Refine
Has Fulltext
- yes (24)
Is part of the Bibliography
- yes (24)
Document Type
- Journal article (24) (remove)
Language
- English (24)
Keywords
- Positronen-Emissions-Tomografie (15)
- PET (11)
- positron emission tomography (8)
- neuroendocrine tumor (5)
- 18F-FDG (3)
- PET/CT (3)
- PRRT (3)
- SPECT (3)
- SSTR (3)
- theranostics (3)
- 123I-mIBG (2)
- 123I-metaiodobenzylguanidine (2)
- 18F-FDS (2)
- 18F-LMI1195 (2)
- Prostate Cancer (2)
- RADS (2)
- medullary thyroid carcinoma (2)
- myocardial sympathetic innervation imaging (2)
- peptide receptor radionuclide therapy (2)
- personalized medicine (2)
- personalized treatment (2)
- precision medicine (2)
- somatostatin receptor (2)
- tyrosine kinase inhibitor (2)
- vandetanib (2)
- 11C-HED (1)
- 11C-Hydroxyephedrine (1)
- 11C-hydroxyephedrine (1)
- 123I-Ioflupane (1)
- 18F-DCFPL (1)
- 18F-DCFPyL (1)
- 18F-flurpiridaz (1)
- 18FFBnTP (1)
- 2- deoxy-2-(18F)fluoro-D-glucose (1)
- 2-deoxy-2-(18F)fluoro-D-glucose (1)
- 2-deoxy-2-18F-fluoro-D-sorbitol (1)
- 68Ga-DOTATATE/-TOC (1)
- 99mTc-DTPA (1)
- AI (1)
- Antidepressants (1)
- CXCR4 (1)
- DCGAN (1)
- DOTATOC (1)
- DaTscan (1)
- ECG (1)
- FV45 (1)
- GAN (1)
- GI (1)
- Ganglia (1)
- Gastrointestinal (1)
- Glomerular filtration (1)
- HFmrEF (1)
- ICD (1)
- Imaging pitfalls (1)
- MDD (1)
- MPI (1)
- MRI (1)
- Magnetresonanztomografie (1)
- Medullärer Schilddrüsenkrebs (1)
- Myokarditis (1)
- Neuroendocrine (1)
- Neuroendocrine Tumor (1)
- Nierenfunktionsstörung (1)
- Oncology (1)
- PSMA (1)
- PSMA-PET (1)
- Parkinsonism (1)
- Parkinson’s disease (1)
- Pitfall (1)
- Positron Emission Tomography (1)
- Positron-Emission Tomography (1)
- Positronenemissionstomografie (1)
- Prostata (1)
- Radionuclide Therapy (1)
- Radiotracer (1)
- SPECT/CT (1)
- SSTR-PET (1)
- Single-Photon-Emissions-Computertomographie (1)
- Stammzelle (1)
- Standardisierung (1)
- TKI (1)
- Tracer (1)
- Virchow Node (1)
- ZDF rats (1)
- [177Lu]-DOTATATE/-DOTATOC (1)
- [68Ga] (1)
- [68Ga]DOTATOC (1)
- [\(^{68}\)Ga]Pentixafor (1)
- \(^{18}\)F-FDG (1)
- \(^{18}\)F-fluorodeoxyglucose (1)
- ageing (1)
- angiotensin II type 1 receptor (1)
- antidepressant (1)
- arrhythmia (1)
- artificial intelligence (1)
- cardiac innervation imaging (1)
- cardiac nerve (1)
- cardiac sympathetic nerve system (1)
- cardiac sympathetic nervous system (1)
- cardiomyocytes (1)
- chemokine receptor (1)
- coronary artery disease (1)
- depression (1)
- diabetes (1)
- diabetic cardiomyopathy (1)
- fatty acid (1)
- heart failure (1)
- heart failure with mid-range ejection fraction (1)
- hiPSC-CM (1)
- induced pluripotent stem cells (1)
- inflammation (1)
- kidney (1)
- machine learning (1)
- magnetic resonance imaging (1)
- major depressive disorder (1)
- myocardial nerve (1)
- myocardial perfusion imaging (1)
- myocarditis (1)
- pancreas (1)
- phaeochromocytoma (1)
- prostate cancer (1)
- prostate-specific membrane antigen (PSMA) (1)
- quantification (1)
- renal failure (1)
- renal imaging (1)
- renin-angiotensin system (1)
- reporting and data systems (1)
- single photon emission computed tomography: sympathetic nerve (1)
- somatostatin receptor (SSTR) (1)
- split renal function (1)
- standardization (1)
- stem cell therapy (1)
- storage vesicle turnover (1)
- stroke (1)
- sympathetic nervous system (1)
- tracer (1)
- tumor heterogeneity (1)
- unilateral ureteral obstruction (1)
- valsartan (1)
Institute
- Klinik und Poliklinik für Nuklearmedizin (24) (remove)
Sonstige beteiligte Institutionen
- Johns Hopkins School of Medicine (11)
- Johns Hopkins University School of Medicine (4)
- Department of Biomedical Imaging, National Cerebral and Cardiovascular Research Center, Suita, Japan (1)
- Department of Nuclear Medicine, Kanazawa University (1)
- Division of Medical Technology and Science, Department of Medical Physics and Engineering, Course of Health Science, Osaka University Graduate School of Medicine, Suita Japan (1)
- Institut for Molecular Biology and CMBI, Department of Genomics, Stem Cell Biology and Regenerative Medicine, Leopold-Franzens-University Innsbruck, Innsbruck, Austria (1)
- Johns Hopkins Medicine (1)
- Johns Hopkins School of Medicine, Baltimore, MD, USA (1)
- Johns Hopkins School of Medicine, The Russell H Morgan Department of Radiology and Radiological Science, Baltimore, MD, USA (1)
- Johns Hopkins University, Baltimore, MD, U.S. (1)
EU-Project number / Contract (GA) number
- 701983 (24) (remove)
Even as medical data sets become more publicly accessible, most are restricted to specific medical conditions. Thus, data collection for machine learning approaches remains challenging, and synthetic data augmentation, such as generative adversarial networks (GAN), may overcome this hurdle. In the present quality control study, deep convolutional GAN (DCGAN)-based human brain magnetic resonance (MR) images were validated by blinded radiologists. In total, 96 T1-weighted brain images from 30 healthy individuals and 33 patients with cerebrovascular accident were included. A training data set was generated from the T1-weighted images and DCGAN was applied to generate additional artificial brain images. The likelihood that images were DCGAN-created versus acquired was evaluated by 5 radiologists (2 neuroradiologists [NRs], vs 3 non-neuroradiologists [NNRs]) in a binary fashion to identify real vs created images. Images were selected randomly from the data set (variation of created images, 40%-60%). None of the investigated images was rated as unknown. Of the created images, the NRs rated 45% and 71% as real magnetic resonance imaging images (NNRs, 24%, 40%, and 44%). In contradistinction, 44% and 70% of the real images were rated as generated images by NRs (NNRs, 10%, 17%, and 27%). The accuracy for the NRs was 0.55 and 0.30 (NNRs, 0.83, 0.72, and 0.64). DCGAN-created brain MR images are similar enough to acquired MR images so as to be indistinguishable in some cases. Such an artificial intelligence algorithm may contribute to synthetic data augmentation for "data-hungry" technologies, such as supervised machine learning approaches, in various clinical applications.
Background: Precise regional quantitative assessment of renal function is limited with conventional \(^{99m}\)Tc-labeled renal radiotracers. A recent study reported that the positron emission tomography (PET) radiotracer 2-deoxy-2-(\(^{18}\)F-fluorosorbitol (\(^{18}\)F-FDS) has ideal pharmacokinetics for functional renal imaging. Furthermore, (\(^{18}\)F-FDS is available via simple reduction from routinely used 2-deoxy-2-(\(^{18}\)F-fluoro-D-glucose ((\(^{18}\)F-FDG). We aimed to further investigate the potential of (\(^{18}\)F-FDS PET as a functional renal imaging agent using rat models of kidney diseases.
Methods: Two different rat models of renal impairment were investigated: Glycerol induced acute renal failure (ARF) by intramuscular administration of glycerol in hind legs and unilateral ureteral obstruction (UUO) by ligation of the left ureter. 24h after these treatments, dynamic 30 min 18F-FDS PET data were acquired using a dedicated small animal PET system. Urine 18F-FDS radioactivity 30 min after radiotracer injection was measured together with co-injected \(^{99m}\)Tc-diethylenetriaminepentaacetic acid (\(^{99m}\)Tc-DTPA) urine activity. Results: Dynamic PET imaging demonstrated rapid (\(^{18}\)F-FDS accumulation in the renal cortex and rapid radiotracer excretion via kidneys in control healthy rats. On the other hand, significantly delayed renal radiotracer uptake (continuous slow uptake) was observed in ARF rats and UUO-treated kidneys. Measured urine radiotracer concentrations of (\(^{18}\)F-FDS and \(^{99m}\)Tc-DTPA were well correlated (R=0.84, P<0.05).
Conclusions: (\(^{18}\)F-FDS PET demonstrated favorable kinetics for functional renal imaging in rat models of kidney diseases. Advantages of high spatiotemporal resolution of PET imaging and simple tracer production could potentially complement or replace conventional renal scintigraphy in select cases and significantly improve the diagnostic performance of renal functional imaging.
As a scintigraphic approach evaluating cardiac nerve integrity, \(^{123}\)I-metaiodobenzylguanidine (123I-mIBG) has been recently Food and Drug Administration approved. A great deal of progress has been made by the prospective ADMIRE-HF trial, which primarily demonstrated the association of denervated myocardium assessed by \(^{123}\)I-mIBG and cardiac events. However, apart from risk stratification, myocardial nerve function evaluated by molecular imaging should also be expanded to other clinical contexts, in particular to guide the referring cardiologist in selecting appropriate candidates for specific therapeutic interventions. In the present issue of the Journal of Nuclear Cardiology, the use of 123I-mIBG for identifying cardiomyopathy patients, which would most likely not benefit from ICD due low risk of arrhythmias, is described. If we aim to deliver on the promise of cardiac innervation imaging as a powerful tool for risk stratification in a manner similar to nuclear oncology, studies such as the one reviewed here may imply an important step to lay the proper groundwork for a more widespread adoption in clinical practice.