Prevalence of interstitial pneumonia suggestive of COVID-19 at 18F-FDG PET/CT in oncological asymptomatic patients in a high prevalence country during pandemic period: a national multi-centric retrospective study.

PURPOSE: To assess the presence and pattern of incidental interstitial lung alterations suspicious of COVID-19 on fluorine-18-fluorodeoxyglucose positron emission tomography (PET)/computed tomography (CT) ([18F]FDG PET/CT) in asymptomatic oncological patients during the period of active COVID-19 in a country with high prevalence of the virus. METHODS: This is a multi-center retrospective observational study involving 59 Italian centers. We retrospectively reviewed the prevalence of interstitial pneumonia detected during the COVID period (between March 16 and 27, 2020) and compared to a pre-COVID period (January-February 2020) and a control time (in 2019). The diagnosis of interstitial pneumonia was done considering lung alterations of CT of PET. RESULTS: Overall, [18F]FDG PET/CT was performed on 4008 patients in the COVID period, 19,267 in the pre-COVID period, and 5513 in the control period. The rate of interstitial pneumonia suspicious for COVID-19 was significantly higher during the COVID period (7.1%) compared with that found in the pre-COVID (5.35%) and control periods (5.15%) (p < 0.001). Instead, no significant difference among pre-COVID and control periods was present. The prevalence of interstitial pneumonia detected at PET/CT was directly associated with geographic virus diffusion, with the higher rate in Northern Italy. Among 284 interstitial pneumonia detected during COVID period, 169 (59%) were FDG-avid (average SUVmax of 4.1). CONCLUSIONS: A significant increase of interstitial pneumonia incidentally detected with [18F]FDG PET/CT has been demonstrated during the COVID-19 pandemic. A majority of interstitial pneumonia were FDG-avid. Our results underlined the importance of paying attention to incidental CT findings of pneumonia detected at PET/CT, and these reports might help to recognize early COVID-19 cases guiding the subsequent management.

Decreased amount of vimentin N-terminal truncated proteolytic products in parkin-mutant skin fibroblasts.

Vimentin, a member of cytoskeleton intermediate filaments proteins, plays a critical role in cell structure and dynamics. The present proteomic study reveals reduced amount of six different lengths, N-terminal truncated proteolytic products of vimentin, in the primary skin fibroblasts from two unrelated PD patients, as compared to control fibroblasts. The decreased amount of N-terminal truncated forms of vimentin in parkin-mutant fibroblasts, could contribute to impairment of cellular function, potentially contributing to the pathogenesis of Parkinson disease.

cAMP regulates the functional activity, coupling efficiency and structural organization of mammalian FOF1 ATP synthase.

The present study shows that in isolated mitochondria and myoblast cultures depletion of cAMP, induced by sAC inhibition, depresses both ATP synthesis and hydrolysis by the FOF1 ATP synthase (complex V) of the oxidative phosphorylation system (OXPHOS). These effects are accompanied by the decrease of the respiratory membrane potential, decreased level of FOF1 connecting subunits and depressed oligomerization of the complex. All these effects of sAC inhibition are prevented by the addition of the membrane-permeant 8-Br-cAMP. These results show, for the first time, that cAMP promotes ATP production by complex V and prevents, at the same time, its detour to a mitochondrial membrane leak conductance, which is involved in cell death.

Function and expression study uncovered hepatocyte plasma membrane ecto-ATP synthase as a novel player in liver regeneration.

ATP synthase, canonically mitochondrially located, is reported to be ectopically expressed on the plasma membrane outer face of several cell types. We analysed, for the first time, the expression and catalytic activities of the ecto- and mitochondrial ATP synthase during liver regeneration. Liver regeneration was induced in rats by two-thirds partial hepatectomy. The protein level and the ATP synthase and/or hydrolase activities of the hepatocyte ecto- and mitochondrial ATP synthase were analysed on freshly isolated hepatocytes and mitochondria from control, sham-operated and partial hepatectomized rats. During the priming phase of liver regeneration, 3 h after partial hepatectomy, liver mitochondria showed a marked lowering of the ATP synthase protein level that was reflected in the impairment of both ATP synthesis and hydrolysis. The ecto-ATP synthase level, in 3 h partial hepatectomized hepatocytes, was decreased similarly to the level of the mitochondrial ATP synthase, associated with a lowering of the ecto-ATP hydrolase activity coupled to proton influx. Noteworthily, the ecto-ATP synthase activity coupled to proton efflux was completely inhibited in 3 h partial hepatectomized hepatocytes, even in the presence of a marked intracellular acidification that would sustain it as in control and sham-operated hepatocytes. At the end of the liver regeneration, 7 days after partial hepatectomy, the level and the catalytic activities of the ecto- and mitochondrial ATP synthase reached the control and sham-operated values. The specific modulation of hepatocyte ecto-ATP synthase catalytic activities during liver regeneration priming phase may modulate the extracellular ADP/ATP levels and/or proton influx/efflux trafficking, making hepatocyte ecto-ATP synthase a candidate for a novel player in the liver regeneration process.

Intramitochondrial adenylyl cyclase controls the turnover of nuclear-encoded subunits and activity of mammalian complex I of the respiratory chain.

In mammalian cells the nuclear-encoded subunits of complex I are imported into mitochondria, where they are assembled with mt-DNA encoded subunits in the complex, or exchanged with pre-existing copies in the complex. The present work shows that in fibroblast cultures inhibition by KH7 of cAMP production in the mitochondrial matrix by soluble adenylyl cyclase (sAC) results in decreased amounts of free non-incorporated nuclear-encoded NDUFS4, NDUFV2 and NDUFA9 subunits of the catalytic moiety and inhibition of the activity of complex I. Addition of permeant 8-Br-cAMP prevents this effect of KH7. KH7 inhibits accumulation in isolated rat-liver mitochondria and incorporation in complex I of "in vitro" produced, radiolabeled NDUFS4 and NDUFV2 subunits. 8-Br-cAMP prevents also this effect of KH7. Use of protease inhibitors shows that intramitochondrial cAMP exerts this positive effect on complex I by preventing digestion of nuclear-encoded subunits by mitochondrial protease(s), whose activity is promoted by KH7 and H89, an inhibitor of PKA.

Altered protein expression pattern in skin fibroblasts from parkin-mutant early-onset Parkinson's disease patients.

Parkinson's disease (PD) is the most common neurodegenerative movement disorder caused primarily by selective degeneration of the dopaminergic neurons in substantia nigra. In this work the proteomes extracted from primary fibroblasts of two unrelated, hereditary cases of PD patients, with different parkin mutations, were compared with the proteomes extracted from commercial adult normal human dermal fibroblasts (NHDF) and primary fibroblasts from the healthy mother of one of the two patients. The results show that the fibroblasts from the two different cases of parkin-mutant patients display analogous alterations in the expression level of proteins involved in different cellular functions, like cytoskeleton structure-dynamics, calcium homeostasis, oxidative stress response, protein and RNA processing.

Ten-year experience in the management of distal ureteral stones greater than 10 mm in size.

AIM: Extracorporeal shock wave lithotripsy (ESWL) and semirigid ureteroscopy lithotripsy (URSL) have become standards of treatment for ureteral calculi. The aim of this retrospective study was to compare ESWL vs. URSL in terms of safety and efficacy for treatment of large distal ureteral stones ≥ 1cm. PATIENTS AND METHODS: This investigation assessed 637 patients with distal ureteral stones (10 to 15mm in size). 313 in the ESWL group were treated on an outpatient basis using the LithoDiamond machine without anaesthesia. URSL was performed in 324 patients with a 6-8 Fr semirigid ureterorenoscope and YAG laser under spinal anaesthesia. A successful outcome was defined as the patient being stone free 1 month after treatment. For all patients the parameters, including stone-free rate, operation time, complications, were inserted retrospectively in this study after review of medical records and operating room logs. RESULTS: The stone-free rate after URSL was 77.5% and 45.4% after ESWL treatment (p<0.001). The mean operative time between two groups was 74.7±9.8 for URSL group and 38.3±7.6 for ESWL group. The average number of office visits was 4.2 and 2.6 in patients treated with ESWL and URSL, respectively. Double j stents were inserted in 28.7% of patients. Twenty-one patients needed rehospitalisations for major complications. However, the differences in the overall complication rate were not statistically significant, with a rate of 16.3% for URSL and 14.4% for ESWL (p=0.246). CONCLUSION: We have shown that URSL has enough safety and efficacy for the treatment of distal ureteral stones ≥ 1cm. URSL is associated with higher stone clearance rate as compared with ESWL.

Regulation of the biogenesis of OXPHOS complexes in cell transition from replicating to quiescent state: involvement of PKA and effect of hydroxytyrosol.

A study is presented on the expression of mitochondrial oxidative phosphorylation complexes in exponentially growing and serum-starved, quiescent human fibroblast cultures. The functional levels of respiratory complexes I and III and complex V (adenosine triphosphate (ATP) synthase) were found to be severely depressed in serum-starved fibroblasts. The depression of oxidative phosphorylation system (OXPHOS) complexes was associated with reduced levels of peroxisome proliferator-activated receptor gamma coactivator 1-alpha (PGC-1α) and the down-stream nuclear respiratory factor 1 (NRF1) and mitochondrial transcription factors (TFAM). In serum-starved fibroblasts decrease of the catalytic activity of AMP cyclic dependent protein kinase (PKA) and phosphorylation of cAMP response element-binding protein (CREB), the transcription coactivator of the PGC-1α gene, was found. Hydroxytyrosol prevented the decline in the expression of the PGC-1α transcription cascade of OXPHOS complexes in serum-starved fibroblast cultures. The positive effect of HT was associated with activation of PKA and CREB phosphorylation. These results show involvement of PKA, CREB and PGC-1α in the regulation of OXPHOS in cell transition from the replicating to the quiescent state.

Epigallocatechin-3-gallate prevents oxidative phosphorylation deficit and promotes mitochondrial biogenesis in human cells from subjects with Down's syndrome.

A critical role for mitochondrial dysfunction has been proposed in the pathogenesis of Down's syndrome (DS), a human multifactorial disorder caused by trisomy of chromosome 21, associated with mental retardation and early neurodegeneration. Previous studies from our group demonstrated in DS cells a decreased capacity of the mitochondrial ATP production system and overproduction of reactive oxygen species (ROS) in mitochondria. In this study we have tested the potential of epigallocatechin-3-gallate (EGCG) - a natural polyphenol component of green tea - to counteract the mitochondrial energy deficit found in DS cells. We found that EGCG, incubated with cultured lymphoblasts and fibroblasts from DS subjects, rescued mitochondrial complex I and ATP synthase catalytic activities, restored oxidative phosphorylation efficiency and counteracted oxidative stress. These effects were associated with EGCG-induced promotion of PKA activity, related to increased cellular levels of cAMP and PKA-dependent phosphorylation of the NDUFS4 subunit of complex I. In addition, EGCG strongly promoted mitochondrial biogenesis in DS cells, as associated with increase in Sirt1-dependent PGC-1α deacetylation, NRF-1 and T-FAM protein levels and mitochondrial DNA content. In conclusion, this study shows that EGCG is a promoting effector of oxidative phosphorylation and mitochondrial biogenesis in DS cells, acting through modulation of the cAMP/PKA- and sirtuin-dependent pathways. EGCG treatment promises thus to be a therapeutic approach to counteract mitochondrial energy deficit and oxidative stress in DS.

The mechanism of alternative splicing of the X-linked NDUFB11 gene of the respiratory chain complex I, impact of rotenone treatment in neuroblastoma cells.

A study is presented on the regulation of alternative splicing (AS) of the Ndufb11 gene of complex I of the mitochondrial respiratory chain and the impact on this process of rotenone treatment in neuroblastoma cells. In physiological conditions the Ndufb11 gene produces at high level a short transcript isoform encoding for a 153 aa protein. This subunit is essential for the assembly of a functional and stable mammalian complex I. The gene produces also, at low level, a longer transcript isoform encoding for a 163 aa protein whose role is unknown. Evidence is presented here showing that the level of the two isoforms is regulated by three DGGGD ESS elements located in exon 2 which can bind the hnRNPH1 protein. In neuronal cells rotenone treatment affects the Ndufb11 alternative splicing pathway, with the increase of the 163/153 mRNAs ratio. This effect appears to be due to the down-regulation of the hnRNPH1 protein. Since rotenone induces apoptosis in neuronal cells, the post-transcriptional regulation of the Ndufb11 gene can be involved in the programmed cell death process.

Short-term type-1 diabetes differentially modulates 14-3-3 proteins in rat brain and liver.

BACKGROUND: The 14-3-3 proteins family consists of seven proteins that are highly conserved molecular chaperones with roles in the regulation of metabolism, signal transduction, cell cycle control, protein trafficking and apoptosis. Their role in several pathologies has been reported. In this study, we investigated the mRNA and protein expression of the 14-3-3s in rat brain and liver in the early stage of Type-1 diabetes (T1D). MATERIAL AND METHODS: Diabetes was induced by a single intraperitoneal injection (70 mg/kg bw) of freshly prepared streptozotocin (STZ), and, after 3 weeks of treatment, brain and liver nuclei and cytosolic extracts were prepared. Quantitative real-time PCR and Western blotting analyses were performed to evaluate mRNA and protein expression for each of the seven 14-3-3s. RESULTS: In nondiabetic control rats, the expression profile of 14-3-3s revealed a tissue-specific distribution, and the expression level of each isoform was found higher in the brain than in the liver. In the diabetic brain, mRNA and protein levels of the 14-3-3ß, ε, ζ, η and θ were lower; 14-3-3σ mRNA significantly increased while its protein level decreased. In the diabetic liver, the mRNA of 14-3-3γ, 14-3-3θ and 14-3-3σ significantly increased, but only the 14-3-3γ protein level increased. Overall, in diabetic animals, the changes in the expression levels of brain 14-3-3s were much more pronounced than in the liver. CONCLUSION: Our results indicate that during the early phase of STZ-induced T1D, the 14-3-3 proteins are affected in an isoform- and tissue-specific way.

Adoption of AI in Oncological Imaging: Ethical, Regulatory, and Medical-Legal Challenges.

Artificial Intelligence (AI) algorithms have shown great promise in oncological imaging, outperforming or matching radiologists in retrospective studies, signifying their potential for advanced screening capabilities. These AI tools offer valuable support to radiologists, assisting them in critical tasks such as prioritizing reporting, early cancer detection, and precise measurements, thereby bolstering clinical decision-making. With the healthcare landscape witnessing a surge in imaging requests and a decline in available radiologists, the integration of AI has become increasingly appealing. By streamlining workflow efficiency and enhancing patient care, AI presents a transformative solution to the challenges faced by oncological imaging practices. Nevertheless, successful AI integration necessitates navigating various ethical, regulatory, and medical-legal challenges. This review endeavors to provide a comprehensive overview of these obstacles, aiming to foster a responsible and effective implementation of AI in oncological imaging.

Radiomics and Artificial Intelligence in Renal Lesion Assessment.

Radiomics, the extraction and analysis of quantitative features from medical images, has emerged as a promising field in radiology with the potential to revolutionize the diagnosis and management of renal lesions. This comprehensive review explores the radiomics workflow, including image acquisition, feature extraction, selection, and classification, and highlights its application in differentiating between benign and malignant renal lesions. The integration of radiomics with artificial intelligence (AI) techniques, such as machine learning and deep learning, can help patients' management and allow the planning of the appropriate treatments. AI models have shown remarkable accuracy in predicting tumor aggressiveness, treatment response, and patient outcomes. This review provides insights into the current state of radiomics and AI in renal lesion assessment and outlines future directions for research in this rapidly evolving field.

Artificial Intelligence in Lung Cancer Imaging: From Data to Therapy.

Lung cancer remains a global health challenge, leading to substantial morbidity and mortality. While prevention and early detection strategies have improved, the need for precise diagnosis, prognosis, and treatment remains crucial. In this comprehensive review article, we explore the role of artificial intelligence (AI) in reshaping the management of lung cancer. AI may have different potential applications in lung cancer characterization and outcome prediction. Manual segmentation is a time-consuming task, with high inter-observer variability, that can be replaced by AI-based approaches, including deep learning models such as U-Net, BCDU-Net, and others, to quantify lung nodules and cancers objectively and to extract radiomics features for the characterization of the tissue. AI models have also demonstrated their ability to predict treatment responses, such as immunotherapy and targeted therapy, by integrating radiomic features with clinical data. Additionally, AI-based prognostic models have been developed to identify patients at higher risk and personalize treatment strategies. In conclusion, this review article provides a comprehensive overview of the current state of AI applications in lung cancer management, spanning from segmentation and virtual biopsy to outcome prediction. The evolving role of AI in improving the precision and effectiveness of lung cancer diagnosis and treatment underscores its potential to significantly impact clinical practice and patient outcomes.

Radiologists' perceptions on AI integration: An in-depth survey study.

PURPOSE: To assess the perceptions and attitudes of radiologists toward the adoption of artificial intelligence (AI) in clinical practice. METHODS: A survey was conducted among members of the SIRM Lombardy. Radiologists' attitudes were assessed comprehensively, covering satisfaction with AI-based tools, propensity for innovation, and optimism for the future. The questionnaire consisted of two sections: the first gathered demographic and professional information using categorical responses, while the second evaluated radiologists' attitudes toward AI through Likert-type responses ranging from 1 to 5 (with 1 representing extremely negative attitudes, 3 indicating a neutral stance, and 5 reflecting extremely positive attitudes). Questionnaire refinement involved an iterative process with expert panels and a pilot phase to enhance consistency and eliminate redundancy. Exploratory data analysis employed descriptive statistics and visual assessment of Likert plots, supported by non-parametric tests for subgroup comparisons for a thorough analysis of specific emerging patterns. RESULTS: The survey yielded 232 valid responses. The findings reveal a generally optimistic outlook on AI adoption, especially among young radiologist (<30) and seasoned professionals (>60, p<0.01). However, while 36.2 % (84 out 232) of subjects reported daily use of AI-based tools, only a third considered their contribution decisive (30 %, 25 out of 84). AI literacy varied, with a notable proportion feeling inadequately informed (36 %, 84 out of 232), particularly among younger radiologists (46 %, p < 0.01). Positive attitudes towards the potential of AI to improve detection, characterization of anomalies and reduce workload (positive answers > 80 %) and were consistent across subgroups. Radiologists' opinions were more skeptical about the role of AI in enhancing decision-making processes, including the choice of further investigation, and in personalized medicine in general. Overall, respondents recognized AI's significant impact on the radiology profession, viewing it as an opportunity (61 %, 141 out of 232) rather than a threat (18 %, 42 out of 232), with a majority expressing belief in AI's relevance to future radiologists' career choices (60 %, 139 out of 232). However, there were some concerns, particularly among breast radiologists (20 of 232 responders), regarding the potential impact of AI on the profession. Eighty-four percent of the respondents consider the final assessment by the radiologist still to be essential. CONCLUSION: Our results indicate an overall positive attitude towards the adoption of AI in radiology, though this is moderated by concerns regarding training and practical efficacy. Addressing AI literacy gaps, especially among younger radiologists, is essential. Furthermore, proactively adapting to technological advancements is crucial to fully leverage AI's potential benefits. Despite the generally positive outlook among radiologists, there remains significant work to be done to enhance the integration and widespread use of AI tools in clinical practice.

Allosteric interactions and proton conducting pathways in proton pumping aa(3) oxidases: heme a as a key coupling element.

In this paper allosteric interactions in protonmotive heme aa(3) terminal oxidases of the respiratory chain are dealt with. The different lines of evidence supporting the key role of H(+)/e(-) coupling (redox Bohr effect) at the low spin heme a in the proton pump of the bovine oxidase are summarized. Results are presented showing that the I-R54M mutation in P. denitrificans aa(3) oxidase, which decreases by more than 200mV the E(m) of heme a, inhibits proton pumping. Mutational amino acid replacement in proton channels, at the negative (N) side of membrane-inserted prokaryotic aa(3) oxidases, as well as Zn(2+) binding at this site in the bovine oxidase, uncouples proton pumping. This effect appears to result from alteration of the structural/functional device, closer to the positive, opposite (P) surface, which separates pumped protons from those consumed in the reduction of O(2) to 2 H(2)O.

Comparative secretome analysis of four isogenic Bacillus clausii probiotic strains.

BACKGROUND: The spore-bearing alkaliphilic Bacillus species constitute a large, heterogeneous group of microorganisms, important for their ability to produce enzymes, antibodies and metabolites of potential medical use. Some Bacillus species are currently being used for manufacturing probiotic products consisting of bacterial spores, exhibiting specific features (colonization, immune-stimulation and antimicrobial activity) that can account for their claimed probiotic properties. In the present work a comparative proteomic study was performed aimed at characterizing the secretome of four closely related isogenic O/C, SIN, N/R and T B. clausii strains, already marketed in a pharmaceutical mixture as probiotics. RESULTS: Proteomic analyses revealed a high degree of concordance among the four secretomes, although some proteins exhibited considerable variations in their expression level in the four strains. Among these, some proteins with documented activity in the interaction with host cells were identified, such as the glycolytic enzyme enolase, with a putative plasminogen-binding activity, GroEL, a molecular chaperone shown to be able to bind to mucin, and flagellin protein, a structural flagella protein and a putative immunomodulation agent. CONCLUSION: This study shows, for the first time, differences in the secretome of the OC, SIN, NR and T B. clausii strains. These differences indicate that specific secretome features characterize each of the four strains despite their genotypic similarity. This could confer to the B. clausii strains specific probiotic functions associated with the differentially expressed proteins and indicate that they can cooperate as probiotics as the secretome components of each strain could contribute to the overall activity of a mixed probiotic preparation.

How do patients perceive the AI-radiologists interaction? Results of a survey on 2119 responders.

PURPOSE: In this study we investigate how patients perceive the interaction between artificial intelligence (AI) and radiologists by designing a survey. METHOD: We created a survey focused on the application of Artificial Intelligence in radiology which consisted of 20 questions distributed in three sections:Only completed questionnaires were considered for analysis. RESULTS: 2119 subjects completed the survey. Among them, 1216 respondents were over 60 years old, showing interest in AI even though they were not digital natives. Although >45% of the respondents reported a high level of education, only 3% said they were AI experts. 87% of respondents favored using AI to support diagnosis but would like to be informed. Only 10% would consult another specialist if their doctor used AI support. Most respondents (76%) said they would not feel comfortable if the diagnosis was made by the AI alone, highlighting the importance of the physician's role in the emotional management of the patient. Finally, 36% of respondents were willing to discuss the topic further in a focus group. CONCLUSION: Patients' perception of the use of AI in radiology was positive, although still strictly linked to the supervision of the radiologist. Respondents showed interest and willingness to learn more about AI in the medical field, confirming how patients' confidence in AI technology and its acceptance is central to its widespread use in clinical practice.

Chest X-ray in Emergency Radiology: What Artificial Intelligence Applications Are Available?

Due to its widespread availability, low cost, feasibility at the patient's bedside and accessibility even in low-resource settings, chest X-ray is one of the most requested examinations in radiology departments. Whilst it provides essential information on thoracic pathology, it can be difficult to interpret and is prone to diagnostic errors, particularly in the emergency setting. The increasing availability of large chest X-ray datasets has allowed the development of reliable Artificial Intelligence (AI) tools to help radiologists in everyday clinical practice. AI integration into the diagnostic workflow would benefit patients, radiologists, and healthcare systems in terms of improved and standardized reporting accuracy, quicker diagnosis, more efficient management, and appropriateness of the therapy. This review article aims to provide an overview of the applications of AI for chest X-rays in the emergency setting, emphasizing the detection and evaluation of pneumothorax, pneumonia, heart failure, and pleural effusion.

Amplifying the Effects of Contrast Agents on Magnetic Resonance Images Using a Deep Learning Method Trained on Synthetic Data.

OBJECTIVES: Artificial intelligence (AI) methods can be applied to enhance contrast in diagnostic images beyond that attainable with the standard doses of contrast agents (CAs) normally used in the clinic, thus potentially increasing diagnostic power and sensitivity. Deep learning-based AI relies on training data sets, which should be sufficiently large and diverse to effectively adjust network parameters, avoid biases, and enable generalization of the outcome. However, large sets of diagnostic images acquired at doses of CA outside the standard-of-care are not commonly available. Here, we propose a method to generate synthetic data sets to train an "AI agent" designed to amplify the effects of CAs in magnetic resonance (MR) images. The method was fine-tuned and validated in a preclinical study in a murine model of brain glioma, and extended to a large, retrospective clinical human data set. MATERIALS AND METHODS: A physical model was applied to simulate different levels of MR contrast from a gadolinium-based CA. The simulated data were used to train a neural network that predicts image contrast at higher doses. A preclinical MR study at multiple CA doses in a rat model of glioma was performed to tune model parameters and to assess fidelity of the virtual contrast images against ground-truth MR and histological data. Two different scanners (3 T and 7 T, respectively) were used to assess the effects of field strength. The approach was then applied to a retrospective clinical study comprising 1990 examinations in patients affected by a variety of brain diseases, including glioma, multiple sclerosis, and metastatic cancer. Images were evaluated in terms of contrast-to-noise ratio and lesion-to-brain ratio, and qualitative scores. RESULTS: In the preclinical study, virtual double-dose images showed high degrees of similarity to experimental double-dose images for both peak signal-to-noise ratio and structural similarity index (29.49 dB and 0.914 dB at 7 T, respectively, and 31.32 dB and 0.942 dB at 3 T) and significant improvement over standard contrast dose (ie, 0.1 mmol Gd/kg) images at both field strengths. In the clinical study, contrast-to-noise ratio and lesion-to-brain ratio increased by an average 155% and 34% in virtual contrast images compared with standard-dose images. Blind scoring of AI-enhanced images by 2 neuroradiologists showed significantly better sensitivity to small brain lesions compared with standard-dose images (4.46/5 vs 3.51/5). CONCLUSIONS: Synthetic data generated by a physical model of contrast enhancement provided effective training for a deep learning model for contrast amplification. Contrast above that attainable at standard doses of gadolinium-based CA can be generated through this approach, with significant advantages in the detection of small low-enhancing brain lesions.