Accuracy and longitudinal consistency of PET/MR attenuation correction in amyloid PET imaging amid software and hardware upgrades.

BACKGROUND AND PURPOSE Integrated PET/MR allows the simultaneous acquisition of PET biomarkers and structural and functional MRI to study Alzheimer disease (AD). Attenuation correction (AC), crucial for PET quantification, can be performed using a deep learning approach, DL-Dixon, based on standard Dixon images. Longitudinal amyloid PET imaging, which provides important information about disease progression or treatment responses in AD, is usually acquired over several years. Hardware and software upgrades often occur during a multiple-year study period, resulting in data variability. This study aims to harmonize PET/MR DL-Dixon AC amid software and head coil updates and evaluate its accuracy and longitudinal consistency. MATERIALS AND METHODS Tri-modality PET/MR and CT images were obtained from 329 participants, with a subset of 38 undergoing tri-modality scans twice within approximately three years. Transfer learning was employed to fine-tune DL-Dixon models on images from two scanner software versions (VB20P and VE11P) and two head coils (16-channel and 32-channel coils). The accuracy and longitudinal consistency of the DL-Dixon AC were evaluated. Power analyses were performed to estimate the sample size needed to detect various levels of longitudinal changes in the PET standardized uptake value ratio (SUVR). RESULTS The DL-Dixon method demonstrated high accuracy across all data, irrespective of scanner software versions and head coils. More than 95.6% of brain voxels showed less than 10% PET relative absolute error in all participants. The median [interquartile range] PET mean relative absolute error was 1.10% [0.93%, 1.26%], 1.24% [1.03%, 1.54%], 0.99% [0.86%, 1.13%] in the cortical summary region, and 1.04% [0.83%, 1.36%], 1.08% [0.84%, 1.34%], 1.05% [0.72%, 1.32%] in cerebellum using the DL-Dixon models for the VB20P-16-channel-coil, VE11P-16-channel-coil and VE11P-32-channel-coil data, respectively. The within-subject coefficient of variation and intra-class correlation coefficient of PET SUVR in the cortical regions were comparable between the DL-Dixon and CT AC. Power analysis indicated that similar numbers of participants would be needed to detect the same level of PET changes using DL-Dixon and CT AC. CONCLUSIONS DL-Dixon exhibited excellent accuracy and longitudinal consistency across the two software versions and head coils, demonstrating its robustness for longitudinal PET/MR neuroimaging studies in AD. ABBREVIATIONS AC = attenuation correction; AD = Alzheimer disease; HU = Hounsfield unit; ICC = intraclass correlation coefficient; MAE = mean absolute error; MRAE = mean relative absolute error; pCT = pseudo-CT; PiB = Pittsburgh Compound B; SD = standard deviation; SUVR = standardized uptake value ratio; wCV = within-subject coefficient of variation.