Pulmonary artery involvement due to Behçet's syndrome and Hughes Stovin syndrome: a comparative study.

OBJECTIVES: Hughes-Stovin syndrome (HSS) is a rare inflammatory condition defined as pulmonary artery aneurysms (PAA) associated with deep vein thrombosis. It is similar to vascular involvement of Behçet's syndrome (BS), but differs in the absence of typical skin-mucosal findings. Whether HSS is a distinct entity or a form fruste of BS is debated. We formally compared HSS cases retrieved from the literature to BS patients with PAI followed by a tertiary centre. METHODS: A systemic literature search using 'Hughes Stovin syndrome' as the key word covering the period between 2000 and 2023 revealed 58 (43 M/15 F) case reports (PROSPERO: CRD42023413537). We identified 74 (62M/12 F) BS patients with PAI followed up in a tertiary centre in Turkey from 2000 until 2020. We evaluated two cohorts head-to-head in terms of demographic and clinical features. RESULTS: BS and HSS patients were found to be comparable with regard to several demographic, clinical and histopathological features. However, PAA were significantly more frequent and isolated pulmonary artery thrombosis (PAT) less common in HSS than that found in BS. Moreover, patients with HSS were more likely to be treated with anti-coagulants and vascular or surgical interventions, whereas less likely to receive immunosuppressive treatment. CONCLUSIONS: Our study indicates that HSS is indeed an 'incomplete form of BS'. It can be considered as evidence supporting the notion that the vascular phenotype develops independently from skin-mucosa lesions and uveitis in BS. However, HSS has been described mainly focusing on aneurysms, overlooking the aspect of in-situ thrombosis.

Radiomics-based machine learning models in STEMI: a promising tool for the prediction of major adverse cardiac events.

OBJECTIVE: To evaluate the potential value of the machine learning (ML) models using radiomic features of late gadolinium enhancement (LGE) and cine images on magnetic resonance imaging (MRI) along with relevant clinical information and conventional MRI parameters for the prediction of major adverse cardiac events (MACE) in ST-segment elevation myocardial infarction (STEMI) patients. METHODS: This retrospective study included 60 patients with the first STEMI. MACE consisted of new-onset congestive heart failure, ventricular arrhythmia, and cardiac death. Radiomic features were extracted from cine and LGE images. Inter-class correlation coefficients (ICCs) were calculated to assess inter-observer reproducibility. LASSO (least absolute shrinkage and selection operator) method was used for radiomic feature selection. Seven separate models using a different combination of the available information were investigated. Classifications with repeat random sampling were done using adaptive boosting, k-nearest neighbor, naive Bayes, neural network, random forest, stochastic gradient descent, and support vector machine algorithms. RESULTS: Of the 1748 extracted radiomic features, 1393 showed good inter-observer agreement. With LASSO, 25 features were selected. Among the ML algorithms, the neural network showed the highest predictive performance on average (area under the curve (AUC) 0.822 ± 0.181). Of the best-calculated model, the one using clinical parameters, CMRI parameters, and selected radiomic features (model 7), the diagnostic performance was as follows: 0.965 AUC, 0.894 classification accuracy, 0.906 sensitivity, 0.883 specificity, 0.875 positive predictive value (PPV), and 0.912 negative predictive value (NPV). CONCLUSION: The radiomics-based ML models incorporating clinical and conventional MRI parameters are promising for predicting MACE occurrence in STEMI patients in the follow-up period. KEY POINTS: • Acute coronary occlusion results in variable changes at the cellular level ranging from myocyte swelling to myonecrosis depending on the duration of the ischemia and the metabolic state of the heart, which causes subtle heterogeneous signal changes that are imperceptible to the human eye with cardiac MRI. • Radiomics-based machine learning analysis of cardiac MR images is promising for risk prediction. • Combining MRI-derived parameters and clinical variables increases the accuracy of predictive models.

Primary hypophysitis: Experience of a Single Tertiary Center.

PURPOSE: The authors review the clinical outcomes of patients with primary hypophysitis (PH). METHODS: Patients with PH who were followed up between 2007 and 2018 at our clinic were evaluated. Clinical, endocrinologic, pathologic, radiologic findings and treatment modalities were assessed. RESULTS: Seventeen patients with PH were assessed. The median follow-up was 24 (range, 6-84) months. Histologic confirmation was available in 8 patients (6 lymphocytic hypophysitis, 1 lymphocytic-granulomatous hypophysitis, 1 xanthomatous hypophysitis). None of the cases were diagnosed after pregnancy. Two patients had an autoimmune disease. The most commonly seen symptom was headache. The most common anterior pituitary deficiencies were hypocortisolemia and hypothyroidism. The radiologic findings of the patients at the time of diagnosis revealed various results including space-occupying lesion (41.2%), loss of posterior hypophysis bright spot (47.1%), pituitary stalk thickening (41.2%), uniform contrast enhancement (17.6%), partially empty sella (11.8%), optic chiasm compression (11.8%). The most frequent initial treatment modality was observation. Ten patients who were followed up conservatively had no endocrinologic deterioration; additional treatment was not needed in 8 of these 10 patients. The second most frequent initial treatment modality was pituitary surgery. Five patients received steroid treatment. We found serious adverse effects during steroid treatment in 3 of 5 (60%) patients; unilateral avascular necrosis of the femoral head (n=2), diabetes mellitus(n=1). CONCLUSION: Correctly diagnosing PH and giving appropriate treatment is challenging. It is unclear whether active treatment with steroids improves clinical outcomes. The serious adverse effects of steroids are also taken into account. Observation, surgery and/or radiotherapy can be appropriate treatment modalities for selected patients.

Radiogenomics of lower-grade gliomas: machine learning-based MRI texture analysis for predicting 1p/19q codeletion status.

OBJECTIVE: To evaluate the potential value of the machine learning (ML)-based MRI texture analysis for predicting 1p/19q codeletion status of lower-grade gliomas (LGG), using various state-of-the-art ML algorithms. MATERIALS AND METHODS: For this retrospective study, 107 patients with LGG were included from a public database. Texture features were extracted from conventional T2-weighted and contrast-enhanced T1-weighted MRI images, using LIFEx software. Training and unseen validation splits were created using stratified 10-fold cross-validation technique along with minority over-sampling. Dimension reduction was done using collinearity analysis and feature selection (ReliefF). Classifications were done using adaptive boosting, k-nearest neighbours, naive Bayes, neural network, random forest, stochastic gradient descent, and support vector machine. Friedman test and pairwise post hoc analyses were used for comparison of classification performances based on the area under the curve (AUC). RESULTS: Overall, the predictive performance of the ML algorithms were statistically significantly different, χ2(6) = 26.7, p < 0.001. There was no statistically significant difference among the performance of the neural network, naive Bayes, support vector machine, random forest, and stochastic gradient descent, adjusted p > 0.05. The mean AUC and accuracy values of these five algorithms ranged from 0.769 to 0.869 and from 80.1 to 84%, respectively. The neural network had the highest mean rank with mean AUC and accuracy values of 0.869 and 83.8%, respectively. CONCLUSIONS: The ML-based MRI texture analysis might be a promising non-invasive technique for predicting the 1p/19q codeletion status of LGGs. Using this technique along with various ML algorithms, more than four-fifths of the LGGs can be correctly classified. KEY POINTS: • More than four-fifths of the lower-grade gliomas can be correctly classified with machine learning-based MRI texture analysis. Satisfying classification outcomes are not limited to a single algorithm. • A few-slice-based volumetric segmentation technique would be a valid approach, providing satisfactory predictive textural information and avoiding excessive segmentation duration in clinical practice. • Feature selection is sensitive to different patient data set samples so that each sampling leads to the selection of different feature subsets, which needs to be considered in future works.

Radiomics of Renal Masses: Systematic Review of Reproducibility and Validation Strategies.

OBJECTIVE. The purpose of this study was to systematically review the radiomics literature on renal mass characterization in terms of reproducibility and validation strategies. MATERIALS AND METHODS. With use of PubMed and Google Scholar, a systematic literature search was performed to identify original research papers assessing the value of radiomics in characterization of renal masses. The data items were extracted on the basis of three main categories: baseline study characteristics, radiomic feature reproducibility strategies, and statistical model validation strategies. RESULTS. After screening and application of the eligibility criteria, a total of 41 papers were included in the study. Almost one-half of the papers (19 [46%]) presented at least one reproducibility analysis. Segmentation variability (18 [44%]) was the main theme of the analyses, outnumbering image acquisition or processing (3 [7%]). No single paper considered slice selection bias. The most commonly used statistical tool for analysis was intraclass correlation coefficient (14 of 19 [74%]), with no consensus on the threshold or cutoff values. Approximately one-half of the papers (22 [54%]) used at least one validation method, with a predominance of internal validation techniques (20 [49%]). The most frequently used internal validation technique was k-fold cross-validation (12 [29%]). Independent or external validation was used in only three papers (7%). CONCLUSION. Workflow characteristics described in the radiomics literature about renal mass characterization are heterogeneous. To bring radiomics from a mere research area to clinical use, the field needs many more papers that consider the reproducibility of radiomic features and include independent or external validation in their workflow.

Machine learning-based unenhanced CT texture analysis for predicting BAP1 mutation status of clear cell renal cell carcinomas.

BACKGROUND: BRCA1-associated protein 1 (BAP1) mutation is an unfavorable factor for overall survival in patients with clear cell renal cell carcinoma (ccRCC). Radiomics literature about BAP1 mutation lacks papers that consider the reliability of texture features in their workflow. PURPOSE: Using texture features with a high inter-observer agreement, we aimed to develop and internally validate a machine learning-based radiomic model for predicting the BAP1 mutation status of ccRCCs. MATERIAL AND METHODS: For this retrospective study, 65 ccRCCs were included from a public database. Texture features were extracted from unenhanced computed tomography (CT) images, using two-dimensional manual segmentation. Dimension reduction was done in three steps: (i) inter-observer agreement analysis; (ii) collinearity analysis; and (iii) feature selection. The machine learning classifier was random forest. The model was validated using 10-fold nested cross-validation. The reference standard was the BAP1 mutation status. RESULTS: Out of 744 features, 468 had an excellent inter-observer agreement. After the collinearity analysis, the number of features decreased to 17. Finally, the wrapper-based algorithm selected six features. Using selected features, the random forest correctly classified 84.6% of the labelled slices regarding BAP1 mutation status with an area under the receiver operating characteristic curve of 0.897. For predicting ccRCCs with BAP1 mutation, the sensitivity, specificity, and precision were 90.4%, 78.8%, and 81%, respectively. For predicting ccRCCs without BAP1 mutation, the sensitivity, specificity, and precision were 78.8%, 90.4%, and 89.1%, respectively. CONCLUSION: Machine learning-based unenhanced CT texture analysis might be a potential method for predicting the BAP1 mutation status of ccRCCs.

Radiomics with artificial intelligence: a practical guide for beginners.

Radiomics is a relatively new word for the field of radiology, meaning the extraction of a high number of quantitative features from medical images. Artificial intelligence (AI) is broadly a set of advanced computational algorithms that basically learn the patterns in the data provided to make predictions on unseen data sets. Radiomics can be coupled with AI because of its better capability of handling a massive amount of data compared with the traditional statistical methods. Together, the primary purpose of these fields is to extract and analyze as much and meaningful hidden quantitative data as possible to be used in decision support. Nowadays, both radiomics and AI have been getting attention for their remarkable success in various radiological tasks, which has been met with anxiety by most of the radiologists due to the fear of replacement by intelligent machines. Considering ever-developing advances in computational power and availability of large data sets, the marriage of humans and machines in future clinical practice seems inevitable. Therefore, regardless of their feelings, the radiologists should be familiar with these concepts. Our goal in this paper was three-fold: first, to familiarize radiologists with the radiomics and AI; second, to encourage the radiologists to get involved in these ever-developing fields; and, third, to provide a set of recommendations for good practice in design and assessment of future works.

Prognostic value of ADC measurements in predicting overall survival in patients undergoing 90Y radioembolization for colorectal cancer liver metastases.

AIM: To assess the ability of diffusion-weighted imaging (DWI) in predicting the overall survival in patients who underwent Yttrium 90 radioembolization (90Y-RE) for colorectal liver metastases (CLM) with other well-established clinical and imaging parameters by comparing the pre- and post-treatment apparent diffusion coefficient (ADC) values of the lesions. METHODS: A total of 81 metastatic lesions of 27 consecutive patients who underwent DWI before and after the 90Y-RE session were enrolled in the study. ADC values were calculated from the entire (ADCe) and peripheral (ADCp) tumor on pre- and post-treatment DWI, and any relative increase in ADC >0% accepted as a functional imaging response. The impact of functional imaging response in addition to other well-known parameters including Response Evaluation Criteria in Solid Tumors (RECIST), hepatic tumor burden, Eastern Cooperative Oncology Group performance status (ECOG-PS) and the presence of extrahepatic metastases in predicting overall survival (OS) was assessed using Kaplan-Meier curves and Cox-regression analyses. RESULTS: The median OS of the patients was 10 months (range, 6-20 months) while the median OS of the responders being significantly longer than the non-responders for ADCe and ADCp (median 11 vs 7 months, P = 0.003; median 12 vs. 7 months, P < 0.0001, respectively). The RECIST score was also significantly affected the OS (progressive or stable disease median 8 months vs. partial response 15 indent months, P = 0.019). The other parameters including hepatic tumor burden, gender, ECOG score, the involvement of the liver lobes, and the presence of extrahepatic metastases were not associated with the OS. In multivariate analysis, only ADCp remained as an independent predictor of OS (P = 0.003, HR = 19.878). CONCLUSION: Any increase in relative ADCp or ADCe values after Y90-RE treatment was associated with longer OS in CLM patients, and DWI seems to be valuable imaging biomarker in predicting OS in CLM patients during the early post-interventional period after 90Y-RE.

Reliability of Single-Slice-Based 2D CT Texture Analysis of Renal Masses: Influence of Intra- and Interobserver Manual Segmentation Variability on Radiomic Feature Reproducibility.

OBJECTIVE. The objective of our study was to investigate the potential influence of intra- and interobserver manual segmentation variability on the reliability of single-slice-based 2D CT texture analysis of renal masses. MATERIALS AND METHODS. For this retrospective study, 30 patients with clear cell renal cell carcinoma were included from a public database. For intra- and interobserver analyses, three radiologists with varying degrees of experience segmented the tumors from unenhanced CT and corticomedullary phase contrast-enhanced CT (CECT) in different sessions. Each radiologist was blind to the image slices selected by other radiologists and him- or herself in the previous session. A total of 744 texture features were extracted from original, filtered, and transformed images. The intraclass correlation coefficient was used for reliability analysis. RESULTS. In the intraobserver analysis, the rates of features with good to excellent reliability were 84.4-92.2% for unenhanced CT and 85.5-93.1% for CECT. Considering the mean rates of unenhanced CT and CECT, having high experience resulted in better reliability rates in terms of the intraobserver analysis. In the interobserver analysis, the rates were 76.7% for unenhanced CT and 84.9% for CECT. The gray-level cooccurrence matrix and first-order feature groups yielded higher good to excellent reliability rates on both unenhanced CT and CECT. Filtered and transformed images resulted in more features with good to excellent reliability than the original images did on both unenhanced CT and CECT. CONCLUSION. Single-slice-based 2D CT texture analysis of renal masses is sensitive to intra- and interobserver manual segmentation variability. Therefore, it may lead to nonreproducible results in radiomic analysis unless a reliability analysis is considered in the workflow.

Predictive Factors for Rathke's Cleft Cyst Consistency.

OBJECTIVE: Rathke's cleft cysts (RCCs) may have various anatomic, clinical, and radiologic characteristics, which may be related to their differences in texture or consistency. The purpose of the study was to investigate RCCs based on consistency. METHODS: We retrospectively reviewed 25 cases of patients with RCCs who underwent endoscopic endonasal transsphenoidal surgery between 2008 and 2018. Cases were divided into 3 types based on cyst consistency: fluid (serous) or type A (n = 4); semi-fluid (mucoid) or type B (n = 17); and non-fluid (caseous) or type C (n = 4). Demographic, clinical, radiologic, and surgical characteristics for each group were analyzed. RESULTS: All type A RCCs (100%) had visual impairment. The mean age (42.8 ± 13 years) and cyst volume (2442.5 ± 533.6 mm3) were higher in these patients. T1-weighted images were hypointense and T2-weighted images were hyperintense on magnetic resonance imaging. Type B RCCs were more frequently encountered (68%). Although headache was the most common (82.3%) symptom, endocrine disorders were also prevalent (52.9%). T1-weighted images were typically isointense or hyperintense on magnetic resonance imaging. Type C RCCs had the youngest patient population (30.3 ± 10.2 years) and T2-weighted images were predominantly hypointense in this group. CONCLUSIONS: The proposed novel consistency classification of RCCs will provide a practical tool for more accurately estimating the nature of the pathology, because each type has its own specific characteristics. Furthermore, the new classification of RCCs may aid in planning a consistency-specific surgery.

Unenhanced CT Texture Analysis of Clear Cell Renal Cell Carcinomas: A Machine Learning-Based Study for Predicting Histopathologic Nuclear Grade.

OBJECTIVE. The purpose of this study is to investigate the predictive performance of machine learning (ML)-based unenhanced CT texture analysis in distinguishing low (grades I and II) and high (grades III and IV) nuclear grade clear cell renal cell carcinomas (RCCs). MATERIALS AND METHODS. For this retrospective study, 81 patients with clear cell RCC (56 high and 25 low nuclear grade) were included from a public database. Using 2D manual segmentation, 744 texture features were extracted from unenhanced CT images. Dimension reduction was done in three consecutive steps: reproducibility analysis by two radiologists, collinearity analysis, and feature selection. Models were created using artificial neural network (ANN) and binary logistic regression, with and without synthetic minority oversampling technique (SMOTE), and were validated using 10-fold cross-validation. The reference standard was histopathologic nuclear grade (low vs high). RESULTS. Dimension reduction steps yielded five texture features for the ANN and six for the logistic regression algorithm. None of clinical variables was selected. ANN alone and ANN with SMOTE correctly classified 81.5% and 70.5%, respectively, of clear cell RCCs, with AUC values of 0.714 and 0.702, respectively. The logistic regression algorithm alone and with SMOTE correctly classified 75.3% and 62.5%, respectively, of the tumors, with AUC values of 0.656 and 0.666, respectively. The ANN performed better than the logistic regression (p < 0.05). No statistically significant difference was present between the model performances created with and without SMOTE (p > 0.05). CONCLUSION. ML-based unenhanced CT texture analysis using ANN can be a promising noninvasive method in predicting the nuclear grade of clear cell RCCs.

Preoperative evaluation of tumour consistency in pituitary macroadenomas: a machine learning-based histogram analysis on conventional T2-weighted MRI.

PURPOSE: To evaluate the potential value of machine learning (ML)-based histogram analysis (or first-order texture analysis) on T2-weighted magnetic resonance imaging (MRI) for predicting consistency of pituitary macroadenomas (PMA) and to compare it with that of signal intensity ratio (SIR) evaluation. METHODS: Fifty-five patients with 13 hard and 42 soft PMAs were included in this retrospective study. Histogram features were extracted from coronal T2-weighted original, filtered and transformed MRI images by manual segmentation. To achieve balanced classes (38 hard vs 42 soft), multiple samples were obtained from different slices of the PMAs with hard consistency. Dimension reduction was done with reproducibility analysis, collinearity analysis and feature selection. ML classifier was artificial neural network (ANN). Reference standard for the classifications was based on surgical and histopathological findings. Predictive performance of histogram analysis was compared with that of SIR evaluation. The main metric for comparisons was the area under the receiver operating characteristic curve (AUC). RESULTS: Only 137 of 162 features had excellent reproducibility. Collinearity analysis yielded 20 features. Feature selection algorithm provided six texture features. For histogram analysis, the ANN correctly classified 72.5% of the PMAs regarding consistency with an AUC value of 0.710. For SIR evaluation, accuracy and AUC values were 74.5% and 0.551, respectively. Considering AUC values, ML-based histogram analysis performed better than SIR evaluation (z = 2.312, p = 0.021). CONCLUSION: ML-based T2-weighted MRI histogram analysis might be a useful technique in predicting the consistency of PMAs, with a better predictive performance than that of SIR evaluation.

Added Value of Dynamic Contrast-Enhanced Magnetic Resonance Imaging in Predicting Response to Somatostatin Analogs in Acromegaly Patients.

AIM: To investigate the added value of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) sequences in predicting somatostatin analog (SSA) responses in patients with acromegaly. MATERIAL AND METHODS: This study included 55 active acromegaly patients with macroadenoma. Mean and maximum signal intensities were measured using region of interests in T2-weighted (T2W) and DCE-MRI sequences. Semi-quantitative values indicating relative signal intensity ratios and contrast-enhanced kinetics were obtained. Bivariate and multivariate analyses were used to determine whether the pathological granulation pattern of adenomas (dense versus others) was associated with patients' demographic variables and semi-quantitative MRI parameters. RESULTS: Three parameters formed the logistic model, x2(3)=23.278, p < 0.0001: age (odds ratio [OR]=1.08), hypointensity of adenomas in T2W images (OR=15.45), and high maximum enhancement ratio in the second interval (ER2max) values (OR=2195.74). The overall accuracy of this model was 85.45% with an area under the curve of 0.880. Sensitivity, specificity, positive predictive, and negative predictive values of the model were 68.75%, 92.31%, 78.58%, and 87.8%, respectively. CONCLUSION: In patients with newly diagnosed acromegaly, the model created based on the relative T2W signal intensity, patient's age, and ER2 < submax parameter from DCE-MRI sequences might be used to more accurately predict SSA responses.

Influence of segmentation margin on machine learning-based high-dimensional quantitative CT texture analysis: a reproducibility study on renal clear cell carcinomas.

OBJECTIVE: To determine the possible influence of segmentation margin on each step (feature reproducibility, selection, and classification) of the machine learning (ML)-based high-dimensional quantitative computed tomography (CT) texture analysis (qCT-TA) of renal clear cell carcinomas (RcCCs). MATERIALS AND METHODS: For this retrospective study, 47 patients with RcCC were included from a public database. Two segmentations were obtained by two radiologists for each tumour: (i) contour-focused and (ii) margin shrinkage of 2 mm. Texture features were extracted from original, filtered, and transformed CT images. Feature selection was done using a correlation-based algorithm. The ML classifier was k-nearest neighbours. Classifications were performed with and without using synthetic minority over-sampling technique. Reference standard was nuclear grade (low versus high). Intraclass correlation coefficient (ICC), Pearson's correlation coefficient, Wilcoxon signed-ranks test, and McNemar's test were used in the analysis. RESULTS: The segmentation with margin shrinkage of 2 mm (772 of 828; 93.2%) yielded more texture features with excellent reproducibility (ICC ≥ 0.9) than contour-focused segmentation (714 of 828; 86.2%), p < 0.0001. The feature selection algorithms resulted in different feature subsets for two segmentation datasets with only one common feature. All ML-based models based on contour-focused segmentation (area under the curve [AUC] range, 0.865-0.984) performed better than those with margin shrinkage of 2 mm (AUC range, 0.745-0.887), p < 0.05. CONCLUSIONS: Each step of the ML-based high-dimensional qCT-TA was susceptible to a slight change of 2 mm in segmentation margin. Despite yielding fewer features with excellent reproducibility, use of the contour-focused segmentation provided better classification performance for distinguishing nuclear grade. KEY POINTS: • Each step of a machine learning (ML)-based high-dimensional quantitative computed tomography texture analysis (qCT-TA) is sensitive to even a slight change of 2 mm in segmentation margin. • Despite yielding fewer texture features with excellent reproducibility, performing the segmentation focusing on the outermost boundary of the tumours provides better classification performance in ML-based qCT-TA of renal clear cell carcinomas for distinguishing nuclear grade. • Findings of an ML-based high-dimensional qCT-TA may not be reproducible in clinical practice even using the same feature selection algorithm and ML classifier unless the possible influence of the segmentation margin is considered.

Increased vein wall thickness in Behçet disease.

OBJECTIVE: Lower extremity (LE) deep venous thrombosis (DVT) is the main feature of vascular involvement in Behçet disease (BD). We thought that vein wall thickness (VWT) could be a surrogate marker for venous inflammation and hence predict future vascular involvement. We assessed VWT in proximal LE veins in BD patients without DVT, BD patients with DVT, and healthy controls in a formal, masked protocol. METHODS: We studied 50 (43 male and 7 female) BD patients with LE DVT (group 1), 50 (43 male and 7 female) BD patients without any vascular involvement (group 2), and 50 (43 male and 7 female) age- and sex-matched apparently healthy controls (group 3). Two radiologists blinded to the diagnosis of BD used ultrasound to measure VWT of common femoral vein, femoral vein, and great saphenous vein in both legs. Interobserver reliability was assessed using the intraclass correlation coefficient and Bland-Altman plots. RESULTS: There was good agreement between the two observers. The mean VWT was significantly increased in both BD patients with LE DVT and those without apparent vascular involvement compared with the healthy controls, whereas those with LE DVT had the highest VWT. CONCLUSIONS: VWT of proximal deep and superficial LE veins is increased among the BD patients without any clinical and radiologic vascular involvement. This information, after prospective work, might be useful in management and elucidating disease mechanisms in vascular BD.

Radiogenomics in Clear Cell Renal Cell Carcinoma: Machine Learning-Based High-Dimensional Quantitative CT Texture Analysis in Predicting PBRM1 Mutation Status.

OBJECTIVE: The purpose of this study is to evaluate the potential value of machine learning (ML)-based high-dimensional quantitative CT texture analysis in predicting the mutation status of the gene encoding the protein polybromo-1 (PBRM1) in patients with clear cell renal cell carcinoma (RCC). MATERIALS AND METHODS: In this retrospective study, 45 patients with clear cell RCC (29 without the PBRM1 mutation and 16 with the PBRM1 mutation) were identified in The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma database. To create stable ML models and balanced classes, the data were augmented to a total of 161 labeled segmentations (87 without the PBRM1 mutation and 74 with the PBRM1 mutation) by obtaining three to five different samples per patient. Texture features were extracted from corticomedullary phase contrast-enhanced CT images with the use of an open-source software package for the extraction of radiomic data from medical images. Reproducibility analysis (intraclass correlation) was performed by two radiologists. Attribute selection and model optimization were done using a wrapper-based classifier-specific algorithm with nested cross-validation. ML classifiers were an artificial neural network (ANN) algorithm and a random forest (RF) algorithm. The models were validated using 10-fold cross-validation. The reference standard was the PBRM1 mutation status. The main performance metric was the AUC value. RESULTS: Of 828 extracted texture features, 759 had excellent reproducibility. Using 10 selected features, the ANN algorithm correctly classified 88.2% (142 of 161) of the clear cell RCCs in terms of PBRM1 mutation status (AUC value, 0.925). Using five selected features, the RF algorithm correctly classified 95.0% (153 of 161) of the clear cell RCCs (AUC value, 0.987). Overall, the RF algorithm performed better than the ANN algorithm (z score = -2.677; p = 0.007). CONCLUSION: ML-based high-dimensional quantitative CT texture analysis might be a feasible and potential method for predicting PBRM1 mutation status in patients with clear cell RCC.

Predicting response to somatostatin analogues in acromegaly: machine learning-based high-dimensional quantitative texture analysis on T2-weighted MRI.

OBJECTIVE: To investigate the value of machine learning (ML)-based high-dimensional quantitative texture analysis (qTA) on T2-weighted magnetic resonance imaging (MRI) in predicting response to somatostatin analogues (SA) in acromegaly patients with growth hormone (GH)-secreting pituitary macroadenoma, and to compare the qTA with quantitative and qualitative T2-weighted relative signal intensity (rSI) and immunohistochemical evaluation. METHODS: Forty-seven patients (24 responsive; 23 resistant patients to SA) were eligible for this retrospective study. Coronal T2-weighted images were used for qTA and rSI evaluation. The immunohistochemical evaluation was based on the granulation pattern of the adenomas. Dimension reduction was carried out by reproducibility analysis and wrapper-based algorithm. ML classifiers were k-nearest neighbours (k-NN) and C4.5 algorithm. The reference standard was the biochemical response status. Predictive performance of qTA was compared with those of the quantitative and qualitative rSI and immunohistochemical evaluation. RESULTS: Five hundred thirty-five out of 828 texture features had excellent reproducibility. For the qTA, k-NN correctly classified 85.1% of the macroadenomas regarding response to SAs with an area under the receiver operating characteristic curve (AUC-ROC) of 0.847. The accuracy and AUC-ROC ranges of the other methods were 57.4-70.2% and 0.575-0.704, respectively. Differences in predictive performance between qTA-based classification and the other methods were significant (p < 0.05). CONCLUSIONS: The ML-based qTA of T2-weighted MRI is a potential non-invasive tool in predicting response to SAs in patients with acromegaly and GH-secreting pituitary macroadenoma. The method performed better than the qualitative and quantitative rSI and immunohistochemical evaluation. KEY POINTS: • Machine learning-based texture analysis of T2-weighted MRI can correctly classify response to somatostatin analogues in more than four fifths of the patients. • Machine learning-based texture analysis performs better than qualitative and quantitative evaluation of relative T2 signal intensity and immunohistochemical evaluation. • About one third of the texture features may not be excellently reproducible, indicating that a reliability analysis is necessary before model development.

Shear Wave Elastography of the Lumbar Multifidus Muscle in Patients With Unilateral Lumbar Disk Herniation.

OBJECTIVES: To assess lumbar multifidus muscle stiffness in patients with unilateral lumbar disk herniation (LDH) causing nerve root compression using shear wave elastography (SWE). METHODS: Thirty-three patients with unilateral subarticular LDH (L3-L4, L4-L5, and L5-S1) causing nerve root compression, diagnosed by magnetic resonance imaging, were enrolled in the study. Exclusion criteria were bilateral or multilevel LDH confirmed on magnetic resonance imaging, bilateral leg symptoms, and patients with a history of any spinal operation, malignancy, trauma, infection, spondylolisthesis, severe lateral recess stenosis, spinal canal stenosis, and substantial comorbidities. Two observers separately evaluated the multifidus muscle using SWE. Shear wave elastographic examinations of the muscle were performed slightly below the herniation using the spinous process of the vertebra as a landmark. The stiffness of the muscle between affected and normal sides was compared. Moreover, the correlation between the stiffness and duration of the symptoms and the correlation between the stiffness and severity of the nerve compression were also calculated. RESULTS: The mean stiffness values of the multifidus muscle on the affected side (mean ± SD: observer 1, 14.08 ± 3.57 kPa; observer 2, 13.70 ± 4.05 kPa) were significantly lower compared to the contralateral side (observer 1, 18.81 ± 3.95 kPa; observer 2, 18.28 ± 4.12 kPa; P < .001). The muscle stiffness had a moderate negative correlation with the duration of the symptoms and the severity of the nerve compression (observer 1, r = -0.535; observer 2, r = -0.458; P < .001). CONCLUSIONS: The multifidus muscle on the ipsilateral side of the LDH showed reduced stiffness values, and stiffness values were negatively correlated with the disease duration and severity of the nerve compression. Further studies might reveal the potential role of SWE of the multifidus muscle in determining clinical outcomes and assessing effectiveness treatment in patients with LDH.

Assessment of the common carotid artery wall stiffness by Shear Wave Elastography in Behcet's disease.

AIM: To evaluate endothelial dysfunction and subclinical atherosclerosis in Behcet's disease (BD) by measuring the common carotid artery (CCA) wall stiffness and carotid intima-media thickness (CIMT). MATERIALS AND METHODS: We prospectively evaluated CIMT and the CCA wall stiffness of 34 BD patients and 28 age/sex-matched controls. CIMT measurements were performed from the posterior wall of the carotid artery approximately 10 mm proximal to the initiation of the carotid bulb using B-mode ultrasound. The stiffness of the CCA was measured from the superficial wall of the CCA using shear wave elastography (SWE). SWE measurements were recorded as shear wave velocity (SWV) using m/s as a unit. RESULTS: The mean right (0.5±0.11 mm) and left (0.5±0.14 mm) CIMT of the patients were significantly higher compared to the mean right (0.41±0.07 mm) and left (0.41±0.11 mm) CIMT of the healthy controls (p=0.001 and p= 0.003 respectively). The mean right (3.72±0.94 m/s) and left (3.57±0.72 m/s) CCA wall stiffness of the patients were significantly higher compared to the mean right (2.42±0.49 m/s) and left (2.56±0.49 m/s) CCA wall stiffness of the controls (p<0.001 for both). CONCLUSIONS: SWE seems to be a promising modality to evaluate endothelial dysfunction in BD by interpreting the arterial stiffness, and SWE might be an important adjunct to clinical and laboratory findings, and imaging modalities to assess cardiovascular risk in BD. Moreover, SWE evaluation of the arterial stiffness might assist us to understand pathophysiological aspects of BD.

Quantitative Assessment of Thyroid, Submandibular, and Parotid Glands Elasticity With Shear-Wave Elastography in Children.

Tissue elasticity is becoming a more commonly used parameter in evaluation of parenchyma in inflammatory diseases. Considering the changes in the thyroid and salivary glands with adolescence, determination of mean elasticity ranges with a function of age is necessary to apply ultrasound elastography more widely in the pediatric population.The thyroid, submandibular, and parotid glands of 127 healthy volunteers (66 males, 61 females; mean age = 10.3 ± 3.9 years; range = 3-17 years) were evaluated with shear-wave elastography.The mean elasticity values for the thyroid, submandibular, and parotid glands were 14.6 ± 3.3, 11.8 ± 2.2, and 11.8 ± 2.6 kPa, respectively. There was a significant positive correlation between age and elasticity of the thyroid, submandibular, and parotid glands. There was a significant correlation between age and elasticity value of the thyroid gland adjusted for weight and height.This study provided the baseline quantitative elasticity measures of thyroid, submandibular, and parotid glands, which would be a reference for upcoming studies. In addition, an increase in elasticity value in thyroid gland as a function of age independent of change in weight and height was demonstrated.