Ordered subset expectation maximisation vs Bayesian penalised likelihood reconstruction algorithm in 18F-PSMA-1007 PET/CT

Abstract

Background: The aim of the study was to compare widely used ordered subset expectation maximisation (OSEM) algorithm with a new Bayesian penalised likelihood (BPL) Q.Clear algorithm in 18F-PSMA-1007 PET/CT. Methods: We retrospectively assessed 25 18F-PSMA-1007 PET/CT scans with both OSEM and Q.Clear reconstructions available. Each scan was independently reported by two physicians both in OSEM and Q.Clear. SUVmax, SUVmean and tumour-to-background ratio (TBR) of each lesion were measured. Reports were also compared for their final conclusions and the number and localisation of lesions. Results: In both reconstructions the same 87 lesions were reported. Mean SUVmax, SUVmean and TBR were higher for Q.Clear than OSEM (7.01 vs 6.53 [p = 0.052], 4.16 vs 3.84 [p = 0.036] and 20.2 vs 16.8 [p < 0.00001], respectively). Small lesions (< 10 mm) had statistically significant higher SUVmax, SUVmean and TBR in Q.Clear than OSEM (5.37 vs 4.79 [p = 0.032], 3.08 vs 2.70 [p = 0.04] and 15.5 vs 12.5 [p = 0.00214], respectively). For lesions ≥ 10 mm, no significant differences were observed. Findings with higher tracer avidity (SUVmax ≥ 5) tended to have higher SUVmax, SUVmean and TBR values in Q.Clear (11.6 vs 10.3 [p = 0.00278], 7.0 vs 6.7 [p = 0.077] and 33.9 vs 26.7 [p < 0.00001, respectively). Mean background uptake did not differ significantly between Q.Clear and OSEM (0.42 vs 0.39, p = 0.07). Conclusions: In 18F-PSMA-1007 PET/CT, Q.Clear SUVs and TBR tend to be higher (regardless of lesion localisation), especially for small and highly avid lesions. Increase in SUVs is also higher for lesions with high tracer uptake. Still, Q.Clear does not affect 18F-PSMA-1007 PET/CT specificity and sensitivity.