Can the Combination of Magnetic Resonance Imaging, Neutrophil-to-Lymphocyte Ratio and Platelet-to-Lymphocyte Ratio Predict the Mass Origin in Ovarian Masses?

Objective: Evaluate the effectiveness of magnetic resonance imaging (MRI), blood parameters, and tumor markers to determine the role of objective criteria in distinguishing malignant, borderline, and benign masses and to minimize unnecessary surgical interventions by reducing interpretation differences. Methods: The histopathological and clinical-laboratory results of the patients who underwent surgery for the initial diagnosis and whose ovarian masses were confirmed were retrospectively reviewed. Between groups, age, cancer antigen 125, mean platelet volume (MPV), neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), the presence of ascites, the ovarian-adnexal reporting and data system MRI scores, mass characteristics, and lymphocyte count were compared. Results: The study comprised a total of 191 patients. These patients were categorized into three groups: Benign (n=113), borderline (n=26), and malignant (n=52). No noteworthy correlation was detected between the unilocular or multilocular nature of solid, cystic, or mixed masses and the rates of NLR, PLR, or MPV. However, a notable correlation was identified between NLR and the presence of acidity (p=0.003). In ovarian cancer patients, there was no significant difference in NLR and MPV between malignant epithelial and malignant sex cord-stromal types (p>0.05), whereas a significant difference emerged in the PLR ratio (p=0.013). Conclusion: In ovarian masses with malignant potential, laboratory parameters such as NLR and PLR can guide the diagnosis process. In the future, various studies such as the development of different tests, markers, and imaging methods, the use of blood tests such as NLR, PLR, and MPV in cancer diagnosis will be possible. The results of these studies may contribute to the development of new methods for the diagnosis of ovarian cancer and the improvement of treatment protocols.

The effect of sarcopenia and sarcopenic obesity on survival in gastric cancer.

BACKGROUND: Sarcopenic obesity arises from increased muscle catabolism triggered by inflammation and inactivity. Its significance lies in its role in contributing to morbidity and mortality in gastric cancer. This study aims to explore the potential correlation between sarcopenia, sarcopenic obesity, and gastric cancer, as well as their effect on survival. MATERIALS AND METHODS: This retrospective study included 162 patients aged ≥ 18 years who were diagnosed with stomach cancer. Patient age, gender, diagnostic laboratory results, and cancer characteristics were documented. Sarcopenia was assessed using the skeletal muscle index (SMI) (cm2/m2), calculated by measuring muscle mass area from a cross-sectional image at the L3 vertebra level of computed tomography (CT). RESULTS: Among the 162 patients, 52.5% exhibited sarcopenia (with cut-off limits of 52.4 cm2/m2 for males and 38.5 cm2/m2 for females), and 4.9% showed sarcopenic obesity. Average skeletal muscle area (SMA) was 146.8 cm2; SMI was 50.6 cm2/m2 in men and 96.9 cm2 and 40.6 cm2/m2 in women, respectively. Sarcopenia significantly reduced mean survival (p = 0.033). There was no association between sarcopenic obesity and mortality (p > 0.05), but mortality was higher in sarcopenic obesity patients (p = 0.041). Patient weight acted as a protective factor against mortality, supporting the obesity paradox. Tumor characteristics, metabolic parameters, and concurrent comorbidities did not significantly impact sarcopenia or mortality. CONCLUSION: Sarcopenia is more prevalent in the elderly population and is linked to increased mortality in gastric cancer patients. Paradoxically, higher body mass index (BMI) was associated with improved survival. Computed tomography offers a practical and reliable method for measuring muscle mass and distinguishing these distinctions. TRIAL REGISTRATION: This study was approved by Istanbul Training and Research Hospital Clinical Research Ethics Committee of the University of Health Sciences (29.05.2020/2383).

The role of endobronchial ultrasonography elastography in the diagnosis of hilar and mediastinal lymph nodes.

BACKGROUND: Endobronchial ultrasonography (EBUS) is a minimally invasive diagnostic tool in the diagnosis of mediastinal lymph nodes (LNs) and has sonographic features. We aimed to investigate the diagnostic accuracy of EBUS elastography, which evaluates tissue compressibility integrated into EBUS, on malignant vs. benign mediastinal-hilar LNs. METHODS: A single-center, prospective study was conducted at the University of Health Sciences Yedikule Chest Diseases and Thoracic Surgery Training and Research Hospital between 01/10/2019 and 15/11/2019. The features of 219 LNs evaluated by thoracic computed tomography (CT), positron emission tomography (PET)/CT, EBUS sonography and EBUS elastography were recorded. The LNs sampled by EBUS-guided fine needle aspiration were classified according to EBUS elastography color distribution findings as follows: type 1, predominantly nonblue (green, yellow, and red); type 2, part blue, part nonblue; type 3, predominantly blue. The strain ratio (SR) was calculated based on normal tissue with the relevant region. RESULTS: The average age of 131 patients included in the study was 55.86 ± 13 years, 76 (58%) were male. Two hundred and nineteen lymph nodes were sampled from different stations. Pathological diagnosis of 75 (34.2%) LNs was malignant, the rest was benign. When EBUS B-mode findings and pathological results were compared, sensitivity was 65.33%, specificity 63.19%, positive predictive value (PPV) 48%, negative predictive value (NPV) 77.8%, and diagnostic yield (DY) 64%. When the pathological diagnoses and EBUS elastography findings were compared, while type 1 LNs were considered to be benign and type 3 LNs malignant, sensitivity 94.12%, specificity 86.54%, PPV 82.1%, NPV 95.7%, and DY 89.5%. SR of malignant LNs was significantly higher than benign LNs (p < 0.001). When the classification according to color scale and SR were compared, no difference was found in DY (p = 0.155). DISCUSSION: The diagnostic accuracy of EBUS elastography is high enough to distinguish malignant LN from benign ones with the SR option. When compared with EBUS-B mode sonographic findings, it was found to have a higher diagnostic yield.

REliability of consensus-based segMentatIoN in raDiomic feature reproducibility (REMIND): A word of caution.

OBJECTIVE: To evaluate the reliability of consensus-based segmentation in terms of reproducibility of radiomic features. METHODS: In this retrospective study, three tumor data sets were investigated: breast cancer (n = 30), renal cell carcinoma (n = 30), and pituitary macroadenoma (n = 30). MRI was utilized for breast and pituitary data sets, while CT was used for renal data set. 12 readers participated in the segmentation process. Consensus segmentation was created by making corrections on a previous region or volume of interest. Four experiments were designed to evaluate the reproducibility of radiomic features. Reliability was assessed with intraclass correlation coefficient (ICC) with two cut-off values: 0.75 and 0.9. RESULTS: Considering the lower bound of the 95% confidence interval and the ICC threshold of 0.90, at least 61% of the radiomic features were not reproducible in the inter-consensus analysis. In the susceptibility experiment, at least half (54%) became non-reproducible when the first reader is replaced with a different reader. In the intra-consensus analysis, at least about one-third (32%) were non-reproducible when the same second reader segmented the image over the same first reader two weeks later. Compared to inter-reader analysis based on independent single readers, the inter-consensus analysis did not statistically significantly improve the rates of reproducible features in all data sets and analyses. CONCLUSIONS: Despite the positive connotation of the word "consensus", it is essential to REMIND that consensus-based segmentation has significant reproducibility issues. Therefore, the usage of consensus-based segmentation alone should be avoided unless a reliability analysis is performed, even if it is not practical in clinical settings.

Transparency in Artificial Intelligence Research: a Systematic Review of Availability Items Related to Open Science in Radiology and Nuclear Medicine.

RATIONALE AND OBJECTIVES: Reproducibility of artificial intelligence (AI) research has become a growing concern. One of the fundamental reasons is the lack of transparency in data, code, and model. In this work, we aimed to systematically review the radiology and nuclear medicine papers on AI in terms of transparency and open science. MATERIALS AND METHODS: A systematic literature search was performed in PubMed to identify original research studies on AI. The search was restricted to studies published in Q1 and Q2 journals that are also indexed on the Web of Science. A random sampling of the literature was performed. Besides six baseline study characteristics, a total of five availability items were evaluated. Two groups of independent readers including eight readers participated in the study. Inter-rater agreement was analyzed. Disagreements were resolved with consensus. RESULTS: Following eligibility criteria, we included a final set of 194 papers. The raw data was available in about one-fifth of the papers (34/194; 18%). However, the authors made their private data available only in one paper (1/161; 1%). About one-tenth of the papers made their pre-modeling (25/194; 13%), modeling (28/194; 14%), or post-modeling files (15/194; 8%) available. Most of the papers (189/194; 97%) did not attempt to create a ready-to-use system for real-world usage. Data origin, use of deep learning, and external validation had statistically significantly different distributions. The use of private data alone was negatively associated with the availability of at least one item (p<0.001). CONCLUSION: Overall rates of availability for items were poor, leaving room for substantial improvement.

Radiomics of locally advanced rectal cancer: machine learning-based prediction of response to neoadjuvant chemoradiotherapy using pre-treatment sagittal T2-weighted MRI.

PURPOSE: Variable response to neoadjuvant chemoradiotherapy (nCRT) is observed among individuals with locally advanced rectal cancer (LARC), having a significant impact on patient management. In this work, we aimed to investigate the potential value of machine learning (ML)-based magnetic resonance imaging (MRI) radiomics in predicting therapeutic response to nCRT in patients with LARC. MATERIALS AND METHODS: Seventy-six patients with LARC were included in this retrospective study. Radiomic features were extracted from pre-treatment sagittal T2-weighted MRI images, with 3D segmentation. Dimension reduction was performed with a reliability analysis, pair-wise correlation analysis, analysis of variance, recursive feature elimination, Kruskal-Wallis, and Relief methods. Models were created using four different algorithms. In addition to radiomic models, clinical only and different combined models were developed and compared. The reference standard was tumor regression grade (TRG) based on the Modified Ryan Scheme (TRG 0 vs TRG 1-3). Models were compared based on net reclassification index (NRI). Clinical utility was assessed with decision curve analysis (DCA). RESULTS: Number of features with excellent reliability is 106. The best result was achieved with radiomic only model using eight features. The area under the curve (AUC), accuracy, sensitivity, and specificity for validation were 0.753 (standard deviation [SD], 0.082), 81.1%, 83.8%, and 75.0%; for testing, 0.705 (SD, 0.145), 73.9%, 81.2%, and 57.1%, respectively. Based on the clinical only model as reference, NRI for radiomic only model was the best. DCA also showed better clinical utility for radiomic only model. CONCLUSIONS: ML-based T2-weighted MRI radiomics might have a potential in predicting response to nCRT in patients with LARC.

Could arterial stiffness be early reversible target organ damage test in childhood hypertension?

OBJECTIVE: The recommended treatment for hypertension (HTN) in children has been revised recently. This study aimed to present the changes in target organ damage (TOD) and arterial stiffness parameters after treatment in children with primary HTN who were managed in accordance with the 2016 European Society of Hypertension Guidelines. METHODS: Patients with primary HTN included in this study were newly diagnosed, untreated, and were followed-up for a minimum of 6 months. HTN was confirmed by 24-h ambulatory blood pressure monitoring (ABPM). All patients underwent the following assessments: anthropometrical measurements of body mass index (BMI), carotid intima-media thickness (cIMT), left ventricular mass index (LVMI), plasma creatinine, urea, electrolytes, uric acid, fasting plasma glucose, blood lipids, urinalysis, urine culture, and first morning urine albumin tocreatinine ratio. The ABPM device performed measurements such as central blood pressure (cBP) and pulse wave velocity (PWV). RESULTS: Thirty-two of 104 patients were enrolled. Seventeen patients were male, and 53% were obese. Compared with pretreatment, creatinine, urea, systolic BP (SBP), diastolic BP (DBP), systolic load, diastolic load, central SBP (cSBP), cSBP z score, cDBP, and PWV z score decreased, whereas LVMI and BMI z scores were unchanged. CONCLUSION: After BP improvement, while LVMI did not regress, the cSBP, cSBP z, and PWV z score values, which are markers of arterial stiffness, regressed. This supports the corrective effect of BP control on the cardiovascular system even in a short-term follow-up. Further longitudinal studies are needed for the assessment of BP control on arterial stiffness in childhood.

Transbronchial cryobiopsy for diagnosing parenchymal lung diseases: real-life experience from a tertiary referral center.

BACKGROUND AND OBJECTIVES: Transbronchial cryobiopsy (cryo-TBB) is increasingly being used in the diagnosis of diffuse parenchymal lung diseases (DPLD). Varying diagnostic success and complication rates have been reported. Herein we report our experience with cryo-TBB, focusing on diagnostic yield, factors affecting diagnosis, and safety. METHODS: This retrospective study was conducted in a tertiary referral chest diseases hospital. Data regarding the patients, procedures, complication rates, diagnostic yield, and the final diagnosis made by a multidisciplinary committee at all diagnosis stages were evaluated. RESULTS: We recruited 147 patients with suspected DPLD. The definitive diagnosis was made pathologically in 98 of 147 patients (66.6%) and using a multidisciplinary approach in 109 of 147 (74.1%) cases. The number of samples had a significant effect on diagnostic success. Histopathologic diagnostic yield and diagnostic yield with a multidisciplinary committee after a single biopsy were 50%, and histopathological diagnostic yield and diagnostic yield with multidisciplinary committee increased to 71.4% and 85.7%, respectively, with a second biopsy (p = 0.034). The incidence of mild-to-moderate hemorrhage was 31.9%; no severe hemorrhage occurred. Pneumothorax rate was 15.6%, and the mortality rate was 0.68%. CONCLUSIONS: Cryo-TBB has sufficient diagnostic yield in the context of a multidisciplinary diagnosis with acceptable complication rates. Performing at least 2 biopsies and from at least 2 segments increases diagnostic success.

18F-FDG PET/CT in Hyalinized Cholecystitis.

ABSTRACT: Hyalinizing cholecystitis is a rare type of chronic cholecystitis. Moderate patchy transmural especially perivascular lymphoplasmacytic inflammatory cell infiltration is observed in the gallbladder wall. We present the 18F-FDG PET/CT and MRI findings of this rare subtype of chronic cholecystitis. Hyalinizing cholecystitis should be kept in mind in the differential diagnosis of gallbladder wall thickening with intense 18F-FDG uptake.

Tubular gastric adenocarcinoma: machine learning-based CT texture analysis for predicting lymphovascular and perineural invasion.

PURPOSE: Lymphovascular invasion (LVI) and perineural invasion (PNI) are associated with poor prognosis in gastric cancers. In this work, we aimed to investigate the potential role of computed tomography (CT) texture analysis in predicting LVI and PNI in patients with tubular gastric adenocarcinoma (GAC) using a machine learning (ML) approach. METHODS: Sixty-eight patients who underwent total gastrectomy with curative (R0) resection and D2-lymphadenectomy were included in this retrospective study. Texture features were extracted from the portal venous phase CT images. Dimension reduction was first done with a reproducibility analysis by two radiologists. Then, a feature selection algorithm was used to further reduce the high-dimensionality of the radiomic data. Training and test splits were created with 100 random samplings. ML-based classifications were done using adaptive boosting, k-nearest neighbors, Naive Bayes, neural network, random forest, stochastic gradient descent, support vector machine, and decision tree. Predictive performance of the ML algorithms was mainly evaluated using the mean area under the curve (AUC) metric. RESULTS: Among 271 texture features, 150 features had excellent reproducibility, which were included in the further feature selection process. Dimension reduction steps yielded five texture features for LVI and five for PNI. Considering all eight ML algorithms, mean AUC and accuracy ranges for predicting LVI were 0.777-0.894 and 76%-81.5%, respectively. For predicting PNI, mean AUC and accuracy ranges were 0.482-0.754 and 54%-68.2%, respectively. The best performances for predicting LVI and PNI were achieved with the random forest and Naive Bayes algorithms, respectively. CONCLUSION: ML-based CT texture analysis has a potential for predicting LVI and PNI of the tubular GACs. Overall, the method was more successful in predicting LVI than PNI.

Machine Learning in Radiomic Renal Mass Characterization: Fundamentals, Applications, Challenges, and Future Directions.

OBJECTIVE. The purpose of this study is to provide an overview of the traditional machine learning (ML)-based and deep learning-based radiomic approaches, with focus placed on renal mass characterization. CONCLUSION. ML currently has a very low barrier to entry into general medical practice because of the availability of many open-source, free, and easy-to-use toolboxes. Therefore, it should not be surprising to see its related applications in renal mass characterization. A wider picture of the previous works might be beneficial to move this field forward.

Computed tomography texture analysis in patients with gastric cancer: a quantitative imaging biomarker for preoperative evaluation before neoadjuvant chemotherapy treatment.

PURPOSE: The aim of the study is to explore the role of computed tomography texture analysis (CT-TA) for predicting clinical T and N stages and tumor grade before neoadjuvant chemotherapy treatment in gastric cancer (GC) patients during the preoperative period. MATERIALS AND METHODS: CT images of 114 patients with GC were included in this retrospective study. Following pre-processing steps, textural features were extracted using MaZda software in the portal venous phase. We evaluated and analyzed texture features of six principal categories for differentiating between T stages (T1,2 vs T3,4), N stages (N+ vs N-) and grades (low-intermediate vs. high). Classification was performed based on texture parameters with high model coefficients in linear discriminant analysis (LDA). RESULTS: Dimension-reduction steps yielded five textural features for T stage, three for N stage and two for tumor grade. The discriminatory capacities of T stage, N stage and tumor grade were 90.4%, 81.6% and 64.5%, respectively, when LDA algorithm was employed. CONCLUSION: CT-TA yields potentially useful imaging biomarkers for predicting the T and N stages of patients with GC and can be used for preoperative evaluation before neoadjuvant treatment planning.

Prediction of Benign and Malignant Solid Renal Masses: Machine Learning-Based CT Texture Analysis.

RATIONALE AND OBJECTIVES: This study aimed to investigate whether benign and malignant renal solid masses could be distinguished through machine learning (ML)-based computed tomography (CT) texture analysis. MATERIALS AND METHODS: Seventy-nine patients with 84 solid renal masses (21 benign; 63 malignant) from a single center were included in this retrospective study. Malignant masses included common renal cell carcinoma (RCC) subtypes: clear cell RCC, papillary cell RCC, and chromophobe RCC. Benign masses are represented by oncocytomas and fat-poor angiomyolipomas. Following preprocessing steps, a total of 271 texture features were extracted from unenhanced and contrast-enhanced CT images. Dimension reduction was done with a reliability analysis and then with a feature selection algorithm. A nested-approach was used for feature selection, model optimization, and validation. Eight ML algorithms were used for the classifications: decision tree, locally weighted learning, k-nearest neighbors, naive Bayes, logistic regression, support vector machine, neural network, and random forest. RESULTS: The number of features with good reproducibility was 198 for unenhanced CT and 244 for contrast-enhanced CT. Random forest algorithm demonstrated the best predictive performance using five selected contrast-enhanced CT texture features. The accuracy and area under the curve metrics were 90.5% and 0.915, respectively. Having eliminated the highly collinear features from the analysis, the accuracy and area under the curve values slightly increased to 91.7% and 0.916, respectively. CONCLUSION: ML-based contrast-enhanced CT texture analysis might be a potential method for distinguishing benign and malignant solid renal masses with satisfactory performance.

Schwannomas of Uncommon Peripheral Locations: Analysis of Imaging Findings of 21 Cases.

BACKGROUND: Schwannomas are benign slow-growing tumors most often associated with the cranial nerves. Schwannomas often originate from the eighth cranial nerve. They may also originate from the peripheral nervous system of the neck and extremities. However extracranial peripheral schwannomas are considered a rare entity. OBJECTIVES: The knowledge of rare localizations and typical imaging findings will lead to a successfulradiological diagnosis. Therefore, in this study, we present the clinical findings and MRI characteristics of schwannomas with a rare localization involving the peripheral, lower and upper extremity and intramuscular regions. MATERIALS AND METHODS: The hospital database was screened for patients with an extracranial soft tissue mass. Twenty-one cases of schwannomas were found in rare localization. We analyzed the MR images of these patients retrospectively. The MR images were evaluated in terms of tumor location, signal intensity, and enhancement pattern. The histological examination of all the patients confirmed the diagnosis of schwannoma. RESULTS: In 21 patients, the schwannomas were peripheral, localized to upper (n = 6) and lower extremities (n = 11). The remaining four patients had intramuscular schwannomas. The patients diagnosed with intramuscular schwannomas had schwannomas in sternocleidomastoid, gastrocnemius, triceps muscle and lateral wall of the abdomen. The average long-axis diameter of the tumor was 27.7 mm and the average short-axis diameter was 16.4 mm. The contrast pattern was diffused in eight tumors and peripheral in 13. CONCLUSION: In this study, we present clinical findings and MRI characteristics of schwannomas with a rare localization involving the peripheral, lower and upper extremity and intramuscular regions.

Clear Cell Renal Cell Carcinoma: Machine Learning-Based Quantitative Computed Tomography Texture Analysis for Prediction of Fuhrman Nuclear Grade.

OBJECTIVE: To evaluate the performance of quantitative computed tomography (CT) texture analysis using different machine learning (ML) classifiers for discriminating low and high nuclear grade clear cell renal cell carcinomas (cc-RCCs). MATERIALS AND METHODS: This retrospective study included 53 patients with pathologically proven 54 cc-RCCs (31 low-grade [grade 1 or 2]; 23 high-grade [grade 3 or 4]). In one patient, two synchronous cc-RCCs were included in the analysis. Mean age was 57.5 years. Thirty-four (64.1%) patients were male and 19 were female (35.9%). Mean tumour size based on the maximum diameter was 57.4 mm (range, 16-145 mm). Forty patients underwent radical nephrectomy and 13 underwent partial nephrectomy. Following pre-processing steps, two-dimensional CT texture features were extracted using portal-phase contrast-enhanced CT. Reproducibility of texture features was assessed with the intra-class correlation coefficient (ICC). Nested cross-validation with a wrapper-based algorithm was used in feature selection and model optimisation. The ML classifiers were support vector machine (SVM), multilayer perceptron (MLP, a sort of neural network), naïve Bayes, k-nearest neighbours, and random forest. The performance of the classifiers was compared by certain metrics. RESULTS: Among 279 texture features, 241 features with an ICC equal to or higher than 0.80 (excellent reproducibility) were included in the further feature selection process. The best model was created using SVM. The selected subset of features for SVM included five co-occurrence matrix (ICC range, 0.885-0.998), three run-length matrix (ICC range, 0.889-0.992), one gradient (ICC = 0.998), and four Haar wavelet features (ICC range, 0.941-0.997). The overall accuracy, sensitivity (for detecting high-grade cc-RCCs), specificity (for detecting high-grade cc-RCCs), and overall area under the curve of the best model were 85.1%, 91.3%, 80.6%, and 0.860, respectively. CONCLUSIONS: The ML-based CT texture analysis can be a useful and promising non-invasive method for prediction of low and high Fuhrman nuclear grade cc-RCCs. KEY POINTS: • Based on the percutaneous biopsy literature, ML-based CT texture analysis has a comparable predictive performance with percutaneous biopsy. • Highest predictive performance was obtained with use of the SVM. • SVM correctly classified 85.1% of cc-RCCs in terms of nuclear grade, with an AUC of 0.860.

Subacute Venous Infarct Mimicking Cerebral Metastasis in 18F-FDG PET/CT.

A 68-year-old woman with colon carcinoma was referred to F-FDG PET/CT imaging for staging. In addition to primary tumor involvement, PET/CT demonstrated focal FDG uptake in the right temporal lobe suggestive of primary brain tumor or metastasis. To delineate the lesion, a brain MRI scan showed sigmoid sinus thrombosis and vasogenic edema in the right temporal lobe. The patient presented a history of right-sided headache that began 1 week before the PET/CT. Neurological examination and MRI findings were concluded as subacute venous infarct due to sigmoid sinus thrombosis and that is a potential cause for false-positive FDG uptake on PET/CT.

Textural differences between renal cell carcinoma subtypes: Machine learning-based quantitative computed tomography texture analysis with independent external validation.

OBJECTIVE: To develop externally validated, reproducible, and generalizable models for distinguishing three major subtypes of renal cell carcinomas (RCCs) using machine learning-based quantitative computed tomography (CT) texture analysis (qCT-TA). MATERIALS AND METHODS: Sixty-eight RCCs were included in this retrospective study for model development and internal validation. Another 26 RCCs were included from public databases (The Cancer Genome Atlas-TCGA) for independent external validation. Following image preparation steps (reconstruction, resampling, normalization, and discretization), 275 texture features were extracted from unenhanced and corticomedullary phase CT images. Feature selection was firstly done with reproducibility analysis by three radiologists, and; then, with a wrapper-based classifier-specific algorithm. A nested cross-validation was performed for feature selection and model optimization. Base classifiers were the artificial neural network (ANN) and support vector machine (SVM). Base classifiers were also combined with three additional algorithms to improve generalizability performance. Classifications were done with the following groups: (i), non-clear cell RCC (non-cc-RCC) versus clear cell RCC (cc-RCC) and (ii), cc-RCC versus papillary cell RCC (pc-RCC) versus chromophobe cell RCC (chc-RCC). Main performance metric for comparisons was the Matthews correlation coefficient (MCC). RESULTS: Number of the reproducible features is smaller for the unenhanced images (93 out of 275) compared to the corticomedullary phase images (232 out of 275). Overall performance metrics of the machine learning-based qCT-TA derived from corticomedullary phase images were better than those of unenhanced images. Using corticomedullary phase images, ANN with adaptive boosting algorithm performed best for discrimination of non-cc-RCCs from cc-RCCs (MCC = 0.728) with an external validation accuracy, sensitivity, and specificity of 84.6%, 69.2%, and 100%, respectively. On the other hand, the performance of the machine learning-based qCT-TA is rather poor for distinguishing three major subtypes. The SVM with bagging algorithm performed best for discrimination of pc-RCC from other RCC subtypes (MCC = 0.804) with an external validation accuracy, sensitivity, and specificity of 69.2%, 71.4%, and 100%, respectively. CONCLUSIONS: Machine learning-based qCT-TA can distinguish non-cc-RCCs from cc-RCCs with a satisfying performance. On the other hand, the performance of the method for distinguishing three major subtypes is rather poor. Corticomedullary phase CT images provide much more valuable texture parameters than unenhanced images.

Is appendectomy always adequate for treatment?: Clinical manifestations of isolated actinomycosis in the appendix.

Isolated appendiceal actinomycosis is a rare chronic progressive suppurative infection. Its causative agent in humans is a Gram-positive saprophytic anaerobic bacteria, Actinomyces israelii. We present a case of an acute appendicitis that developed in a 54-year-old woman due to isolated appendiceal actinomycosis. Diagnosis of appendiceal actinomycosis causing acute appendicitis is generally performed postoperatively histopathologically, and appendectomy alone is not sufficient for treatment. It is an important factor that should be considered by clinicians that definitive treatment of the infection is possible by appropriate antibiotic use.

Relations Between Hyoid-Related Cephalometric Measurements and Severity of Obstructive Sleep Apnea.

OBJECTIVE: To evaluate the relationship between the hyoid-related cephalometric measurements and the apnea-hypopnea index (AHI) in patients diagnosed with obstructive sleep apnea (OSA). METHODS: A total of 56 subjects were evaluated by lateral cephalometric radiography and polysomnography (PSG). The OSA diagnosis was made according to the patients' AHI. Included were 13 primary snoring, 16 mild OSA, 10 moderate OSA, and 17 severe OSA. C3-hyoid distance and mentum-hyoid distance were measured on lateral cephalogram. Cephalometric measurements and PSG parameters were compared among the different OSA groups. RESULTS: The distance between the mentum and hyoid was significantly longer in the severe OSA group than in the primary snoring, mild OSA, and moderate OSA groups (P = 0.029). There was a significant positive correlation between the AHI value and the distance of the mentum hyoid (r = 0.368, P = 0.005). The C3-hyoid distance among the groups was not statistically significant different (P = 0.889). CONCLUSION: The mentum-hyoid distance of patients with severe OSA was longer compared to the other OSA groups. These patients might have more benefit from the surgeries that have an impact on the position of the hyoid bone compared to other patients with OSA.