This study aims to develop an algorithm for the automatic segmentation of the parotid gland on CT images of the head and neck using U-Net architecture and to evaluate the model’s performance. In this retrospective study, a total of 30 anonymized CT volumes of the head and neck were sliced into 931 axial images of the parotid glands. Ground truth labeling was performed with the CranioCatch Annotation Tool (CranioCatch, Eskisehir, Turkey) by two oral and maxillofacial radiologists. The images were resized to 512 × 512 and split into training (80%), validation (10%), and testing (10%) subgroups. A deep convolutional neural network model was developed using U-net architecture. The automatic segmentation performance was evaluated in terms of the F1-score, precision, sensitivity, and the Area Under Curve (AUC) statistics. The threshold for a successful segmentation was determined by the intersection of over 50% of the pixels with the ground truth. The F1-score, precision, and sensitivity of the AI model in segmenting the parotid glands in the axial CT slices were found to be 1. The AUC value was 0.96. This study has shown that it is possible to use AI models based on deep learning to automatically segment the parotid gland on axial CT images.

Introduction: COVID-19 is a contagious disease caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). The nature of dentistry leads to close contact with patients and exposure to saliva, blood, and other bodily fluids during treatment processes and it is a field where high-frequency devices that can make it easier for virus contamination are used. This study aims to determine the knowledge and approaches of COVID-19 infection control of intern dentists who have begun face-to-face education and their COVID-19-related fear and anxiety levels. Methods: The study comprised 4th and 5th-year students who began face-to-face education at the Ankara University Faculty of Dentistry 2020/2021 spring semester. A questionnaire was used as the data collection tool for this study. The data were collected using a knowledge questionnaire and a COVID-19 fear and anxiety scale. Results: The average COVID-19 knowledge score of the students was 63.65±9.64, their coronavirus fear average score was 17.63±5.57, and their anxiety average score was found to be 2.37±3.32. A positive relationship was found between the anxiety scores and the COVID-19 fear scores. The results of this study show that the COVID-19 knowledge level and fear of dentistry students are moderate and that their COVID-19 anxiety level is low. Conclusion: It was found that the knowledge and fear of coronavirus levels of intern dentistry students were moderate and that their coronavirus anxiety level was low.

This study aims to investigate the effect of using an artificial intelligence (AI) system (Diagnocat, Inc., San Francisco, USA) for caries detection, by comparing cone-beam computed tomography (CBCT) evaluation results with and without the software. 500 CBCT volumes are scored by three dentomaxillofacial radiologists for the presence of caries separately on a five-point confidence scale without and with the aid of the AI system. After visual evaluation, the deep convolutional neural network model generated a radiological report and observers scored again using AI interface. The ground truth was determined by a hybrid approach. Intra- and inter-observer agreements are evaluated with sensitivity, specificity, accuracy, and kappa statistics. 6008 surfaces are determined as ‘presence of caries’ and 13928 surfaces are determined as ‘absence of caries’ for ground truth. The area under the ROC curve of Observer 1, 2, and 3 are found to be 0.855/0.920, 0.863/0.917, and 0.747/0.903, respectively (unaided/aided). Fleiss Kappa coefficients are changed from 0.325 to 0.468 and the best accuracy (0.939) is achieved in the aided results. The radiographic evaluations performed with aid of the AI system are found to be more compatible and accurate than unaided evaluations in the detecting of dental caries with CBCT images.

Objective: The aim of this study is to analyze the frequency of radix paramolaris (RP) and radix entomolaris (RE) in the first and second molars using cone beam computed tomography (CBCT). Materials and Methods: The CBCT images of a total of 400 patients at the ages of 14 to 66 were included in the study. On the images that were included, two maxillofacial radiologists simultaneously examined the presence of radix paramolaris and radix entomolaris by using axial CBCT cross-sections from the pulpal chamber towards the apical. Results: At least one RE or RP was observed in 36 of the 400 patients (9%). A total of 20 RPs (1.25%) were observed, including 2 bilateral and 16 unilateral cases. A total of 38 REs (2.38%) were observed, including 11 bilateral and 16 unilateral cases. There was at least one RE or RP in 16 of the 149 male patients (10.7%) and in 20 of the 251 female patients (8%). Conclusion: Consequently, while the prevalence and types of third root variations differ between different populations, RE is seen more frequently in mandibular first molar teeth, and RP is seen more frequently in mandibular second molar teeth. No significant relationship could be found between sex and the prevalence of third root variations in mandibular molar teeth images included in this study. No significant difference was found between the right and left sides as the localizations of RP and RE in terms of prevalence. Keywords: Radix entomolaris; Radix paramolaris; Root canal morphology; Cone-beam CT; Mandibular molar