PurposeDifferentiating brain metastasis recurrence from radiation necrosis can be challenging during MRI follow-up after stereotactic radiotherapy. [18F]-FDG is the most available PET tracer, but standard images performed 30 to 60 minutes postinjection provide insufficient accuracy. We compared the diagnostic performance and interobserver agreement of [18F]-FDG PET with delayed images (4–5 hours postinjection) with the ones provided by standard and dual-time-point imaging.MethodsConsecutive patients referred for brain [18F]-FDG PET after inconclusive MRI were retrospectively included between 2015 and 2020 in 3 centers. Two independent nuclear medicine physicians interpreted standard (visually), delayed (visually), and dual-time-point (semiquantitatively) images, respectively. Adjudication was applied in case of discrepancy. The final diagnosis was confirmed histologically or after 6 months of MRI follow-up. Areas under the receiver operating characteristic curves were pairwise compared.ResultsForty-eight lesions from 46 patients were analyzed. Primary tumors were mostly located in the lungs (57%) and breast (23%). The median delay between radiotherapy and PET was 15.7 months. The final diagnosis was tumor recurrence in 24 of 48 lesions (50%), with histological confirmation in 19 of 48 lesions (40%). Delayed images provided a larger area under the receiver operating characteristic curve (0.88; 95% confidence interval [CI], 0.75–0.95) than both standard (0.69; 95% CI, 0.54–0.81; P = 0.0014) and dual-time-point imaging (0.77; 95% CI, 0.63–0.88; P = 0.045), respectively. Interobserver agreement was almost perfect with delayed images (κ = 0.83), whereas it was moderate with both standard (κ = 0.48) and dual-time-point images (κ = 0.61).Conclusions[18F]-FDG PET with delayed images is an accurate and reliable alternative to differentiate metastasis recurrence from radiation necrosis in case of inconclusive MRI after brain stereotactic radiotherapy.