Thurfjell L, Lundqvist R, Lilja J, Vandenberghe R.
A software application for automated analysis of [18F] flutemetamol amyloid imaging data.
Human Amyloid Imaging 2011 Meeting Abstracts. 2011 Jan 15;
Background: Although visual read can be readily used to categorize amyloid imaging scans into raised or
normal uptake levels, image quantification can help in equivocal cases and will also be necessary for longitudinal
comparisons. For use in routine clinical practice, a fully automated quantification method will be beneficial to aid
in image analysis and reporting.
Methods: The application for quantification of [18F]flutemetamol data takes the patientfs PET and MR scan as
input and the following processing steps are applied: 1) the MR is co-registered to the PET; 2) the PET is spatially
normalized to MNI space and the transformation is applied to the co-registered MR; 3) counts in a reference
region (cerebellum or pons) are extracted and an SUVR image is computed; 4) a VOI atlas is applied and SUVR
values within cortical regions defined by the atlas are computed; 5) cortical surface projections are computed; and
6) the results are compared to a normals database and z-scores are computed. Result views include VOI SUVR
values and z-scores, voxel-based z-scores projected on the subjectfs MR as well as SUVR and z-score surface
projections. The MR is optional and if not available, an MR template (ICBM-152) is used for display purposes.
27 patients with early-stage AD, 20 with MCI and 25 healthy volunteers (HV) from the [18F]flutemetamol Phase II
study was used to evaluate the application. The HV data was used to build a normals database. All scans were
analyzed and were categorized into raised or normal levels of amyloid based on the z-score value of a composite
cortical VOI using a threshold of 2.0. The results were compared to a blinded visual read using five trained readers.
Results: The categorization of scans made by the automated application showed concordance with the visual
read results in all the AD and HV scans and in 19 of 20 MCI scans. The results were identical for both reference
Conclusion: [18F]flutemetamol scans can be reliably categorized using a fully automated software intended for