The aim of this study was to assess the ability of MRI radiomic features to differentiate between benign parotid gland tumors (BPGT) and malignant parotid gland tumors (MPGT). This retrospective study included 93 patients who underwent MRI examinations of the head and neck region (78 patients presenting unique PGT, while 15 patients presented double PGT). A total of 108 PGT with histological confirmation were eligible for the radiomic analysis and were assigned to a training group (n = 83; 58 BPGT; 25 MPGT) and a testing group (n = 25; 16 BPGT; 9 MPGT). The radiomic features were extracted from 3D segmentations of the PGT on the T2-weighted and fat-saturated, contrast-enhanced T1-weighted images. Following feature reduction techniques, including LASSO regression analysis, a radiomic signature (RS) was built with five radiomic features. The RS presented a good diagnostic performance in differentiating between PGT, achieving an area under the curve (AUC) of 0.852 (p < 0.001) in the training set and 0.786 (p = 0.017) in the testing set. In both datasets, the RS proved to have lower values in the BPGT group as compared to MPGT group (p < 0.001 and p = 0.023, respectively). The multivariate analysis revealed that RS was independently associated with PGT malignancy, together with the ill-defined margin pattern (p = 0.031, p = 0.001, respectively). The complex model, using clinical data, MRI features and the RS, presented a higher diagnostic performance (AUC of 0.976) in comparison to the RS alone. MRI-based radiomic features could be considered potential additional imaging biomarkers able to discriminate between benign and malignant parotid gland tumors.
This study aimed to assess the effectiveness of MRI-based texture features of the lacrimal glands (LG) in augmenting the imaging differentiation between primary Sjögren’s Syndrome (pSS) affected LG and healthy LG, as well as to emphasize the possible importance of radiomics in pSS early-imaging diagnosis. The MRI examinations of 23 patients diagnosed with pSS and 23 healthy controls were retrospectively included. Texture features of both LG were extracted from a coronal post-contrast T1-weighted sequence, using a dedicated software. The ability of texture features to discriminate between healthy and pSS lacrimal glands was performed through univariate, multivariate, and receiver operating characteristics analysis. Two quantitative textural analysis features, RunLengthNonUniformityNormalized (RLNonUN) and Maximum2DDiameterColumn (Max2DDC), were independent predictors of pSS-affected glands (p < 0.001). Their combined ability was able to identify pSS LG with 91.67% sensitivity and 83.33% specificity. MRI-based texture features have the potential to function as quantitative additional criteria that could increase the diagnostic accuracy of pSS-affected LG.
This study aimed to assess the effectiveness of saline sealing in reducing the incidence of pneumothorax after a CT-guided lung biopsy. This was a retrospective case-control study of patients who underwent CT-guided biopsies for lung tumors using 18 G semiautomatic core needles in conjunction with 17 G coaxial needles. The patients were divided into two consecutive groups: a historical Group A (n = 111), who did not receive saline sealing, and Group B (n = 87), who received saline sealing. In Group B, NaCl 0.9% was injected through the coaxial needle upon its removal. The incidence of pneumothorax and chest tube insertion was compared between the two groups. Multivariate logistic regression was performed to verify the contribution of other pneumothorax risk factors. The study included 198 patients, with 111 in Group A and 87 in Group B. There was a significantly (p = 0.02) higher pneumothorax rate in Group A (35.1%, n = 39) compared to Group B (20.7%, n = 18). The difference regarding chest tube insertion was not significant (p = 0.1), despite a tendency towards more insertions in Group A (5.4%, n = 6), compared to Group B (1.1%, n = 1). Among the risk factors for pneumothorax, only the presence of emphysema (OR = 3.5, p = 0.0007) and belonging to Group A (OR = 2.2, p = 0.02) were significant. Saline sealing of the needle tract after a CT-guided lung biopsy can significantly reduce the incidence of pneumothorax. This technique is safe, readily available, and inexpensive, and should be considered as a routine preventive measure during this procedure.
Biological soft tissues are characterized by viscoelastic properties. The propagation of shear waves within tissues is influenced by both elasticity, which is linked to the shear wave speed, and viscosity, which is linked to the shear wave dispersion. This study aimed to functionally assess the parotid glands (PG) and submandibular glands (SMG) in a group of 40 healthy subjects using the novel Viscosity PLUS (Vi.PLUS) and 2D Shear-Wave Elastography PLUS (2D-SWE.PLUS) techniques. The viscosity and stiffness of PG and SMG were measured before and after gustatory stimulation with a sialagogue agent (commercially available lemon juice) using the new SuperSonic MACH 30 ultrasound system equipped with a curvilinear C6-1X transducer. PG presented a mean basal viscosity and elasticity of 2.10 ± 0.19 Pa.s and 11.32 ± 1.91 kPa, respectively, which significantly increased poststimulation to 2.39 ± 0.17 Pa.s (p < 0.001) and 12.58 ± 1.92 kPa (p < 0.001), respectively. SMG did not present statistically increased values of viscosity and elasticity following stimulation (2.31 ± 015 Pa.s vs. 2.37 ± 0.18 Pa.s, p = 0.086, and 10.40 ± 1.64 kPa vs. 10.90 ± 1.98 kPa, p = 0.074, respectively). Vi.PLUS measurements presented a good positive correlation with 2D-SWE.PLUS values for PG and SMG, before and after stimulation. Gender and BMI were not confounding factors for these two parameters. Vi.PLUS represents an innovative non-invasive imaging technique that, together with 2D-SWE.PLUS proves to be useful in functionally assessing the major salivary glands in healthy subjects.
Viscosity and elasticity represent biomechanical properties of soft tissues that suffer changes during the pathophysiological alterations of the tissue in various conditions. This study aimed to determine average viscosity values for the thyroid gland and to evaluate the potential influences of age, gender and body mass index (BMI), using a recent technique Viscosity Plane-wave UltraSound (Vi PLUS). A total of 85 healthy Caucasian volunteers (56 women and 29 men, median age of 29 years, range 17–81 years) were included in this prospective monocentric study conducted between January 2022 and March 2022. Thyroid viscosity was measured using the SuperSonic MACH 30® Ultrasound system (Aixplorer, SuperSonic Imagine, Aix-en-Provence, France), equipped with a curvilinear C6-IX transducer that allows simultaneous quantification of the viscosity and stiffness. The mean thyroid viscosity measurement value was 2.63 ± 0.47 Pa.s. No statistically significant differences were detected between the left and the right lobes of the thyroid gland. A significant positive correlation was found between thyroid viscosity and elasticity (r = 0.685, p < 0.0001). There was no statistically significant correlation between body mass index (BMI) and thyroid gland viscosity and elasticity values (r = 0.215, p = 0.053; r = 0.106, p = 0.333). No correlation between viscosity and gender was established (p > 0.05). Vi PLUS represents a new and promising ultrasonographic technique that can provide helpful information for evaluating the thyroid parenchyma, similar to elastography. The effect of the potential confounding factors on thyroid viscosity was negligible, except for BMI.
It has recently been shown that the interpretation by partial differential equations (PDEs) of a class of convolutional neural networks (CNNs) supports definition of architectures such as parabolic and hyperbolic networks. These networks have provable properties regarding the stability against the perturbations of the input features. Aiming for robustness, we tackle the problem of detecting changes in chest X-ray images that may be suggestive of COVID-19 with parabolic and hyperbolic CNNs and with domain-specific transfer learning. To this end, we compile public data on patients diagnosed with COVID-19, pneumonia, and tuberculosis, along with normal chest X-ray images. The negative impact of the small number of COVID-19 images is reduced by applying transfer learning in several ways. For the parabolic and hyperbolic networks, we pretrain the networks on normal and pneumonia images and further use the obtained weights as the initializers for the networks to discriminate between COVID-19, pneumonia, tuberculosis, and normal aspects. For DenseNets, we apply transfer learning twice. First, the ImageNet pretrained weights are used to train on the CheXpert dataset, which includes 14 common radiological observations (e.g., lung opacity, cardiomegaly, fracture, support devices). Then, the weights are used to initialize the network which detects COVID-19 and the three other classes. The resulting networks are compared in terms of how well they adapt to the small number of COVID-19 images. According to our quantitative and qualitative analysis, the resulting networks are more reliable compared to those obtained by direct training on the targeted dataset.
About Me
Radiology Resident
PhD Student at the University of Medicine and Pharmacy "Iuliu Hațieganu" Cluj-Napoca
Radiology Resident
PhD Student at the University of Medicine and Pharmacy "Iuliu Hațieganu" Cluj-Napoca