ABSTRACT
BACKGROUND: 68 Ga-PSMA PET is the leading prostate cancer imaging technique, but the image quality remains noisy and could be further improved using an artificial intelligence-based denoising algorithm. To address this issue, we analyzed the overall quality of reprocessed images compared to standard reconstructions. We also analyzed the diagnostic performances of the different sequences and the impact of the algorithm on lesion intensity and background measures. METHODS: We retrospectively included 30 patients with biochemical recurrence of prostate cancer who had undergone 68 Ga-PSMA-11 PET-CT. We simulated images produced using only a quarter, half, three-quarters, or all of the acquired data material reprocessed using the SubtlePET® denoising algorithm. Three physicians with different levels of experience blindly analyzed every sequence and then used a 5-level Likert scale to assess the series. The binary criterion of lesion detectability was compared between series. We also compared lesion SUV, background uptake, and diagnostic performances of the series (sensitivity, specificity, accuracy). RESULTS: VPFX-derived series were classified differently but better than standard reconstructions (p < 0.001) using half the data. Q.Clear series were not classified differently using half the signal. Some series were noisy but had no significant effect on lesion detectability (p > 0.05). The SubtlePET® algorithm significantly decreased lesion SUV (p < 0.005) and increased liver background (p < 0.005) and had no substantial effect on the diagnostic performance of each reader. CONCLUSION: We show that the SubtlePET® can be used for 68 Ga-PSMA scans using half the signal with similar image quality to Q.Clear series and superior quality to VPFX series. However, it significantly modifies quantitative measurements and should not be used for comparative examinations if standard algorithm is applied during follow-up.
ABSTRACT
PURPOSE: Differentiating brain metastasis recurrence from radiation necrosis can be challenging during MRI follow-up after stereotactic radiotherapy. [ 18 F]-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 [ 18 F]-FDG PET with delayed images (4-5 hours postinjection) with the ones provided by standard and dual-time-point imaging. METHODS: Consecutive patients referred for brain [ 18 F]-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. RESULTS: Forty-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: [ 18 F]-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.
