Evaluation of zero-echo-time attenuation correction for integrated PET/MR brain imaging—comparison to head atlas and (68)Ge-transmission-based attenuation correction

BACKGROUND: MRI does not offer a direct method to obtain attenuation correction maps as its predecessors (stand-alone PET and PET/CT), and bone visualisation is particularly challenging. Recently, zero-echo-time (ZTE) was suggested for MR-based attenuation correction (AC). The aim of this work was to evaluate ZTE- and atlas-AC by comparison to (68)Ge-transmission scan-based AC. Nine patients underwent brain PET/MR and stand-alone PET scanning using the dopamine transporter ligand (11)C-PE2I. For each of them, two AC maps were obtained from the MR images: an atlas-based, obtained from T1-weighted LAVA-FLEX imaging with cortical bone inserted using a CT-based atlas, and an AC map generated from proton-density-weighted ZTE images. Stand-alone PET (68)Ge-transmission AC map was used as gold standard. PET images were reconstructed using the three AC methods and standardised uptake value (SUV) values for the striatal, limbic and cortical regions, as well as the cerebellum (VOIs) were compared. SUV ratio (SUVR) values normalised for the cerebellum were also assessed. Bias, precision and agreement were calculated; statistical significance was evaluated using Wilcoxon matched-pairs signed-rank test. RESULTS: Both ZTE- and atlas-AC showed a similar bias of 6–8% in SUV values across the regions. Correlation coefficients with (68)Ge-AC were consistently high for ZTE-AC (r 0.99 for all regions), whereas they were lower for atlas-AC, varying from 0.99 in the striatum to 0.88 in the posterior cortical regions. SUVR showed an overall bias of 2.9 and 0.5% for atlas-AC and ZTE-AC, respectively. Correlations with (68)Ge-AC were higher for ZTE-AC, varying from 0.99 in the striatum to 0.96 in the limbic regions, compared to atlas-AC (0.99 striatum to 0.77 posterior cortex). CONCLUSIONS: Absolute SUV values showed less variability for ZTE-AC than for atlas-AC when compared to (68)Ge-AC, but bias was similar for both methods. This bias is largely caused by higher linear attenuation coefficients in atlas- and ZTE-AC image compared to (68)Ge-images. For SUVR, bias was lower when using ZTE-AC than for atlas-AC. ZTE-AC shows to be a more robust technique than atlas-AC in terms of both intra- and inter-patient variability. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (10.1186/s40658-018-0220-0) contains supplementary material, which is available to authorized users.