A multicentre comparison of quantitative 90Y PET/CT for dosimetric purposes after radioembolization with resin microspheres

Purpose To investigate and compare the quantitative accuracy of Y-90 imaging across different generation PET/CT scanners, for the purpose of dosimetry after radioembolization with resin microspheres. Methods A strict experimental and imaging protocol was followed by 47 international sites using the NEMA 2007/IEC 2008 PET body phantom with an 8-to-1 sphere-to-background ratio of Y-90 solution. The phantom was imaged over a 7-day period (activity ranging from 0.5 to 3.0 GBq) and all reconstructed data were analysed at a core laboratory for consistent processing. Quantitative accuracy was assessed through measures of total phantom activity, activity concentration in background and hot spheres, misplaced counts in a nonradioactive insert, and background variability. Results Of the 69 scanners assessed, 37 had both time-of-flight (ToF) and resolution recovery (RR) capability. These current generation scanners from GE, Philips and Siemens could reconstruct background concentration measures to within 10 % of true values over the evaluated range, with greater deviations on the Philips systems at low count rates, and demonstrated typical partial volume effects on hot sphere recovery, which dominated spheres of diameter < 20 mm. For spheres > 20 mm in diameter, activity concentrations were consistently underestimated by about 20 %. Non-ToF scanners from GE Healthcare and Siemens were capable of producing accurate measures, but with inferior quantitative recovery compared with ToF systems. Conclusion Current generation ToF scanners can consistently reconstruct Y-90 activity concentrations, but they underestimate activity concentrations in small structures (a parts per thousand currency sign37 mm diameter) within a warm background due to partial volume effects and constraints of the reconstruction algorithm. At the highest count rates investigated, measures of background concentration (about 300 kBq/ml) could be estimated on average to within 1 %, 5 % and 2 % for GE Healthcare (all-pass filter, RR + ToF), Philips (4i8s ToF) and Siemens (2i21s all-pass filter, RR + ToF) ToF systems, respectively. Over the range of activities investigated, comparable performance between GE Healthcare and Siemens ToF systems suggests suitability for quantitative analysis in a scenario analogous to that of postradioembolization imaging for treatment of liver cancer.