Background: Diverticula are commonly observed in the duodenum. Duodenal diverticulum (DD) usually does not give symptoms throughout life and is diagnosed by coincidence. However, it may present with different symptoms in patients. Objective: This study aims to evaluate the prevalence of DD and juxtapapillary duodenal diverticulum (JDD) and its association with other possible pathologies and to determine its clinical impact by using Computed Tomography (CT). Methods: This retrospective observational study, which was taken consecutively between the years of 2013-2020, was evaluated in the Radiology Department. The total number of cases was 4850 (male-2440; female-2410). CT images were evaluated by two experienced radiologists at the workstation. DD and JDD prevalence and clinical findings in the hospital registry system were examined. Results: The age of the patients included in the study ranged from 17 to 92 years (mean age 46.94±16.42). In patients with DD (female-130; male-101), mean age was 62.24 ± 12.69 (21-92). The prevalence of DD was 4.76% (n=231). The prevalence of JDD was 4.02% (n=195) and increased with age (p<0.01). The average diameter of the JDD was measured as 23.29±8.22 (9.5-55.3) mm. A significant positive correlation was found between age and DD diameter (p=0.039). DDs were found most commonly 84.42% (n=195) in the second segment of the duodenum as JDD. In patients with JDD, the mean diameter of choledochus and wirsung canal were 6.7 ± 2.4 (3-15.3) mm and 0.31 ± 0.1 (0.1-6.5) mm respectively. The choledochal diameter was correlated with the JDD size (p = 0.004). Cholelithiasis (n=56), choledocholithiasis (n=20), cholecystitis (n=52), diverticulitis (n=15), duodenitis (n=37), pancreatitis (n=5) and hiatal hernia (n=60) with JDD were observed. Periampullary carcinoma was detected in one patient. Conclusion: Our study shows that cholelithiasis, choledocholithiasis, cholecystitis, diverticulitis, duodenitis, pancreatitis may be associated with JDD. Therefore, in contrast-enhanced abdominal CT scans taken for various reasons, investigation of the presence and characteristics of JDD and detection of pathologies that may be associated with JDD are important for patients to benefit from early diagnosis and treatment opportunities and to take precautions against possible complications.

Background: Due to the high mortality of lung cancer, the aim was to find convolutional neural network models that can distinguish benign and malignant cases with high accuracy, which can help in early diagnosis with diagnostic imaging. Methods: Patients who underwent tomography in our clinic and who were found to have lung nodules were retrospectively screened between January 2015 and December 2020. The patients were divided into two groups: benign (n=68; 38 males, 30 females; mean age: 59±12.2 years; range, 27 to 81 years) and malignant (n=29; 19 males, 10 females; mean age: 65±10.4 years; range, 43 to 88 years). In addition, a control group (n=67; 38 males, 29 females; mean age: 56.9±14.1 years; range, 26 to 81 years) consisting of healthy patients with no pathology in their sections was formed. Deep neural networks were trained with 80% of the three-class dataset we created and tested with 20% of the data. After the training of deep neural networks, feature extraction was done for these networks. The features extracted from the dataset were classified by machine learning algorithms. Performance results were obtained using confusion matrix analysis. Results: After training deep neural networks, the highest accuracy rate of 80% was achieved with the AlexNET model among the models used. In the second stage results, obtained after feature extraction and using the classifier, the highest accuracy rate was achieved with the support vector machine classifier in the VGG19 model with 93.5%. In addition, increases in accuracy were noted in all models with the use of the support vector machine classifier. Conclusion: Differentiation of benign and malignant lung nodules using deep learning models and feature extraction will provide important advantages for early diagnosis in radiology practice. The results obtained in our study support this view.

Introduction: Chronic kidney disease is irreversible and may result in end-stage renal failure (ESRF). The kidney replacement program is determined by calculating Kt/V ratios, one of the dialysis efficiency indicators in treatment planning in routine dialysis applications in ESRF patients. We aimed to investigate whether there is a correlation between flow rate and Kt/V ratio. Methods: All patients were evaluated by B-mode ultrasonography (US) and color doppler ultrasonography (CDUS). The anastomosis line diameter was measured in the B-mode US. The fistula flow rate was calculated in a spectral examination at the anatomical location where the fistulized flow was best obtained at the anastomosis level. Patients with a fistula flow rate above 300 mL/min in CDUS examinations were considered reasonable flow rates. The fistula flow rate in these patients was compared with the Kt/V ratios. Spearman’s rank correlation coefficient was calculated since the normal distribution condition was not met to determine the relationship between variables. Results: The results of this study showed a high level (r=0.72, P=0.001) of positive and statistically significant correlation between flow rate and Kt/V ratio in upper arm arteriovenous fistula in patients with end stage renal failure. Conclusion: We found a highly positive and statistically significant correlation between fistula flow rate and Kt/V ratio. Low Kt/V ratios have different causes. Low fistula flow should be considered first in low Kt/V values.

Objective Celiac disease (CD) is characterized by an immune response in genetically gluten-sensitive individuals resulting in inflammatory damage of the small intestine. The radiological identification of pelvic venous dilatation (PVD) is important as it can contribute to the diagnosis of different spectrums of pelvic and systemic diseases. In our study, we aimed to determine the prevalence of PVD in CD patients and to present our findings with the literature. Materials and Methods This retrospective observational study was approved by the institutional review board in our institution. All patients were patients diagnosed with CD by clinical evaluation, serological data, and intestinal biopsy, and who underwent CT between October 2011 and March 2020 in our medical center. CD patients (n=149) and control group (n=250) who had contrastenhanced CT were evaluated for PVD. In all patients, PVD prevalence was examined in the patient and the control group. The diameter of the pelvic veins was measured and noted. Complaints of the patients were noted from the hospital records. Results Among a total of 149 histopathologically proven patient groups, there were 93 female and 56 male patients with a mean age of 35.11±13.03 and 36.23±15.06 years, respectively. Among a total of 250 control groups; there were 145 females and 105 males with a mean age of 38.65±15.38 and 37.25±13.56 years, respectively. PVD prevalence in the female and male were 60.22% (n=56) and 41.07% (n=23) in CD patients, respectively. 46.75% (n=36) CD patients had abdominal pain and were correlated with PVD (p