A radiomics-based logistic regression model for the assessment of emphysema severity.

Introduction: The aim of this study is to develop a model that differentiates between the radiological patterns of severe and mild emphysema using radiomics parameters, as well as to examine the parameters included in the model. Materials and Methods: Over the last 12 months, a total of 354 patients were screened based on the presence of terms such as "Fleischner", "CLE", and "centriacinar" in their thoracic CT reports, culminating in a study population of 82 patients. The study population was divided into Group 1 (Fleischner mild and moderate; n= 45) and Group 2 (Fleischner confluent and advanced destructive; n= 37). Volumetric segmentation was performed, focusing on the upper lobe segments of both lungs. From these segmented volumes, radiomics parameters including shape, size, first-order, and second-order features were calculated. The best model parameters were selected based on the Bayesian Information Criterion and further optimized through grid search. The final model was tested using 1000 iterations of bootstrap resampling. Results: In the training set, performance metrics were calculated with a sensitivity of 0.862, specificity of 0.870, accuracy of 0.863, and AUC of 0.910. Correspondingly, in the test set, these values were sensitivity= 0.848; specificity= 0.865; accuracy= 0.857; and AUC= 0.907. Conclusion: The logistic regression model, composed of radiomics parameters and trained on a limited number of cases, effectively differentiated between mild and severe radiological patterns of emphysema using computed tomography images.

A CT Radiomics Analysis of the Adrenal Masses: Can We Discriminate Lipid-poor Adenomas from the Pheochromocytoma and Malignant Masses?

AIMS: The aim of the study is to demonstrate a non-invasive alternative method to aid the decision making process in the management of adrenal masses. BACKGROUND: Lipid-poor adenomas constitute 30% of all adrenal adenomas. When discovered incidentally, additional dynamic adrenal examinations are required to differentiate them from an adrenal malignancy or pheochromocytoma. OBJECTIVE: In this retrospective study, we aimed to discriminate lipid-poor adenomas from other lipidpoor adrenal masses by using radiomics analysis in single contrast phase CT scans. MATERIALS AND METHODS: A total of 38 histologically proven lipid-poor adenomas (Group 1) and 38 cases of pheochromocytoma or malignant adrenal mass (Group 2) were included in this retrospective study. Lesions were segmented volumetrically by two independent authors, and a total of 63 sizes, shapes, and first- and second-order parameters were calculated. Among these parameters, a logit-fit model was produced by using 6 parameters selected by the LASSO (least absolute shrinkage and selection operator) regression. The model was cross-validated with LOOCV (leave-one-out crossvalidation) and 1000-bootstrap sampling. A random forest model was also generated in order to use all parameters without the risk of multicollinearity. This model was examined with the nested crossvalidation method. RESULTS: Sensitivity, specificity, accuracy and AUC were calculated in test sets as 84.2%, 81.6%, 82.9% and 0.829 in the logit fit model and 91%, 80%, 82.8% and 0.975 in the RF model, respectively. CONCLUSION: Predictive models based on radiomics analysis using single-phase contrast-enhanced CT can help characterize adrenal lesions.

Evaluation of the models generated from clinical features and deep learning-based segmentations: Can thoracic CT on admission help us to predict hospitalized COVID-19 patients who will require intensive care?

BACKGROUND: The aim of the study was to predict the probability of intensive care unit (ICU) care for inpatient COVID-19 cases using clinical and artificial intelligence segmentation-based volumetric and CT-radiomics parameters on admission. METHODS: Twenty-eight clinical/laboratory features, 21 volumetric parameters, and 74 radiomics parameters obtained by deep learning (DL)-based segmentations from CT examinations of 191 severe COVID-19 inpatients admitted between March 2020 and March 2021 were collected. Patients were divided into Group 1 (117 patients discharged from the inpatient service) and Group 2 (74 patients transferred to the ICU), and the differences between the groups were evaluated with the T-test and Mann-Whitney test. The sensitivities and specificities of significantly different parameters were evaluated by ROC analysis. Subsequently, 152 (79.5%) patients were assigned to the training/cross-validation set, and 39 (20.5%) patients were assigned to the test set. Clinical, radiological, and combined logit-fit models were generated by using the Bayesian information criterion from the training set and optimized via tenfold cross-validation. To simultaneously use all of the clinical, volumetric, and radiomics parameters, a random forest model was produced, and this model was trained by using a balanced training set created by adding synthetic data to the existing training/cross-validation set. The results of the models in predicting ICU patients were evaluated with the test set. RESULTS: No parameter individually created a reliable classifier. When the test set was evaluated with the final models, the AUC values were 0.736, 0.708, and 0.794, the specificity values were 79.17%, 79.17%, and 87.50%, the sensitivity values were 66.67%, 60%, and 73.33%, and the F1 values were 0.67, 0.62, and 0.76 for the clinical, radiological, and combined logit-fit models, respectively. The random forest model that was trained with the balanced training/cross-validation set was the most successful model, achieving an AUC of 0.837, specificity of 87.50%, sensitivity of 80%, and F1 value of 0.80 in the test set. CONCLUSION: By using a machine learning algorithm that was composed of clinical and DL-segmentation-based radiological parameters and that was trained with a balanced data set, COVID-19 patients who may require intensive care could be successfully predicted.

A CT radiomics analysis of COVID-19-related ground-glass opacities and consolidation: Is it valuable in a differential diagnosis with other atypical pneumonias?

PURPOSE: To evaluate the discrimination of parenchymal lesions between COVID-19 and other atypical pneumonia (AP) by using only radiomics features. METHODS: In this retrospective study, 301 pneumonic lesions (150 ground-glass opacity [GGO], 52 crazy paving [CP], 99 consolidation) obtained from nonenhanced thorax CT scans of 74 AP (46 male and 28 female; 48.25±13.67 years) and 60 COVID-19 (39 male and 21 female; 48.01±20.38 years) patients were segmented manually by two independent radiologists, and Location, Size, Shape, and First- and Second-order radiomics features were calculated. RESULTS: Multiple parameters showed significant differences between AP and COVID-19-related GGOs and consolidations, although only the Range parameter was significantly different for CPs. Models developed by using the Bayesian information criterion (BIC) for the whole group of GGO and consolidation lesions predicted COVID-19 consolidation and AP GGO lesions with low accuracy (46.1% and 60.8%, respectively). Thus, instead of subjective classification, lesions were reclassified according to their skewness into positive skewness group (PSG, 78 AP and 71 COVID-19 lesions) and negative skewness group (NSG, 56 AP and 44 COVID-19 lesions), and group-specific models were created. The best AUC, accuracy, sensitivity, and specificity were respectively 0.774, 75.8%, 74.6%, and 76.9% among the PSG models and 0.907, 83%, 79.5%, and 85.7% for the NSG models. The best PSG model was also better at predicting NSG lesions smaller than 3 mL. Using an algorithm, 80% of COVID-19 and 81.1% of AP patients were correctly predicted. CONCLUSION: During periods of increasing AP, radiomics parameters may provide valuable data for the differential diagnosis of COVID-19.

Predictive performance of CT for adverse outcomes among COVID-19 suspected patients: a two-center retrospective study.

The aim of the study was to compare the performance of various computed tomography (CT) reporting tools, including zonal CT visual score (ZCVS), the number of involved lobes, and Radiological Society of North America (RSNA) categorization in predicting adverse outcomes among patients hospitalized due to the lower respiratory symptoms during the coronavirus disease 2019 (COVID-19) pandemic. A total of 405 patients admitted with severe respiratory symptoms who underwent a chest CT were enrolled. The primary adverse outcome was intensive care unit (ICU) admission of patients. Predictive performances of reporting tools were compared using the area under the receiver operating characteristic curves (AUC ROC). Among the 405 patients, 39 (9.63%) required ICU support during their hospital stay. At least two or more observers reported a typical and indeterminate COVID-19 pneumonia CT pattern according to RSNA categorization in 70% (285/405) of patients. Among these, 63% (179/285) had a positive polymerase chain reaction (PCR test for the SARS-CoV-2 virus. The median number of lobes involved according to CT was higher in patients who required ICU support (median interquartile range [IQR], 5[3; 5] vs. 3[0; 5]). The median ZCVS score was higher among the patients that subsequently required ICU support (median [IQR], 4[0; 12] vs. 13[5.75; 24]). The bootstrap comparisons of AUC ROC showed significant differences between reporting tools, and the ZCVS was found to be superior (AUC ROC, 71-75%). The ZCVS score at the first admission showed a linear and significant association with adverse outcomes among patients with the lower respiratory tract symptoms during the COVID-19 pandemic.

Intravoxel incoherent motion parameters in the evaluation of chronic hepatitis B virus-induced hepatic injury: fibrosis and capillarity changes.

OBJECTIVE: To evaluate the diagnostic efficacy of intravoxel incoherent motion (IVIM) parameters in hepatitis B virus (HBV)-induced hepatic fibrosis using different calculation methods and to investigate histopathologic origins. MATERIALS AND METHODS: Liver biopsies from 37 prospectively recruited chronic hepatitis B patients were obtained. Twelve b-value (0-1000 s/mm2) diffusion-weighted imaging (DWI) was performed with a 1.5 T scanner and was followed by blinded percutaneous liver biopsy. All biopsy specimens were evaluated with Ishak staging, and the microvascular density (MVD) was calculated. Patients were classified as having no/mild (F0-1), moderate (F2-3), or marked (F4-5) fibrosis. Pseudodiffusion (D*), the perfusion fraction (f), and the apparent diffusion coefficient (ADC) were calculated using all b-values, while true diffusion (D) was calculated using all b-values [D0-1000] and b-values greater than 200 s/mm2 [D200-1000]. Three concentric regions of interest (ROIs) (5, 10, and 20 mm) centered on the biopsy site were used. RESULTS: D* was correlated with the MVD (p = 0.015, Pearson's r = 0.415), but f was not (p = 0.119). D0-1000 was inversely correlated with Ishak stage (p = 0.000, Spearman's rs = - 0.685) and was significantly decreased in all the fibrosis groups; however, only the no/mild and marked fibrosis groups had significantly different D200-1000 values. A pairwise comparison of receiver operating characteristic (ROC) curves of D0-1000 and D200-1000 showed significant differences (p = 0.039). D* was the best at discriminating early fibrosis (AUC = 0.861), while the ADC best discriminated advanced fibrosis (AUC = 0.964). CONCLUSION: D* was correlated with the MVD and is a powerful parameter to discriminate early hepatic fibrosis. D significantly decreased with advanced fibrosis stage when using b-values less than 200 s/mm2 in calculations.

Real-time sonoelastography of the quadriceps tendon in patients undergoing chronic hemodialysis.

OBJECTIVES: This study aimed to compare sonoelastographic findings for the quadriceps tendon in patients with chronic renal failure who were in a dialysis program to findings in a control group. METHODS: Fifty-three randomly allocated patients (mean age, 54.3 years; range, 27-86 years) with chronic renal failure who were in a dialysis program 3 days a week between January and May 2012 were included. The measurements were performed in both knees of 53 patients undergoing dialysis and 25 individuals in the control group. The tendons were classified as follows: type 1, very stiff tissue (blue); type 2, stiff tissue (blue-green); and type 3, intermediate tissue (green-yellow) according to color mapping. RESULTS: The mean quadriceps tendon thicknesses in the patient group were 4.9 mm (range, 1.9-6.5 mm) for the right knee and 4.9 mm (1.4-6.5 mm) for the left knee; the values in the control group were 5.4 mm (3.6-7.0 mm) for the right knee and 5.4 mm (3.4-7.0 mm) for the left knee. The mean elasticity scores in the patient group were 3.14 (1.03-5.23) for the right knee and 3.33 (1.29-5.00) for the left knee; in the control group, the values were 3.79 (1.73-5.23) and 3.69 (1.23-5.53) for the right and left knees, respectively (right knee, P = .025; left knee, P = .018; Mann-Whitney U test). The quadriceps tendons were significantly thinner in the patient group (right knee, P = .054; left knee, P = .015; Mann-Whitney U test). CONCLUSIONS: Quadriceps tendons in patients with chronic renal failure are thinner and have lower elasticity scores compared to controls.

Prevalence of severe carotid artery stenosis and its association with echocardiographic parameters in maintenance hemodialysis patients.

OBJECTIVES: We aimed to determine the prevalence of significant carotid stenosis in maintenance hemodialysis patients and to identify biochemical and echocardiographic predictors of significant carotid stenosis in those patients. STUDY DESIGN: One hundred and seventeen maintenance hemodialysis patients were included in this study. Echocardiography biochemical tests and carotid artery Doppler ultrasonography were performed in all patients. Data obtained from patients without severe carotid stenosis were compared with those obtained from patients with severe carotid stenosis. RESULTS: The mean age of the patients was 56.9±12.2 years. Eleven patients had carotid artery stenosis (9.4%). While there was a trend of higher left ventricle end diastolic diameter in severe carotid artery stenosis (p=0.06), no statistically significant biochemical or echocardiographic differences were noted between the patients. CONCLUSION: This study demonstrated that the prevalence of carotid artery stenosis is 5-10- fold higher than in the general population. All patients in a chronic hemodialysis program should be screened for carotid artery stenosis for prevention of cerebrovascular diseases.

Plasma fibroblast growth factor-23 levels are independently associated with carotid artery atherosclerosis in maintenance hemodialysis patients.

Fibroblast growth factor-23 (FGF-23) has been suggested to play a role in vascular calcification in chronic kidney disease. Common carotid artery intima-media thickness (CIMT) assessment and common carotid artery (CCA) plaque identification using ultrasound are well-recognized tools for identification and monitoring of atherosclerosis. The aim of this study was to test that elevated FGF-23 levels might be associated with carotid artery atherosclerosis in maintenance hemodialysis (HD) patients. In this cross-sectional study, plasma FGF-23 concentrations were measured using a C-terminal human enzyme-linked immunosorbent assay kit. Carotid artery intima-media thickness was measured and CCA plaques were identified by B-Mode Doppler ultrasound. One hundred twenty-eight maintenance HD patients (65 women and 63 men, mean age: 55.5 ± 13 years, mean HD vintage: 52 ± 10 months, all patients are on HD thrice a week) were involved. The mean CIMT were higher with increasing tertiles of plasma FGF-23 levels (0.66 ± 0.14 vs. 0.75 ± 0.05 vs. 0.86 ± 0.20 mm, P<0.0001). Log plasma FGF-23 were higher in patients with plaques in CCA than patients free of plaques (3.0 ± 0.17 vs. 2.7 ± 0.23, P<0.0001). Significant correlation was recorded between log plasma FGF-23 and CIMT (r=0,497, P=0.0001). In multiple regression analysis, a high log FGF-23 concentration was a significant independent risk factor of an increased CIMT. Further studies are needed to clarify whether an increased plasma FGF-23 level is a marker or a potential mechanism for atherosclerosis in patients with end-stage renal disease.

Microscopic polyangiitis with unusual lung involvement.

Microscopic polyangiitis (MPA) is a non-granulomatous, systemic and small vessel vasculitis accompanied by segmental necrotizing glomerulonephritis with no evidence of other small vessel disease. We report a patient with weakness, fever, and arthralgia whose CXR and thoracic CT showed widespread nodular infiltration. His proteinase-3 anti-neutrophilic cytoplasmic antibody (c-ANCA) was positive. The serum creatinine was increased and haematuria subsequently developed. Renal biopsy revealed a focal segmental necrotizing glomerulonephritis which was compatible with MPA. He was treated with high-dose corticosteroid and cyclophosphamide. Because of a worsening CXR and hypoxaemia, mechanical ventilation was applied. Despite this he died of respiratory failure following 20 days of treatment. Nodular infiltration is an unusual radiological pattern in patients with MPA and is the reason for this report.

Preoperative evaluation of renal anatomy and renal masses with helical CT, 3D-CT and 3D-CT angiography.

PURPOSE: The aim of this prospective study was to determine the efficacy of three-dimensional computed tomography (3D-CT) and three-dimensional computed tomographic angiography (3D-CTA) that were reconstructed by using the axial images of the multiphasic helical CT in the preoperative evaluation of renal masses and demonstration of renal anatomy. MATERIALS AND METHODS: Twenty patients that were suspected of having renal masses upon initial physical examination and ultrasonographic evaluation were examined through multiphasic helical CT. Two authors executed CT evaluations. Axial images were first examined and then used to reconstruct 3D-CT and 3D- CTA images. Number, location and size of the renal masses and other findings were noted. Renal vascularization and relationships of the renal masses with the neighboring renal structures were further investigated with 3D-CT and 3D-CTA images. RESULTS: Out of 20 patients, 13 had histopathologically proven renal cell carcinoma. The diagnoses of the remaining seven patients were xanthogranulomatous pyelonephritis, abscess, simple cyst, infected cyst, angiomyolipoma, oncocytoma and arteriovenous fistula. In the renal cell carcinoma group, 3 patients had stage I, 7 patients had stage II, and 3 patients had stage III disease. Sizes of renal cell carcinoma masses were between 23 mm to 60 mm (mean, 36 mm). Vascular invasion was shown in 2 renal cell carcinoma patients. Collecting system invasion was identified in 11 of 13 renal cell patients. These radiologic findings were confirmed with surgical specimens. CONCLUSION: Three-dimensional CT and 3D-CTA are non-invasive, effective imaging techniques for the preoperative evaluation of renal masses.

[Hepatopulmonary syndrome]. / Hepatopulmoner sendrom.

Liver diseases affect lungs. Pulmonary vascular diseases are observed in hepatic diseases and portal hypertension have a wide spectrum that varies from intrapulmonary vascular dilatation to increased pulmonary vascular resistance with pulmonary hypertension. Hepatopulmonary syndrome is a syndrome characterized portal hypertension, intrapulmonary vascular dilatation and abnormal oxygenation (hypoxaemia). This review summarizes the clinicopathologic features, diagnostic criteria, and management of hepatopulmonary syndrome.