Abstract Background Limited amino acid availability for Positron Emission Tomography (PET) imaging hinders therapeutic decision-making for gliomas without typical high-grade imaging features. To address this gap, we evaluated a generative artificial intelligence (AI) approach for creating synthetic [18F]FET-PET and predicting high [18F]FET-uptake from magnetic resonance imaging (MRI). Methods We trained a deep learning (DL)-based model to segment tumors in MRI and extracted radiomic features using the pyradiomics package and classification with a Random Forest classifier. To generate [18F]FET-PET images, we employed a Generative Adversarial Network (GAN) framework and utilized a split-input fusion module for processing different MRI sequences through feature extraction, concatenation, and self-attention. Results We included MR and PET images from 215 studies for the hotspot classification and 211 studies for the synthetic PET generation task. The top-performing radiomic features achieved 80% accuracy for hotspot prediction. From the synthetic [18F]FET-PET, 85% were classified as clinically useful by senior physicians. Peak Signal-to-Noise Ratio analysis indicated high signal fidelity with a peak at 40 dB, while Structural Similarity Index values showed structural congruence. Root Mean Square Error analysis demonstrated lower values below 5.6. Most Visual Information Fidelity scores ranged between 0.6 and 0.7. This indicates that synthetic PET images retain the essential information required for clinical assessment and diagnosis. Conclusion For the first time, we demonstrate that predicting high [18F]FET-uptake and generating synthetic PET images from preoperative MRI in LGG and HGG is feasible. Advanced MRI modalities and other generative AI models will be used to improve the algorithm further in future studies.

In neuroendocrine tumors molecular imaging methods play a key role, either targeting the somatostatin receptor or catecholamine pathways. [18F]SiTATE is a somatostatin receptor-targeting peptide that uses silicon fluoride acceptor (SiFA) radiochemistry, overcoming disadvantages of Gallium-68 labelled DOTA compounds. Here we present the first prospective data of [18F]SiTATE compared to [18F]DOPA-PET in NET patients. 38 patients with suspected neuroendocrine tumors were prospectively included. All patients underwent both [18F]DOPA-PET and [18F]SiTATE-PET. The diagnostic performances were compared on a per-patient and per-lesion basis. 22 of 38 patients did not show [18F]DOPA- or [18F]SiTATE-PET positive disease. [18F]DOPA-PET was rated as the more accurate imaging modality in three cases and [18F]SiTATE-PET in four cases. [18F]SiTATE-PET showed a significantly higher sensitivity on a per lesion basis compared to [18F]DOPA-PET (n = 143; sensitivity [18F]SiTATE: 86.7

Aim Prostate-specific membrane antigen-positron emission tomography (PSMA-PET) is a widely used diagnostic tool in patients with prostate cancer (PC). However, due to the limited availability of PET scanners and relevant acquisition costs, it is important to consider the indications and acquisition time. The aim of this investigation was to determine whether a PET scan from the skull base to the proximal thigh is sufficient to detect the presence of bone metastases. Methods A retrospective analysis was conducted on 1050 consecutive [18F]PSMA-1007-PET-CT scans from the head to the proximal lower leg. The PET scans were categorised according to the presence and amount of bone metastases: (1) 1–5, (2) 6–19 and (3) ≥20. Additionally, the PET scans were evaluated for the presence of bone metastases below the proximal thigh as well as bone metastases above the skull base. Imaging results were compared to patients PSA values. Results Of the 391 patients with bone metastases, 146 (37.3%) exhibited metastases located below the proximal thigh and 104 (26.6%) above the skull base. The majority of bone metastases located below the proximal thigh (145, 99.3%) and above the skull base (94, 90.4%) were identified in patients with more than five bone metastases. No solitary distal metastasis was detected. The PSA value correlated significantly with number of bone metastases (e. g., 1–5 vs. ≥20 bone metastases, P < 0.001) and was significantly higher in patients with distal bone metastases (P < 0.001). ROC analysis showed that a PSA value of 11.15 ng/mL is the optimal cut-off for detecting bone metastases located below the proximal thigh, with an AUC of 0.919 (95% CI: 0.892–0.945, sensitivity 87%, specificity 86%). Similarly, the PSA value of 12.86 ng/mL is the optimal cut-off for detecting bone metastases above the skull base with an AUC of 0.904 (95% CI: 0.874–0.935, sensitivity 87%, specificity 83%). Conclusion PSMA-PET acquisition protocols from the skull base to the proximal femur may be sufficient to accurately detect bone metastatic disease in PC. PSA values can provide decision support for individual PET acquisition protocols.

[1F]tetrafluoroborate ([BF]TFB) is an energing PET tracer with excel- lent properties for human sodium iodidel symporter (NIS)-based imag- ing in patients with differentiated thyroid cancer (DTC). The aim of this study was to compare ['FITFB PET with high-activity posttherapeutic [131 [jiodine whole-body scintigraphy and SPECT/CT in recurrent DTC and with 18F]FDG PET/CT in suspected dedifferentiation. Methods: Twenty-six patients treated with high-activity radioactive [131 Ijiodine therapy (ange, 5.00-10.23 GBq) between May 2020 and November 2022 were retrospectively included. Thyroid-stimulating hormone was stimulate by 2 injections of recombinant thyroid-stimulating hormone (0.9mg) 18 and 24h before therapy. Before treatment, all patients underwent [18FITFB PET/CT 40 min after injection of a median of 321 MBq of [1F]TFB. To study tracer kinetics in DTC lesions, 23 patients received an additional scan at 90 min. [131 Ijiodine therapeutic whole-body scintigraphy and SPECT/C were performed at a median of 3.8 d after treatment. Twenty-five patients underwent additional [1F]FDG PET. Two experienced nuclear medicine physicians evalu- ated all imaging modalities in consensus. Results: A total of 62 sus- pected lesions were identified; of thes, 30 lesions were [131 Jiodine positive, 32 lesions were [(1)oFITFB positive, and 52 were [BF]FDG pos- itive. Three of the 30 [1311jiodine-positive lesions were retrospectively rated as false-positive iodide uptake, Tumor-to-background ratio measurerhents at the 40- and 90-min time points were closely corre- lated (e.gil, for the tumor-to-background ratio for muscle, the Pearson correlation coefficient was 0.91; P<0.001; n = 49). We found a signif- icant negative correlation between [F]TFB uptake and [F]FDG uptake as a potential marker for dedifferentiation (Pearson correlation coefficient, -0.26; P 0.041; n 62). Conclusion: Pretherapeutic [1FJTFB PET/CT may help to predict the positivity of recurrent DTC lesions on [131fliodine scans. Therefore, It may help in the selection of patients for Iliodine therapy. Future prospective trials for iodine therapy guidance are warranted. Lesion [F]TFB uptake seems to be inversely correlated with [F]FDG uptake and therefore might serve as a dedifferentiation marker in DTC.

Objectives: An accurate prognostic assessment is pivotal to adequately inform and individualize follow-up and management of patients with differentiated thyroid cancer (DTC). We aimed to develop a predictive model for recurrent disease in DTC patients treated by surgery and 131I by adopting a decision tree model. Methods: Age, sex, histology, T stage, N stage, risk classes, remnant estimation, thyroid-stimulating hormone (TSH), thyroglobulin (Tg), administered 131I activities and post-therapy whole body scintigraphy (PT-WBS) were identified as potential predictors and put into regression algorithm (conditional inference tree, c-tree) to develop a risk stratification model for predicting persistent/recurrent disease over time. Results: The PT-WBS pattern identified a partition of the population into two subgroups (PT-WBS positive or negative for distant metastases). Patients with distant metastases exhibited lower disease-free survival (either structural, DFS-SD, and biochemical, DFS-BD, disease) compared to those without metastases. Meanwhile, the latter were further stratified into three risk subgroups based on their Tg values. Notably, Tg values >63.1 ng/mL predicted a shorter survival time, with increased DFS-SD for Tg values <63.1 and <8.9 ng/mL, respectively. A comparable model was generated for biochemical disease (BD), albeit different DFS were predicted by slightly different Tg cutoff values (41.2 and 8.8 ng/mL) compared to DFS-SD. Conclusions: We developed a simple, accurate and reproducible decision tree model able to provide reliable information on the probability of structurally and/or biochemically persistent/relapsed DTC after a TTA. In turn, the provided information is highly relevant to refine the initial risk stratification, identify patients at higher risk of reduced structural and biochemical DFS, and modulate additional therapies and the relative follow-up.

Abstract BACKGROUND Lack of availability of amino acid Positron Emission Tomography (PET) in many regions limits comprehensive therapeutic decision-making for patients with gliomas without typical high-grade imaging features. To address this gap, we evaluated a novel generative artificial intelligence (AI) approach for creating synthetic [18F]FET-PET and predicting high [18F]FET-uptake from multimodal magnetic resonance imaging (MRI). MATERIAL AND METHODS Our approach involves training a deep learning (DL)-based model to segment tumors in preoperative MRI and extracting radiomic features using the pyradiomics package and classification with a Random Forest classifier. To generate [18F]FET-PET images, we employed a Generative Adversarial Network (GAN) framework and utilized a split-input fusion module for processing different MRI modalities through feature extraction, concatenation, and self-attention. We employed four principal metrics for quality assessment: Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Root Mean Square Error (RMSE), and Visual Information Fidelity (VIF). RESULTS We included MRI and PET images from 215 studies for the hotspot classification task and 211 studies for the synthetic PET generation task. The top-performing radiomic features achieved 80% accuracy for hotspot prediction. Of all the [18F]FET-PET scans generated synthetically, 90% were classified as clinically useful by senior physicians. PSNR analysis indicated high signal fidelity with a peak at 40 dB, while SSIM values showed substantial structural congruence. RMSE analysis demonstrated lower values below 5.6, indicating a robust congruence of the synthetic PET. Complementing these findings, VIF scores mostly ranged between 0.6 to 0.7, reflecting a high level of visual information fidelity and affirming that the synthetic PET images retain the critical informational content required for clinical assessment and diagnosis. CONCLUSION For the first time, we demonstrate that predicting high [18F]FET-uptake and generating synthetic PET images out of multimodal MRI in LGG and HGG is feasible. Furthermore, we can predict higher [18F]FET-uptake with high accuracy. Advanced MRI modalities and other generative AI models will be used to improve the algorithm further in future studies.

Ziel/Aim Die Aminosäure-PET mit [18F]-Fluorethylthyrosin (FET) wird aktuell vor allem bei höhergradigen Gliomen zur Prognoseeinschätzung als auch Differentialdiagnostik der Therapie-assoziierten Veränderungen eingesetzt. Bei den niedrig-gradigen Gliomen kann die FET-PET für die Identifizierung metabolisch aktiver Tumoranteile hilfreich sein und damit die chirurgische Strategie bestimmen. Diese Studie beleuchtet den prognostischen Wert der [18F]FET-PET für Therapie-naive Patienten mit niedrig-gradigen Gliomen.

Zielsetzung Evaluation des Nutzens eines Radiomics-gestützten Modells zur Vorhersage des Therapieansprechens und Überlebens von Patienten mit kolorektalen Lebermetastasen, die mittels transarterieller Radioembolisation (TARE) behandelt wurden.

Ziel/Aim Die Vorhersage des progressions-freien Überlebens (PFS) mittels Radiomics-Merkmalen (radiomic features, RF) aus dem initialen Staging des F-18-FDG-PET/CTs bei Patienten mit fortgeschrittenem nicht-kleinzelligen Bronchialkarzinom (NSCLC) unter Erstlinientherapie mit dem Checkpoint-Inhibitor Pembrolizumab.

Zielsetzung Die PET-Atembewegungskorrektur verbessert die subjektive Bildqualität und quantitative PET-Messwerte. Es ist jedoch nur unzureichend bekannt, ob dies auch zu einem veränderten TNM-Staging führt. Unsere Studie untersucht den Einfluss der PET-Bewegungskorrektur auf das Lymphknoten-Staging bei Lungenkrebspatienten.

Ziel/Aim Nach chirurgischer Zytoreduktion und Radiochemotherapie gibt es aktuell keine zugelassene Erhaltungstherapie für das Glioblastom. Die intracavitär verabreichte Radioimmuntherapie (RIT) mit Lu-177-markierten 6A10-Antikörperfragmenten, gerichtet gegen Gliom-assoziierte Carboanhydrase 12 stellt eine vielversprechende Strategie dar, die residuale infiltrativ wachsende Tumorlast zu adressieren. Wir berichten über erste klinische Erfahrungen.

Ziel/Aim Die Graft-versus-Host-Erkrankung (GvHD) ist eine häufige Komplikation nach allogener Stammzelltransplantation (alloSCT), assoziiert mit signifikant erhöhter Morbidität und Mortalität. Bisherige Studien konzentrieren sich auf die Beurteilung der intestinalen GvHD mit morphologischer (MRT/CT) oder molekularer Bildgebung (18F-FDG-PET) allein. Ziel dieser retrospektiven Studie war es, den diagnostischen Wert eines kontrastmittelgestützten 18F-FDG-PET-MRT-Protokolls bei Patienten mit akuter intestinaler GvHD zu untersuchen.

Ziel/Aim In the management of breast cancer novel imaging strategies are warranted to further improve the staging in individual patients. The fibroblast activating protein (FAP) is abundantly expressed in breast cancer stroma. The aim of this study was to evaluate the potential of FAP-directed breast PET-MRI and whole-body PET using the FAP ligand 68Ga-FAPi-46 (FAPi) for staging of local disease progression and metastases.

The fibroblast activation protein (FAP) is an emerging target for molecular imaging and therapy in cancer. OncoFAP is a novel small organic ligand for FAP with very high affinity. In this translational study, we establish [68Ga]Ga-OncoFAP-DOTAGA (68Ga-OncoFAP) radiolabeling, benchmark its properties in preclinical imaging, and evaluate its application in clinical PET scanning. 68Ga-OncoFAP was synthesized in a cassette-based fully automated labeling module. Lipophilicity, affinity, and serum stability of 68Ga-OncoFAP were assessed by determining logD7.4, IC50 values, and radiochemical purity. 68Ga-OncoFAP tumor uptake and imaging properties were assessed in preclinical dynamic PET/MRI in murine subcutaneous tumor models. Finally, biodistribution and uptake in a variety of tumor types were analyzed in 12 patients based on individual clinical indications that received 163 ± 50 MBq 68Ga-OncoFAP combined with PET/CT and PET/MRI. 68Ga-OncoFAP radiosynthesis was accomplished with high radiochemical yields. Affinity for FAP, lipophilicity, and stability of 68Ga-OncoFAP measured are ideally suited for PET imaging. PET and gamma counting–based biodistribution demonstrated beneficial tracer kinetics and high uptake in murine FAP-expressing tumor models with high tumor-to-blood ratios of 8.6 ± 5.1 at 1 h and 38.1 ± 33.1 at 3 h p.i. Clinical 68Ga-OncoFAP-PET/CT and PET/MRI demonstrated favorable biodistribution and kinetics with high and reliable uptake in primary cancers (SUVmax 12.3 ± 2.3), lymph nodes (SUVmax 9.7 ± 8.3), and distant metastases (SUVmax up to 20.0). Favorable radiochemical properties, rapid clearance from organs and soft tissues, and intense tumor uptake validate 68Ga-OncoFAP as a powerful alternative to currently available FAP tracers.

Background: Integrated PET/MRI is a promising modality for breast assessment. The most frequently used tracer, fluorine 18 (F-18) fluorodeoxyglucose (FDG), is applied for whole-body staging in advanced breast cancer but has limited accuracy in evaluating primary breast lesions. The fibroblast-activation protein (FAP) is abundantly expressed in invasive breast cancer. FAP-directed PET tracers have recently become available, but results in primary breast tumors remain lacking. Purpose: To evaluate the use of FAP inhibitor (FAPI) breast PET/MRI in assessing breast lesions and of FAPI whole-body scanning for lymph node (LN) and distant staging using the ligand gallium 68 (Ga-68)-FAPI-46. Materials and Methods: In women with histologically confirmed invasive breast cancer, all primary Ga-68-FAPI-46 breast and whole-body PET/MRI and PET/CT examinations conducted at the authors' center between October 2019 and December 2020 were retrospectively analyzed. MRI lesion characteristics and standardized uptake values (SUVs) were quantified with dedicated software. Mann-Whitney U tests were used to compare tumor SUVs across different tumor types. The Pearson correlation coefficient was calculated between SUV and measures of MRI morphologic characteristics. Results: Nineteen women (mean age, 49 years 6 9 [standard deviation]) were evaluated-18 to complement initial staging and one for restaging after therapy for distant metastases. Strong tracer accumulation was observed in all 18 untreated primary breast malignancies (mean maximum SUV [SUVmax] = 13.9 [range, 7.9-29.9]; median lesion diameter = 26 mm [range, 9-155 mm]), resulting in clear tumor delineation across different gradings, receptors, and histologic types. All preoperatively verified LN metastases in 13 women showed strong tracer accumulation (mean SUVmax = 12.2 [range, 3.3-22.4]; mean diameter = 21 mm [range, 14-35 mm]). Tracer uptake established or supported extra-axillary LN involvement in seven women and affected therapy decisions in three women. Conclusion: This retrospective analysis indicates use of Ga-68 fibroblast-activation protein inhibitor tracers for breast cancer diagnosis and staging. (C) RSNA, 2021