Vitaliy Atamaniuk

Parotid tumors exhibit diverse biomechanical and microstructural characteristics that remain challenging to characterize noninvasively. This study aimed to investigate these properties using ex vivo tabletop magnetic resonance elastography (MRE) combined with multiparametric MRI, including relaxometry, diffusion‐weighted imaging, and fat quantification. Twelve patients (six males, six females; mean age 60.3 ± 11.2 years) undergoing parotid tumor resection were included. Resected specimens were assessed histopathologically according to the WHO Classification of Head and Neck Tumors (5th edition, 2022) and imaged within 36 h postresection using two‐dimensional Bessel‐MRE alongside T1 and T2 relaxometry, diffusion imaging, and fat fraction mapping. MRE‐derived parameters included shear wave speed (SWS), penetration rate (PR), elasticity ( μ ), and viscosity ( η ). Compared with adjacent normal tissue, pathological tissue demonstrated significantly higher SWS ( p = 0.014), elasticity ( p = 0.027), viscosity ( p = 0.037), and T1 relaxation time ( p < 0.001), along with reduced fat fraction ( p < 0.001). Penetration rate showed a near‐significant increase ( p = 0.065), whereas T2 exhibited no overall difference. Subtype analysis revealed that pleomorphic adenomas had significantly higher apparent diffusion coefficient (ADC) ( p = 0.008), T1 ( p = 0.008), and T2 ( p = 0.008) values than Warthin tumors, with greater deviation from normal tissue. Correlation analysis showed that in normal tissue, fat fraction strongly influenced variability in SWS, T1, and ADC, with ADC demonstrating a strong negative correlation with fat fraction ( r = −0.95, p < 0.001), limiting its interpretability without fat correction. In contrast, pathological tissue demonstrated a tightly coupled cluster of ADC, T1, and T2 ( r = 0.95–0.96, all p < 0.001) reflecting water content, independent of mechanical parameters. These findings indicate that ex vivo MRE combined with multiparametric MRI enables quantitative assessment of parotid tumor properties through complementary biomarkers reflecting distinct physical mechanisms. Although viscoelastic parameters alone were insufficient to differentiate all tumor subtypes, their integration with diffusion and relaxometry metrics provides a more comprehensive characterization of tumor microstructure. This multiparametric approach shows promise for translation to in vivo applications, potentially enabling improved noninvasive tumor characterization and informing surgical planning.

Magnetic resonance elastography (MRE) enables non‐invasive quantification of liver stiffness and plays a pivotal role in the assessment of hepatic fibrosis. However, clinical implementation remains limited by the need for manual delineation of regions of interest (ROIs), which is time‐consuming, requires expert input, and is prone to interobserver variability. This study assesses the feasibility of a single deep learning (DL) pipeline to fully automate this process—from acquired MRE data to liver‐stiffness quantification—within a controlled proof‐of‐concept setting. To investigate this, we developed and validated a convolutional neural network‐based framework capable of reconstructing stiffness maps and generating liver segmentation masks directly from magnitude and phase images. The models were trained using MRE data from 83 adult volunteers (56 women, 27 men; median age 21 years), primarily representing healthy individuals or those with early‐stage disease. This homogeneous cohort was deliberately selected to facilitate proof‐of‐concept development and reduce confounding sources of biological variability during model optimization. Across several neural network architectures (U‐Net, ResNet, and CycleGAN hybrids), the pipeline produced liver‐stiffness estimates with less than 11% deviation from the reference values in all cases, and less than 3% in the best performing configurations. Agreement between automated and manual measurements was comparable to interreader agreement, with intraclass correlation coefficients—ICC(A,1), calculated using a two‐way random effects model for absolute agreement—of 0.86 (95% CI: 0.71–0.95) and 0.89 (95% CI: 0.74–0.97), respectively. Total inference time per examination was 23.7 ± 4.4 s. These findings demonstrate the technical feasibility of a fully automated, AI‐driven postprocessing pipeline for liver MRE within a controlled proof‐of‐concept setting using data from healthy volunteers. Although the approach shows promise for reducing analysis time and operator dependence, further validation in diverse clinical populations is required before broader generalization. This work represents an initial step toward more accessible, scalable, and standardized liver‐stiffness assessment in research and, potentially, future clinical applications.

Uterine leiomyomas are benign gynecologic tumors that occur in approximately 80% of women of reproductive age. Although often asymptomatic, these tumors may, in some cases, require gynecologic intervention. Conventional imaging tools, such as ultrasonography (US) and magnetic resonance imaging (MRI), are most commonly used to guide treatment selection. However, none of these methods provides definitive criteria for qualifying patients for medical, non‐invasive, or surgical therapy. Therefore, there is a pressing need to develop innovative tools that improve the evaluation of uterine masses and allow for safer and more effective patient stratification for appropriate treatment options. In this context, the relatively recent development of techniques for assessing tissue stiffness offers promising possibilities. The aim of this review was to analyze available research on the use of ultrasound elastography and magnetic resonance elastography in the evaluation of uterine leiomyomas. It highlights the feasibility of these techniques in assessing the viscoelastic properties of leiomyomas and explores their potential application in differential diagnosis and treatment planning.

This study evaluated the hypothesis that ⁶⁸Ga-PSMA-11 PET SUV, obtained via an advanced DL approach, correlates better with MR ADC maps than values from conventional PET-MR. Additionally, we aimed to identify the optimal SUV threshold for maximum correlation with ADC values. A cohort of 32 prostate cancer patients underwent CT and corresponding PET-MR imaging. The dataset underwent K-fold cross-validation, dividing it into four folds. In each fold, 24 patients were used for training, and 8 for validation to create DL models. ADC maps from 27 out of 32 patients were successfully aligned with T2 images for detailed analysis, revealing an inverse correlation (ρ = −0.20 to −0.51) between ADC and SUV values in prostate cancer zones. Statistically significant differences in mean SUV values were observed between PETMRI and PETDL. DL-based SUV values show a stronger correlation with ADC than conventional PET-MR values in our investigation.

Parotid glands are one of the most common sites for salivary gland tumors. Conventional imaging techniques have limited usefulness in the quantitative assessment of the parotid glands, making it difficult to differentiate between healthy tissue and tumors, as well as between benign and malignant tumors. Magnetic resonance elastography (MRE) is a non-invasive technique that may potentially overcome these limitations. Nevertheless, due to the size of the parotid gland, increased elastographic resolution is required. This may be achieved by applying shear waves at higher frequencies. However, it also results in stronger attenuation, making the illumination of the parotid challenging. Here, we describe a novel passive driver tailored to the anatomy of the human face, which minimizes the distance shear waves need to travel from the source to the area of interest and thus decreases shear wave attenuation, making high-frequency shear wave MRE feasible.

Magnetic resonance elastography (MRE) is an accurate noninvasive diagnostic tool for assessing the stiffness of parenchymal organs, including the spleen. However, this measurement may be biased due to postprandial changes in splenic stiffness. The aim of the current study was to evaluate postprandial changes in spleen stiffness assessed by MRE in a large sample of healthy volunteers. This was a prospective institutional research ethics board‐approved study. Healthy volunteers with no history of liver disease were recruited for an MRE test and blood draw from December 2018 to July 2019. Each participant underwent spleen MRE after at least 4 h of fasting and again 30 min after a 1000 kcal meal. Also, 14 randomly selected volunteers underwent additional MRE examinations at 1.5 and 2.5 h after food intake. The MRE data were acquired at 60 Hz using a 1.5‐T MRI scanner. The spleen stiffness was assessed using a weighted mean of stiffness values from regions of interest manually drawn on three to five spleen slices. Spearman's rank correlation, Wilcoxon signed‐rank, Friedman, and Mann–Whitney tests were used for statistical analysis. A total of 100 volunteers met the inclusion criteria and were eventually enrolled in this study (age 23 ± 2 years; 65 women). The mean spleen stiffness for the whole group increased by 7.9% (p < 0.001) from the mean ± SD value of 5.09 ± 0.63 (95% CI: 4.96–5.21) kPa in the fasting state to 5.47 ± 0.66 (95% CI 5.34–5.60) kPa 30 min after the meal and then gradually decreased. However, even 2 h 30 min after the meal, the spleen stiffness was higher than in the fasting state. This difference was statistically significant at p less than 0.001. It was concluded that meal intake results in a statistically significant elevation of spleen stiffness that persists for 2.5 h. This finding supports the recommendation for routine fasting for more than 2.5 h prior to assessing MRE‐based spleen stiffness.

Purpose: Magnetic resonance elastography (MRE) has been established as the most accurate noninvasive technique for diagnosing liver fibrosis. Recent publications have suggested that the measurement of splenic stiffness is useful in setting where portal hypertension may be present. The goal of the current study was to compile normative data for MRE-assessed stiffness measurements of the spleen in young adults. Materials and Methods: A total of 100 healthy young Caucasian volunteers (65 females and 35 males) in the age range of 20 to 32 years were enrolled in this study. The participants reported no history of chronic spleen and liver disease, normal alcohol consumption, and a normal diet. The MRE data were acquired by using a 1.5 T whole-body scanner and a 2D GRE pulse sequence with 60 Hz excitation. Spleen stiffness was calculated as a weighted mean of stiffness values in the regions of interest manually drawn by the radiologist on three to five spleen slices. Results: Mean spleen stiffness was 5.09 ± 0.65 kPa for the whole group. Male volunteers had slightly higher splenic stiffness compared to females: 5.28 ± 0.78 vs. 4.98 ± 0.51 kPa, however, this difference was not statistically significant (p = 0.12). Spleen stiffness did not correlate with spleen fat content and liver stiffness but a statistically significant correlation with spleen volume was found. Conclusions: The findings of this study provide normative values for 2D MRE-based measurement of spleen stiffness in young adults, a basis for assessing the value of this biomarker in young patients with portal system pathologies.