Search

Background: [18F]FDG PET denoising by SubtlePET™ using deep learning artificial intelligence (AI) was previously found to induce slight modifications in lesion and reference organs' quantification and in lesion detection. As a next step, we aimed to evaluate its clinical impact on [18F]FDG PET solid tumour treatment response assessments, while comparing "standard PET" to "AI denoised half-duration PET" ("AI PET") during follow-up. Results: 110 patients referred for baseline and follow-up standard digital [18F]FDG PET/CT were prospectively included. "Standard" EORTC and, if applicable, PERCIST response classifications by 2 readers between baseline standard PET1 and follow-up standard PET2 as a "gold standard" were compared to "mixed" classifications between standard PET1 and AI PET2 (group 1; n = 64), or between AI PET1 and standard PET2 (group 2; n = 46). Separate classifications were established using either standardized uptake values from ultra-high definition PET with or without AI denoising (simplified to "UHD") or EANM research limited v2 (EARL2)-compliant values (by Gaussian filtering in standard PET and using the same filter in AI PET). Overall, pooling both study groups, in 11/110 (10%) patients at least one EORTCUHD or EARL2 or PERCISTUHD or EARL2 mixed vs. standard classification was discordant, with 369/397 (93%) concordant classifications, unweighted Cohen's kappa = 0.86 (95% CI: 0.78–0.94). These modified mixed vs. standard classifications could have impacted management in 2% of patients. Conclusions: Although comparing similar PET images is preferable for therapy response assessment, the comparison between a standard [18F]FDG PET and an AI denoised half-duration PET is feasible and seems clinically satisfactory. [ABSTRACT FROM AUTHOR]

Background: [ 18 F]FDG PET denoising by SubtlePET™ using deep learning artificial intelligence (AI) was previously found to induce slight modifications in lesion and reference organs' quantification and in lesion detection. As a next step, we aimed to evaluate its clinical impact on [ 18 F]FDG PET solid tumour treatment response assessments, while comparing "standard PET" to "AI denoised half-duration PET" ("AI PET") during follow-up., Results: 110 patients referred for baseline and follow-up standard digital [ 18 F]FDG PET/CT were prospectively included. "Standard" EORTC and, if applicable, PERCIST response classifications by 2 readers between baseline standard PET1 and follow-up standard PET2 as a "gold standard" were compared to "mixed" classifications between standard PET1 and AI PET2 (group 1; n = 64), or between AI PET1 and standard PET2 (group 2; n = 46). Separate classifications were established using either standardized uptake values from ultra-high definition PET with or without AI denoising (simplified to "UHD") or EANM research limited v2 (EARL2)-compliant values (by Gaussian filtering in standard PET and using the same filter in AI PET). Overall, pooling both study groups, in 11/110 (10%) patients at least one EORTC UHD or EARL2 or PERCIST UHD or EARL2 mixed vs. standard classification was discordant, with 369/397 (93%) concordant classifications, unweighted Cohen's kappa = 0.86 (95% CI: 0.78-0.94). These modified mixed vs. standard classifications could have impacted management in 2% of patients., Conclusions: Although comparing similar PET images is preferable for therapy response assessment, the comparison between a standard [ 18 F]FDG PET and an AI denoised half-duration PET is feasible and seems clinically satisfactory., (© 2024. The Author(s).)

Importance: Whether F18-choline (FCH) positron emission tomographic (PET)/computed tomographic (CT) scan can replace Tc99m-sestaMIBI (MIBI) single-photon emission (SPE)CT/CT as a first-line imaging technique for preoperative localization of parathyroid adenomas (PTA) in patients with primary hyperparathyroidism (PHPT) is unclear., Objective: To compare first-line FCH PET/CT vs MIBI SPECT/CT for optimal care in patients with PHPT needing parathyroidectomy and to compare the proportions of patients in whom the first-line imaging method resulted in successful minimally invasive parathyroidectomy (MIP) and normalization of calcemia 1 month after surgery., Design, Setting, and Participants: A French multicenter randomized open diagnostic intervention phase 3 trial was conducted. Patients were enrolled from November 2019 to May 2022 and participated up to 6 months after surgery. The study included adults with PHPT and an indication for surgical treatment. Patients with previous parathyroid surgery or multiple endocrine neoplasia type 1 (MEN1) were ineligible., Interventions: Patients were assigned in a 1:1 ratio to receive first-line FCH PET/CT (FCH1) or MIBI SPECT/CT (MIBI1). In the event of negative or inconclusive first-line imaging, they received second-line FCH PET/CT (FCH2) after MIBI1 or MIBI SPECT/CT (MIBI2) after FCH1. All patients underwent surgery under general anesthesia within 12 weeks following the last imaging. Clinical and biologic (serum calcemia and parathyroid hormone levels) assessments were performed 1 and 6 months after surgery., Main Outcomes and Measures: The primary outcome was a true-positive first-line imaging-guided MIP combined with uncorrected serum calcium levels of 2.55 mmol/l or less 1 month after surgery, corresponding to the local upper limit of normality., Results: Overall, 57 patients received FCH1 (n = 29) or MIBI1 (n = 28). The mean (SD) age of patients was 62.8 (12.5) years with 15 male (26%) and 42 female (74%) patients. Baseline patient characteristics were similar between groups. Normocalcemia at 1 month after positive first-line imaging-guided MIP was observed in 23 of 27 patients (85%) in the FCH1 group and 14 of 25 patients (56%) in the MIBI1 group. Sensitivity was 82% (95% CI, 62%-93%) and 63% (95% CI, 42%-80%) for FCH1 and MIBI1, respectively. Follow-up at 6 months with biochemical measures was available in 43 patients, confirming that all patients with normocalcemia at 1 month after surgery still had it at 6 months. No adverse events related to imaging and 4 adverse events related to surgery were reported., Conclusions: This randomized clinical trial found that first-line FCH PET/CT is a suitable and safe replacement for MIBI SPECT/CT. FCH PET/CT leads more patients with PHPT to correct imaging-guided MIP and normocalcemia than MIBI SPECT/CT thanks to its superior sensitivity., Trial Registration: ClinicalTrials.gov Identifier: NCT04040946.

Background: Exploring the value of baseline and early 18 F-FDG PET/CT evaluations in prediction PFS in ER+/HER2- metastatic breast cancer patients treated with a cyclin-dependent kinase inhibitor in combination with an endocrine therapy., Methods: Sixty-six consecutive breast cancer patients who underwent a pre-therapeutic 18 F-FDG PET/CT and a second PET/CT within the first 6 months of treatment were retrospectively included. Metabolic tumour volume (MTV) and total lesion glycolysis (TLG) and D max , which represents tumour dissemination and is defined as the distance between the two most distant lesions, were computed. The variation in these parameters between baseline and early evaluation PET as well as therapeutic evaluation using PERCIST were assessed as prognosticators of PFS at 18 months., Results: The median follow-up was equal to 22.5 months. Thirty progressions occurred (45.4%). The average time to event was 17.8 ± 10.4 months. At baseline, D max was the only predictive metabolic parameter. Patients with a baseline D max ≤ 18.10 cm had a significantly better 18 m-PFS survival than the others: 69.2% (7.7%) versus 36.7% (8.8%), p = 0.017. There was no association between PERCIST evaluation and 18 m-PFS status (p = 0.149) and there was no difference in 18 m-PFS status between patients classified as complete, partial metabolic responders or having stable metabolic disease., Conclusion: Disease spread at baseline PET, as assessed by D max , is predictive of an event occurring within 18 months. In the absence of early metabolic progression, which occurs in 15% of patients, treatment should be continued regardless of the quality of the initial response to treatment., (© 2024. The Author(s).)