Search Results (243)

Background: Artificial intelligence (AI) and deep learning (DL) are rapidly changing the field of diagnostics and imaging in cardiology, offering tools for automatic segmentation, quantification of changes, and risk stratification. These technologies have the potential to increase diagnostic accuracy, work efficiency, and individualization of patient care. Methods: This structured narrative review critically evaluates clinically validated applications of artificial intelligence (AI) and deep learning (DL) in cardiovascular medicine, focusing on imaging (echocardiography, coronary CT angiography, cardiac MRI, and ECG), risk stratification, and biomarker integration. A systematic literature search was conducted in PubMed for studies published between January 2015 and December 2026, supplemented by references from key articles. Original English-language studies reporting quantitative clinical outcomes were included, with 78 studies ultimately analyzed. Results: AI and DL models, including convolutional neural networks and transformers, achieved performance comparable to experts in cardiac imaging, myocardial perfusion assessment, valve defect detection, and coronary event prediction. Multimodal approaches improved diagnostic accuracy and reproducibility, while explainable AI enhanced transparency and clinical confidence. Deep learning also enabled faster image acquisition and processing without compromising precision. Conclusions: AI and DL have transformative potential in cardiology, offering fast, accurate, and scalable diagnostic tools. The integration of multimodal data, the validation of algorithms in prospective studies, and ensuring the transparency of models are key. Future research should focus on prospective, multicenter validations and the ethical and safe implementation of AI in everyday clinical practice. Full article

Background/Objectives: Breast MRI surveillance for women with a personal history of breast cancer (PHBC) is often limited by costs and acquisition times. This study aims to identify the optimal abbreviated breast MR (ABMR) protocol for this population by assessing the diagnostic performance of different sequence additions. Methods: This retrospective study included 1002 women with PHBC who underwent postoperative breast MRI with ultrafast sequences. Propensity score matching using 12 variables yielded recurrence (n = 21) and nonrecurrence (n = 42) groups with balanced characteristics. Four ABMR protocols were simulated by sequentially combining sequences: Step 1 (FAST protocol) included precontrast T1-weighted imaging (T1WI), early-phase T1WI, and subtracted maximal intensity projection (MIP). Step 2 added ultrafast MIP; Step 3 incorporated delayed-phase T1WI; and Step 4 included T2WI and diffusion weighted imaging (DWI). Three expert breast radiologists independently reviewed MRIs. Sensitivity, specificity, accuracy, and area under the curve (AUC) were assessed. Results: Sensitivity, specificity, and accuracy for ABMR protocols ranged from 76.2% to 90.5%, 88.1% to 92.9%, and 85.7% to 90.5%, respectively. The FAST protocol alone provided reliable performance (sensitivity: 81%; specificity: 88.1–90.5%; accuracy: 85.7–87.3%). Additional sequences yielded modest improvements, but no statistically significant differences were observed across all 3 readers (p > 0.05). ABMR protocols demonstrated equivalent diagnostic performance for PHBC surveillance. Conclusions: The FAST protocol alone provided reliable results, indicating its potential as a primary ABMR protocol. While additional sequences slightly improved specificity, they did not significantly enhance diagnostic accuracy. Full article

Insulin acts in the brain to promote satiety. Aging individuals may have brain insulin resistance and altered appetite perceptions. However, it is unclear if exercise impacts cerebral reward centers and appetite perception in middle-aged to older individuals. Purpose: To assess whether a single exercise bout alters cerebral blood flow (CBF) in reward centers in relation to appetite perceptions. Methods: Fifteen sedentary adults (12F; ~56 ± 2y; ~31 ± 1 kg/m²) completed a control and acute exercise condition (70% maximal oxygen consumption) in a randomized, counterbalanced order in the evening. Following an overnight fast, CBF in the accumbens, thalamus, and amygdala (pCASL MRI) was evaluated before and after intranasal insulin spray (INI, 40 IU) administration. Plasma glucose and insulin as well as an appetite visual analog scale (VAS) were assessed at fasting, 30, and 90 min post-INI, as well as at 30 min intervals of a 120 min 75 g oral glucose tolerance test (OGTT). Total area under the curve (tAUC) was calculated. Results: Exercise tended to lower blood glucose (p = 0.072) and plasma insulin (p = 0.007) tAUC, compared with rest. Exercise also raised right thalamus (p = 0.029) and left amygdala CBF (p = 0.023). The rise in fasting CBF in these regions, and the accumbens, correlated with reduced insulin tAUC (r = −0.55 to −0.73, p < 0.050). Although there was no difference in hunger, satisfaction, fullness, or prospective food consumption after exercise, changes in INI-stimulated thalamus CBF related to fullness tAUC after exercise (r = −0.57, p = 0.044). Conclusions: A single exercise bout might increase fasting CBF in some brain regions associated with appetite perception through a potential insulin-related mechanism. Full article

Background/Objectives: Pediatric thoracic trauma requires prompt stabilization and timely imaging; however, actual sequencing and escalation triggers are infrequently delineated at the pathway level. The aim of this study was to analyze imaging pathways observed in routine clinical practice at our institution and to outline a preliminary escalation framework integrating injury mechanism, clinical severity, and initial ultrasound findings. Methods: A retrospective cohort study was conducted at the “Louis Țurcanu” Clinical Emergency Hospital for Children, Timișoara, Romania, including 66 children admitted with primary thoracic trauma between January 2022 and December 2024. Clinical trajectory markers (transfer-in, ICU admission, length of stay) and imaging utilization/sequencing (FAST, CXR, CT, MRI/CTA) were extracted. We divided injuries into two groups: bony (like fractures of the clavicle or scapula) and non-bony. CT escalation was characterized as a chest CT conducted upon admission. Fisher’s exact and Mann–Whitney U tests were used for comparative analyses. Results: FAST was done on all patients but was infrequently positive. Imaging followed heterogeneous but structured patterns, most commonly FAST with CXR, with or without CT. A large group of them had CT scans without first having any X-rays. CT escalation was associated with fracture-pattern injuries and higher-acuity trajectories (transfer-in and ICU admission), as well as prolonged hospital stays. Pathway-level assessment demonstrated that CT escalation effectively captured bony injury patterns, whereas FAST proficiently sorted ICU-level trajectories. Conclusions: Pediatric thoracic trauma imaging functioned as a selective escalation system: FAST served as a universal bedside entry step, and CT operated as an injury pattern- and acuity-linked severity gate. Making this escalation logic clear may help with standardization while still protecting against radiation. Full article

Background/Objectives: Oxidative stress and iron overload remodel erythrocyte membranes in β-thalassemia, but their systemic metabolic correlates are not well defined. We applied untargeted metabolomics to identify serum biomarkers reflecting these pathophysiological processes. Methods: Thirty-one adults with β-thalassemia [18 transfusion-dependent (TDT), 13 non-transfusion-dependent (NTD)] and 8 age/sex-matched healthy controls were studied. Fasting serum was profiled using untargeted UHPLC–Orbitrap MS. Multivariate modeling (SIMCA-P) and FDR-controlled univariate statistics identified discriminant features, followed by pathway enrichment analysis. Associations with clinical variables (chelation regimen, ferritin, cardiac MRI T2*, and liver iron concentration) were examined. Results: A total of 183 metabolites were detected; versus controls, 124 were decreased, 54 increased, and 5 remained unchanged in patients. Key discriminants included lysophosphatidylcholines (LysoPC 18:1, 18:3), polyunsaturated fatty acid (PUFA)-bearing phosphatidylcholines (PC 20:4/18:0, PC 18:0/20:4), conjugated bile acids (glycocholic acid, glycochenodeoxycholic acid, and glycoursodeoxycholic acid), and bilirubin. Pathway analysis revealed significant enrichment (FDR-corrected) in linoleic acid metabolism (q = 0.024, impact = 1.000) and arachidonic acid metabolism (q = 0.022, impact = 0.433), with supportive nominal signals from glycerophospholipid (impact = 0.401) and porphyrin/heme (impact = 0.242) pathways. No significant metabolic differences were observed between TD and NTD patients. Conclusions: β-thalassemia serum metabolomics reflects oxidative membrane lipid remodeling with a prominent PLA₂/LysoPC–arachidonic axis and evidence of heme turnover and altered bile-acid signaling. These data propose a practical biomarker panel-LysoPCs, arachidonic acid-enriched PCs, and conjugated bile acids-warranting targeted validation alongside conventional clinical parameters for disease monitoring and therapeutic assessment. Full article

Incomplete or faulty MRI sequences are common in clinical practice and can impair AI-based analyses that rely on complete multi-contrast data. The relative effectiveness of classical generative adversarial networks (GANs) versus modern diffusion and transformer-based models for clinically usable MRI synthesis remains unclear. This study evaluates cross-modality MRI synthesis using the BraTS 2019 brain tumour dataset, focusing on T1-to-T2 translation. We assess paired and unpaired CycleGAN models and compare them with two stronger but computationally intensive baselines, a conditional denoising diffusion probabilistic model (DDPM) and a transformer-enhanced GAN, using identical data splits and preprocessing pipelines. Inter-modality correlation was evaluated to estimate the achievable similarity between modalities. Conceptually, modality synthesis may be viewed as a representation-learning approach that compensates for missing imaging information by reconstructing clinically relevant features from available contrasts. Paired CycleGAN achieved correlations of $r\approx 0.92–0.93$ and SSIM $\approx 0.90–0.92$, approaching natural T1–T2 correlation ($r\approx 0.95$) while maintaining very fast inference (<50 ms/slice). Unpaired CycleGAN achieved $r\approx 0.74–0.78$ and SSIM $\approx 0.82–0.85$, producing clinically interpretable reconstructions without voxel-level supervision. DDPM achieved the highest fidelity (SSIM $\approx 0.93–0.95$, $r\approx 0.94$) but required substantially greater computational resources, while transformer-enhanced GAN performance was intermediate. Qualitative analysis showed that CycleGAN and DDPM best preserved tumour and tissue boundaries, whereas unpaired CycleGAN occasionally over-smoothed subtle lesions. These findings highlight the trade-off between fidelity and efficiency in cross-modality MRI synthesis, suggesting paired CycleGAN for time-sensitive clinical workflows and diffusion models as a computationally expensive accuracy upper bound. Full article

Two accelerated magnetic resonance imaging (MRI) protocols for pediatric brain imaging, GOBrain and Deep Resolve Swift Brain, developed by Siemens Healthineers (Erlangen, Germany), were evaluated in a series of clinically relevant pediatric cases at 3 Tesla. Pediatric patients are particularly prone to motion, may be uncooperative, and often require sedation, especially in emergency settings. Consequently, there is a persistent clinical demand for fast brain MRI protocols that provide diagnostically sufficient image quality while minimizing examination time. Contemporary turbo spin-echo (TSE)-based clinical protocols commonly integrate parallel imaging (PI) and simultaneous multi-slice (SMS) techniques to achieve substantial reductions in scan time. Recent advances in three-dimensional volumetric encoding, compressed sensing, and deep learning (DL)-based reconstruction have further mitigated geometry-factor-related noise amplification, enabling higher acceleration factors (GOBrain). In parallel, echo-planar imaging (EPI) has emerged as a promising approach for ultrafast multi-contrast imaging. To overcome the limitations of single-shot EPI, a multi-shot EPI-based brain MRI protocol combined with the DL-based reconstruction method Deep Resolve Swift Brain has been developed. This approach leverages the efficiency of EPI while improving image quality. Using these accelerated protocols, a comprehensive diagnostic multi-contrast brain MRI examination, particularly suited to triage and emergency imaging, can be completed in minutes. This case overview, including therapy-related leukencephalopathy in acute lymphoblastic leukemia (ALL), a brain abscess, traumatic diffuse axonal injury (DAI), a posterior circulation infarction due to vertebral artery dissection, leuokostasis syndrome, and a posterior fossa tumor with obstructive hydrocephalus, demonstrates the potential clinical feasibility of both protocols in pediatric neuroimaging. Both protocols position them as supplementary options alongside established imaging protocols, while dedicated high-resolution protocols might remain necessary for subtle pathological findings, such as focal cortical dysplasia, and for neuronavigation until larger comparative studies are available. Full article

Objective: We present the first clinical experience with the BIOGRAPH One next-generation PET/MRI system scanner, evaluating its performance for body and brain imaging in patients across multiple tracers. Methods: A total of 59 patients were scanned on the BIOGRAPH One PET/MRI following standard clinical PET/CT (n = 52) or first-generation PET/MRI (Biograph mMR, n = 7). Scans comprised 30 total body (TB), whole body (WB), or regional scans with [¹⁸F]FDG, and 29 brain scans with either [¹⁸F]FDG (n = 5), [¹⁸F]FE-PE2I (n = 10), [¹⁸F]FET (n = 4), or [⁶⁸Ga]Ga-DOTATOC (n = 10). The PET image quality was visually assessed using a 5-point Likert scale (1 = very good to 5 = very bad) and compared with clinical scans acquired on either a current-generation digital PET/CT or a first-generation PET/MRI system, including evaluation of diagnostic concordance. PET quantification and image noise was compared in brain and WB/TB [¹⁸F]FDG PET scans. Results: PET image quality was rated as good or very good in 93% of scans with a median [inter-quartile range] score of 1.5 [1.5;2]. In 99% of cases, image quality was judged equal to or better than the clinical reference scan (median score 3 [2.5;3]). Diagnostic concordance was observed in 99% of readings. Imaging metrics revealed the anticipated regional bias in brain imaging, while no significant bias was observed in body imaging. Image noise was comparable to that observed with digital PET/CT and demonstrated superiority over first-generation PET/MRI despite potential degradation related to isotope decay in BIOGRAPH One PET/MRI acquisitions scans performed at the end of the imaging workflow. Conclusions: Within the study limitations related to sequential imaging, the BIOGRAPH One PET/MRI scanner demonstrated improved PET sensitivity and workflow potential over its first-generation predecessor, which may allow for broader clinical and research applications. Full article

Recurrent depressive disorder (RDD) and bipolar disorder (BD) are the most common affective disorders worldwide. However, the pathogenesis of these disorders remains far from understood. Macromolecular proton fraction (MPF) mapping is a sensitive and specific quantitative MRI method for the assessment of brain tissue myelination, but its clinical value for affective disorders remains unknown. This cross-sectional study employed fast MPF mapping on a 1.5 T MRI scanner using the single-point synthetic reference method to investigate myelin abnormalities in white matter of RDD and BD patients. ANOVA revealed a significant main effect of the group (RDD vs. BD vs. two age-matched control groups; F (3.76) = 7.42, p < 0.001, η² = 0.227). MPF values were significantly reduced in RDD versus BD patients (p < 0.001). BD showed elevated MPF compared to controls (p = 0.01). MPF levels showed significant weak-to-moderate correlations with clinical scales of affective disorders. These findings demonstrate divergent cerebral myelination patterns—hypomyelination in RDD versus an increased myelin content in BD. In conclusion, MPF mapping demonstrated a promise as a marker of myelin content changes in affective disorder. Full article

With the increasing prevalence of brain tumors, it becomes crucial to ensure fast and reliable segmentation in MRI scans. Medical professionals struggle with manual tumor segmentation due to its exhausting and time-consuming nature. Automated segmentation speeds up decision-making and diagnosis; however, achieving an optimal balance between accuracy and computational cost remains a significant challenge. In many cases, current methods trade speed for accuracy, or vice versa, consuming substantial computing power and making them difficult to use on devices with limited resources. To address this issue, we present PRA-UNet, a lightweight deep learning model optimized for fast and accurate 2D brain tumor segmentation. Using a single 2D input, the architecture processes four types of MRI scans (FLAIR, T1, T1c, and T2). The encoder uses inverted residual blocks and bottleneck residual blocks to capture features at different scales effectively. The Convolutional Block Attention Module (CBAM) and the Spatial Attention Module (SAM) improve the bridge and skip connections by refining feature maps and making it easier to detect and localize brain tumors. The decoder uses depthwise separable convolutions, which significantly reduce computational costs without degrading accuracy. The BraTS2020 dataset shows that PRA-UNet achieves a Dice score of 95.71%, an accuracy of 99.61%, and a processing speed of 60 ms per image, enabling real-time analysis. PRA-UNet outperforms other models in segmentation while requiring less computing power, suggesting it could be suitable for deployment on lightweight edge devices in clinical settings. Its speed and reliability enable radiologists to diagnose tumors quickly and accurately, enhancing practical medical applications. Full article

Background: Interstitial myocardial fibrosis is a crucial pathological feature of many cardiovascular disorders. Myocardial fibrosis resulting in extracellular volume (ECV) expansion can be quantified via cardiac MRI (CMR) with T₁ mapping before and after minimally invasive gadolinium (Gd) contrast agent administration. However, longitudinal repetitive ECV measurements are challenging in rodents due to the prolonged scan time with cardiac and respiratory gating that is required for conventional T₁ mapping and the invasive nature of the rodent intravenous lines. Methods: To address these challenges, the objective of this study is to establish a fast, free-breathing, and gating-free ECV procedure using a minimally invasive subcutaneous catheter for in-scanner Gd administration that can allow longitudinal repetitive ECV evaluations in rodent models. This is achieved by the (1) IntraGate sequence for free-breathing, gating-free cardiac imaging; (2) minimally invasive subcutaneous in-scanner Gd administration; and (3) fast T₁ mapping with a varied flip angle (VFA) in conjunction with (4) triple jugular vein blood T₁ normalization. Additionally, full cine CMR (multi-slice short-axis, long-axis 2-chamber, and long-axis 4-chamber) was acquired during the waiting period to assess comprehensive cardiac function and strain. Results: We successfully established a minimally invasive fast ECV quantification protocol to enable longitudinal repetitive ECV quantifications in rodents. Minimally invasive subcutaneous Gd bolus administration induced a reasonable dynamic contrast enhancement (DCE) time course, reaching a steady state in ~20 min for stable T₁ quantification. The free-breathing gating-free VFA T₁ quantification scheme allows for rapid cardiac (~2.5 min) and jugular vein (49 s) T₁ quantification with no motion artifacts. The triple jugular vein T₁ acquisitions (1 pre-contrast and 2 post-contrast) immediately flanking the heart T₁ acquisitions enable accurate myocardial ECV quantification. Our data demonstrated that left-ventricular myocardial ECV quantification was highly reproducible with repeated scans, and the ECV values (0.25) are comparable to reported ranges among humans and rodents. This protocol was successfully applied to the ischemia–reperfusion injury model to detect myocardial fibrosis, which was validated by histopathology. Conclusions: We established a simple, fast, minimally invasive, and robust CMR protocol in rodents that can enable longitudinal repetitive ECV quantification for cardiovascular disease progression. It can be used to monitor disease regression with interventions. Full article

Even though primary Sjögren disease (pSjD) is mainly associated with sicca symptoms, there are extraglandular manifestations of the disease which affect the quality of life of patients the most and may even be life-threatening. Among the most severe, polyneuropathy and myopathy are worth mentioning. Additionally, clinical observations suggest a higher prevalence of fibromyalgia (FM) in this group of patients, clouding physicians’ assessment and potentially leading to unsuccessful therapeutic decisions. The aim of our study was to evaluate the frequency of pSjD and FM co-occurrence as well as to find the most effective screening tools and markers of such overlap. A total of 97 consecutive patients with diagnosed pSjD were incorporated in the study after obtaining their informed consent. Participants completed a set of broadly available questionnaires, including Fibromyalgia Survey Questionnaire, SF-36 and EULAR Sjögren’s Syndrome Patient-Reported Index (ESSPRI). Data on their laboratory results was collected in the dedicated database. Moreover, patients underwent electroneurographic (ENG) and electromyographic (EMG) testing. Central nervous system (CNS) abnormalities were detected using MRI. Objective disease activity was evaluated based on EULAR Sjögren’s Syndrome Disease Activity Index (ESSDAI). The mean age was 55.3 (range 19.0–78.0 years, SD = 13.9). The disease duration ranged from 2 to 42 years (M = 9.03 years, SD = 7.1 years). Nearly half of the participants (n = 44, 45%) met diagnostic criteria of FM. Interestingly, the diagnosis of FM correlated with CNS involvement. There was no significant correlation between FM and either polyneuropathy/myopathy nor laboratory findings (however, C3c and folic acid concentrations were near the level of significance—mean 1.2 vs. 1.29; p = 0.075 and mean 11.35 vs. 9.21; p = 0.071, respectively). Within the subcategories of SF-36 and ESSPRI scales, significant positive correlation was noted with ESSPRI total score and ESSPRI pain score (neuropathic subcategory), while a negative correlation was found with SF-36 vitality score, physical functioning score, and the SF-36 total score. FM is common among pSjD patients and should be considered rather a comorbidity requiring different therapeutic approaches. At the fast-paced clinical environment, a concise ESSPRI assessment may be helpful in the initial screening of patients at risk of FM. Even though the origin of this phenomenon is unknown, the concepts of central sensitization and microglia polarization may be potential explanations and more molecular research in this direction could benefit the pSjD patients. Full article

Background/Objectives: Segmental non-mass enhancement (NME) is the breast MRI distribution pattern with the highest positive predictive value (PPV) for malignancy. Despite its diagnostic relevance, its imaging characteristics have rarely been examined in isolation, leaving uncertainty in clinical practice. This multicenter retrospective cohort study aimed to evaluate multiparametric MRI features—including internal enhancement pattern, dynamic contrast-enhanced (DCE) kinetics, and diffusion restriction—in segmental NME to identify malignancy predictors. Methods: This retrospective cohort review included 14,834 breast MRI reports from five institutions (September 2017–February 2024), identifying 103 women (mean age, 44.4 ± 9.9 years) with segmental NME (70 malignant, 33 benign). MRI was performed at 1.5 T or 3 T using standardized protocols. Two breast radiologists, blinded to pathology, assessed internal enhancement, DCE kinetics, diffusion restriction, and short tau inversion recovery (STIR) features according to BI-RADS. Statistical analyses included chi-square/Fisher’s tests and logistic regression. Results: Clustered ring enhancement (CRE) was significantly associated with malignancy (p = 0.004). Fast initial-phase enhancement (p < 0.001) and delayed-phase washout (p = 0.011) also correlated with malignancy. On multivariate analysis, fast initial-phase enhancement remained an independent predictor (odds ratio [OR] = 5.133, p = 0.031), whereas slow enhancement predicted benignity (OR = 0.194, p = 0.020). Histologies included ductal carcinoma in situ, invasive ductal carcinoma, granulomatous mastitis, and benign hyperplastic lesions. Conclusions: This study, focusing exclusively on segmental NME, identifies CRE, fast initial-phase enhancement, and washout kinetics as reliable imaging biomarkers. Incorporating these features into breast MRI interpretation may improve diagnostic accuracy, risk stratification, and management decisions. Full article

Arteriovenous malformations (AVMs) are fast-flow vascular malformations formed by direct artery-to-vein shunts without an intervening capillary bed, which increases the risk of hemorrhage and organ-specific damage. A synthesis of recent advances shows that AVMs arise from interplay between germline susceptibility (ENG, ACVRL1, SMAD4, RASA1, EPHB4), somatic mosaicism (KRAS, MAP2K1, PIK3CA), perturbed signaling (TGF-β/BMP, Notch, VEGF, PI3K/AKT, RAS/MAPK), hemodynamic stress, and inflammation. Multimodal imaging—digital subtraction angiography (DSA), MRI/MRA with perfusion and susceptibility sequences, CTA, Doppler ultrasound, and 3D rotational angiography—underpins diagnosis and risk stratification, while arterial spin labeling and 4D flow techniques refine hemodynamic assessment. Management is individualized and multidisciplinary, combining endovascular embolization, microsurgical resection, and stereotactic radiosurgery (SRS); a non-surgical approach and monitoring remain reasonable for some asymptomatic AVMs. Device and technique innovations (detachable-tip microcatheters, pressure-cooker approaches, and newer liquid embolics such as PHIL and Squid) have broadened candidacy, and precision-medicine strategies, including pathway-targeted pharmacotherapy, are emerging for syndromic and somatic-mutation–driven AVMs. Animal models and computational/radiomics tools increasingly guide hypothesis generation and treatment selection. We outline practical updates and future priorities: integrated genomic-imaging risk scores, genotype-informed medical therapy, rational hybrid sequencing, and long-term outcome standards focused on hemorrhage prevention and quality of life. Full article