Six AD patients and four healthy controls were scanned twice with an average interval of 6 weeks. To evaluate the feasibility of short scanning (convenient for AD patients), [11C]PIB uptake was quantitated using 30 min of imaging data (60 to 90 min after tracer injection) for region-to-cerebellum ratio calculations. To evaluate the reproducibility, a test-retest design was used to derive absolute variability (VAR) estimates and intraclass correlation coefficients at both region-of-interest (ROI) and voxel level.

Results: The reproducibility both at the region level (VAR 0.9-5.5%) and at the voxel level (VAR 4.2-6.4%) was good to excellent. Based on the variability estimates obtained, power calculations indicated that 90% power to obtain statistically significant difference can be achieved using a sample size of five subjects per group when a 15% change from baseline (increase or decrease) in [11C]PIB accumulation in the frontal cortex is anticipated in one group compared to no change in another group.

Conclusion: Our results showed that an automated analysis method based on an efficient scanning protocol provides reproducible results for [11C]PIB uptake and appears suitable for PET studies aiming at the quantitation of amyloid accumulation in the brain of AD patients for the evaluation of progression and treatment effects.