Leiner, Tim

A vendor-neutral Agatston score enabled consistent aortic valve calcium quantification across CT systems and improved identification of severe aortic stenosis in patients with discordant echocardiographic findings.

Introduction: This study aimed to develop and evaluate a deep learning (DL) deblurring algorithm for computed tomography (CT). Phantom testing assessed whether DL deblurring could improve CT image quality and coronary artery calcium (CAC) detectability. Materials and Methods: The algorithm consisted of 2 sequential convolutional neural networks (CNNs): one for denoising and one for deblurring. After deblurring, the estimated noise from the first model was reintroduced to preserve image texture. The CNN denoising model was trained to map high-noise images to routine low-noise ones. The CNN deblurring model was trained using natural images—blurred inputs paired with sharp targets. To assess performance, an anthropomorphic phantom with 100 small calcifications was scanned on a CT system using a CAC scoring protocol. Data were acquired at clinical and high doses, then reconstructed with and without DL deblurring, using 25% of the maximum denoising strength. Detectability was defined as the ability to calculate an Agatston score (≥3 adjacent voxels >130 HU). Results: At high dose, CAC detectability increased from 39% (standard reconstruction) to 48% with deblurring. Similar detectability (39%) was achieved at the routine dose with deblurring, representing a 6% improvement compared with the original routine dose data. Discussion: Quantitative results from phantom testing demonstrate that DL deblurring can improve image quality, based on a clinically relevant, task-based CAC detection metric at clinical dose levels.

Foundation models can streamline imaging workflows, improve diagnostic accuracy, enable personalized treatment, and, via integrated generative artificial intelligence, create synthetic images to augment scarce real-world data; however, successful adoption requires explainability, trust, and workflow integration.

Abstract Background The association of body composition with checkpoint inhibitor outcomes in melanoma is a matter of ongoing debate. In this study, we aim to investigate body mass index (BMI) alongside computed tomography (CT)-derived body composition metrics in the largest cohort to date. Methods Patients treated with first-line anti-PD1 ± anti-CTLA4 for advanced melanoma were retrospectively identified from 11 melanoma centers in The Netherlands. From baseline CT scans, 5 body composition metrics were extracted: subcutaneous adipose tissue index, visceral adipose tissue index, skeletal muscle index, density, and gauge. These metrics were correlated in univariable and multivariable Cox proportional hazards analysis with progression-free survival, overall survival, and melanoma-specific survival (PFS, OS, and MSS). Results A total of 1471 eligible patients were included. Median PFS and OS were 9.1 and 38.1 months, respectively. Worse PFS was observed in underweight patients (multivariable hazard ratio [HR] = 1.86, 95% CI = 1.14 to 3.06). Furthermore, prolonged OS was observed in patients with higher skeletal muscle density (multivariable HR = 0.88, 95% CI = 0.81 to 0.97) and gauge (multivariable HR = 0.61, 95% CI = 0.82 to 0.998), whereas higher visceral adipose tissue index was associated with worse OS (multivariable HR = 1.12, 95% CI = 1.04 to 1.22). No association with survival outcomes was found for overweight, obesity, or subcutaneous adipose tissue. Conclusion Our findings suggest that underweight BMI is associated with worse PFS, whereas higher skeletal muscle density and lower visceral adipose tissue index were associated with improved OS. These associations were independent of known prognostic factors, including sex, age, performance status, and extent of disease. No significant association between higher BMI and survival outcomes was observed.

Fetal cardiovascular magnetic resonance imaging (MRI) has emerged as a complementary modality for prenatal imaging in suspected congenital heart disease. Ongoing technical improvements extend the potential clinical value of fetal cardiovascular MRI. Ascertaining equivocal prenatal diagnostics obtained with ultrasonography allows for appropriate parental counseling and planning of postnatal surgery. This work summarizes current acquisition techniques and clinical applications of fetal cardiovascular MRI in the prenatal diagnosis and follow‐up of fetuses with congenital heart disease.Level of Evidence3Technical EfficacyStage 3

Background Adolescents with chronic disease are often exposed to inflammatory, metabolic, and hemodynamic risk factors for early atherosclerosis. Since postmortem studies have shown that atherogenesis starts in the aorta, the CDACD (Cardiovascular Disease in Adolescents with Chronic Disease) study investigated preclinical aortic atherosclerosis in these adolescents. Methods and Results The cross‐sectional CDACD study enrolled 114 adolescents 12 to 18 years old with chronic disorders including juvenile idiopathic arthritis, cystic fibrosis, obesity, corrected coarctation of the aorta, and healthy controls with a corrected atrial septal defect. Cardiovascular magnetic resonance was used to assess aortic pulse wave velocity and aortic wall thickness, as established aortic measures of preclinical atherosclerosis. Cardiovascular magnetic resonance showed a higher aortic pulse wave velocity, which reflects aortic stiffness, and higher aortic wall thickness in all adolescent chronic disease groups, compared with controls ( P <0.05). Age (β=0.253), heart rate (β=0.236), systolic blood pressure (β=−0.264), and diastolic blood pressure (β=0.365) were identified as significant predictors for aortic pulse wave velocity, using multivariable linear regression analysis. Aortic wall thickness was predicted by body mass index (β=0.248) and fasting glucose (β=0.242), next to aortic lumen area (β=0.340). Carotid intima‐media thickness was assessed using ultrasonography, and was only higher in adolescents with coarctation of the aorta, compared with controls ( P <0.001). Conclusions Adolescents with chronic disease showed enhanced aortic stiffness and wall thickness compared with controls. The enhanced aortic pulse wave velocity and aortic wall thickness in adolescents with chronic disease could indicate accelerated atherogenesis. Our findings underscore the importance of the aorta for assessment of early atherosclerosis, and the need for tailored cardiovascular follow‐up of children with chronic disease.

AbstractIron overload is a severe general complication of hereditary anemias. Treatment with iron chelators is hampered by important side‐effects, high costs, and the lack of availability in many countries with a high prevalence of hereditary anemias. In this phase III randomized placebo‐controlled trial, we assigned adults with non‐transfusion‐dependent hereditary anemias with mild‐to‐moderate iron overload to receive esomeprazole (at a dose of 40 mg twice daily) or placebo for 12 months in a cross‐over design. The primary end point was change of liver iron content measured by MRI. A total of 30 participants were enrolled in the trial. Treatment with esomeprazole resulted in a statistically significant reduction in liver iron content that was 0.55 mg Fe/g dw larger than after treatment with placebo (95%CI [0.05 to 1.06]; p = 0.03). Median baseline liver iron content at the start of esomeprazole was 4.99 versus 4.49 mg Fe/g dw at start of placebo. Mean delta liver iron content after esomeprazole treatment was −0.57 (SD 1.20) versus −0.11 mg Fe/g dw (SD 0.75) after placebo treatment. Esomeprazole was well tolerated, reported adverse events were mild and none of the patients withdrew from the study due to side effects. In summary, esomeprazole resulted in a significant reduction in liver iron content when compared to placebo in a heterogeneous group of patients with non‐transfusion‐dependent hereditary anemias. From an international perspective this result can have major implications given the fact that proton pump inhibitors may frequently be the only realistic therapy for many patients without access to or not tolerating iron chelators.

Abstract Aims Precapillary pulmonary hypertension (pPH) affects left ventricular (LV) function by ventricular interdependence. Since LV ejection fraction (EF) is commonly preserved, LV dysfunction should be assessed with more sensitive techniques. Left atrial (LA) strain and estimation of LV intraventricular pressure gradients (IVPG) may be valuable in detecting subtle changes in LV mechanics; however, the value of these techniques in pPH is unknown. Therefore, the aim of our study is to evaluate LA strain and LV-IVPGs from cardiovascular magnetic resonance (CMR) cines in pPH patients. Methods and results In this cross-sectional study, 31 pPH patients and 22 healthy volunteers underwent CMR imaging. Feature-tracking LA strain was measured on four- and two-chamber cines. LV-IVPGs (from apex–base) are computed from a formulation using the myocardial movement and velocity of the reconstructed 3D-LV (derived from long-axis cines using feature-tracking). Systolic function, both LV EF and systolic ejection IVPG, was preserved in pPH patients. Compared to healthy volunteers, diastolic function was impaired in pPH patients, depicted by (i) lower LA reservoir (36 ± 7% vs. 26 ± 9%, P &lt; 0.001) and conduit strain (26 ± 6% vs. 15 ± 8%, P &lt; 0.001) and (ii) impaired diastolic suction (−9.1 ± 3.0 vs. ‒6.4 ± 4.4, P = 0.02) and E-wave decelerative IVPG (8.9 ± 2.6 vs. 5.7 ± 3.1, P &lt; 0.001). Additionally, 11 pPH patients (35%) showed reversal of IVPG at systolic–diastolic transition compared to none of the healthy volunteers (P = 0.002). Conclusions pPH impacts LV function by altering diastolic function, demonstrated by an impairment of LA phasic function and LV-IVPG analysis. These parameters could therefore potentially be used as early markers for LV functional decline in pPH patients.