Purpose To evaluate hyperpolarized (HP) gamma-glutamyl-[1-13C]glycine ([13C]GG) MRI as a non-invasive method for assessing liver injury through imaging of hepatic enzymatic activity.Procedures In this prospective preclinical imaging study, five mice underwent HP 13C MRI at baseline and 48 h after induction of acute liver injury with carbon tetrachloride (CCl4). Dynamic slice-selective HP 13C spectra through the liver were acquired at 3 T. Signals from [13C]GG and its cleavage product [1-13C]glycine (catalyzed by gamma-glutamyl-transferase or GGT) were quantified. Glycine-to-GG area-under-the-curve (AUC) ratios were calculated. Paired comparisons were analyzed using a two-tailed t-test. Liver histopathology was analyzed after imaging.Results At baseline, HP [13C]GG demonstrated detectable in vivo hepatic conversion to [1-13C]glycine. Following CCl4-induced injury, glycine production decreased in all animals despite similar substrate delivery. On average, the glycine-to-GG ratio declined by 25% (p = 0.024). Histology confirmed centrilobular necrosis, steatosis, inflammation, and hepatocyte injury, with relative preservation of periportal structures. Ex vivo GGT activity measurements (normalized to tissue mass) were directionally consistent with the imaging findings.Conclusion HP [13C]GG MRI detects alterations in hepatic extracellular enzymatic activity following acute injury. The observed reduction in product formation likely reflects changes in functional accessibility of enzyme activity due to tissue injury, highlighting the potential of HP MRI for non-invasive assessment of liver function.
Amyloid-beta (Aβ) plaques in Alzheimer's disease (AD) are commonly imaged with specific PET radiotracers. To overcome the cost and availability limitations of PET, developing a more accessible diagnostic tool is essential. This study aimed to develop a deep-learning model that can synthesize Aβ-PET images from widely available MRI scans. The study utilized 431 subjects with both structural MRI and Aβ-PET scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, including 213 cognitively normal (CN), 180 mild cognitive impairment (MCI), and 38 AD dementia cases. A specialized Vector Quantized Generative Adversarial Network (VQGAN) framework has been trained to generate Aβ-PET images from MRI features, utilizing datasets from patients across various stages of AD spectrum. A paired t-test was used to compare synthetic and real Aβ-PET scans, while an ANOVA was performed to evaluate standardized uptake value ratio differences among the CN, MCI, and AD dementia groups. The synthesized Aβ-PET images closely resemble real Aβ-PET scans in terms of regional Aβ distribution, accurately capturing disease-stage characteristics across the AD spectrum. In three key cortical brain regions (frontal cortex, lateral temporal lobe, and posterior cingulate cortex and precuneus), the synthetic images have successfully replicated disease-related Aβ trends, showing statistically significant group differences (p < 0.05). Quantitative evaluation has confirmed the superiority of VQGAN over other models (lower MAE, higher PSNR/SSIM), demonstrating minimized errors, reduced noise, and better structural fidelity in synthesized images. This technology potentially offers a cost-effective, non-invasive alternative method for AD diagnosis and staging.
Artificial intelligence (AI) is transforming cancer management and theranostics by improving the accuracy, efficiency, and personalization of diagnostic and therapeutic workflows. Routine and accurate clinical implementation of theranostics remains limited by complex dosimetry procedures, demanding imaging protocols, and challenges in quantitative image analysis. This review critically evaluates the role of AI throughout the cancer theranostic workflow, with a focus on its potential to address the key clinical and technical challenges that continue to limit the routine implementation of personalized radiopharmaceutical therapy. It examines the current maturity of AI applications, their readiness for clinical translation, and the future prospects. Recent advances in machine learning and deep learning have enabled automated image interpretation, enhanced quantitative imaging, accelerated acquisition protocols, single-time-point dosimetry, and supported radiomics and multi-omics analyses. Emerging concepts, such as theranostic digital twins, physics- and biology-informed neural networks, and explainable AI are also discussed as future directions for precision medicine. Despite substantial progress, challenges related to data quality, interpretability, ethics, privacy, standardization, and clinical validation continue to hinder widespread clinical adoption. Nevertheless, AI-driven technologies are expected to play a central role in advancing personalized radiopharmaceutical therapy and facilitating routine dosimetry-guided treatment in clinical practice.
This study aimed to evaluate the association of atherosclerosis [68Ga]Ga-FAPI-04 uptake with calcified plaque burden, cardiovascular risk factors (CVRFs), and to compare these findings with [18F]FDG PET/CT. A retrospective analysis was performed on 69 patients (referred for non-cardiovascular indications) who underwent both [68Ga]Ga-FAPI-04 and [18F]FDG PET/CT between August 2020 and November 2023. Tracer uptake was quantified using target-to-background ratio (TBR). The wilcoxon signed-rank test was used to compare two tracers’ uptake, while partial correlation and generalized linear model adjusted for age and sex were applied to assess associations with calcified plaque (CP) and CVRFs. FAPI-TBR was significantly higher than that of [18F]FDG in patient-based analyses, in PET-positive arterial wall regions on both modalities, and in the subgroup with concomitant calcification (all P < 0.001). The number of FAPI-positive lesions exhibited significant positive correlations with CP burden and the number of CVRFs; mean TBR‑FAPI was also positively associated with CVRF count (r = 0.250 0.257, all P < 0.05). Subgroup analyses revealed that high-risk patients (CVRFs ≥ 4) had significantly higher TBR-FAPI than low-risk patients [median (IQR): 1.77 (0.32) vs. 1.54 (0.31); P = 0.047], whereas no such difference was observed for [18F]FDG uptake. Furthermore, TBR-FAPI was significantly elevated in overweight patients compared to normal-weight patients (P < 0.001). [⁶⁸Ga]Ga-FAPI-04 PET provides complementary information to [1⁸F]FDG by reflecting fibrotic remodeling, and may aid in refining cardiovascular risk stratification; however, prospective studies are warranted to establish its clinical utility.
Tumor heterogeneity in breast cancer complicates accurate molecular characterization when using standard-of-care imaging modalities. In this study, gallium-68 labeled estradiol-derivatives were synthesized and evaluated as candidate tracers to be used for multiplexed PET imaging with the goal of improving the molecular characterization of breast cancer. 17β-estradiol was conjugated to DOTA and NODAGA macrocycles and radiolabeled with gallium-68. The selectivity of the resulting radiotracers, [68 Ga]Ga-DOTA-estradiol and [68 Ga]Ga-NODAGA-estradiol, were assessed in vitro using recombinant human estrogen receptor (ER) protein and cell lines. In vivo PET/CT imaging was performed in mice bearing ER-positive and ER-negative tumors using [⁶⁸Ga]Ga-NODAGA-estradiol. Both radiotracers were obtained with high radiochemical purity. Neither [68 Ga]Ga-DOTA-estradiol nor [68 Ga]Ga-NODAGA-estradiol displayed selective binding to the recombinant human ER and no uptake difference could be identified between ER-positive and ER-negative cells. Competition blocking studies using non-radioactive [NatGa]Ga-DOTA-estradiol and [NatGa]Ga-NODAGA-estradiol significantly decreased the uptake of [18F]FES within ER-positive cells. In vivo imaging of [68 Ga]Ga-NODAGA-estradiol revealed negligible tumor uptake and predominant hepatobiliary clearance. Two estradiol-derived radiotracers were successfully synthesized and tested, however neither showed selective binding towards ER in vitro or in vivo. The conjugation site of the cyclic macrocycle on 17β-estradiol is likely a key parameter to retain strong binding towards ER. These findings identify an important limitation for chelator-based ER tracer design.
