Radiographs play a key role in diagnosis of periodontal diseases. Deep learning models have been explored for image analysis in periodontal diseases. However, there is lacuna of research in the deep learning model-based detection of furcation involvements [FI]. The objective of this study was to determine the accuracy of deep learning model in the detection of FI in axial CBCT images. We obtained initial dataset 285 axial CBCT images among which 143 were normal (without FI) and 142 were abnormal (with FI). Data augmentation technique was used to create 600(300 normal and 300 abnormal) images by using 200 images from the training dataset. Remaining 85(43 normal and 42 abnormal) images were kept for testing of model. ResNet101V2 with transfer learning was used employed for the analysis of images. Training accuracy of model is 98%, valid accuracy is 97% and test accuracy is 91%. The precision and F1 score were 0.98 and 0.98 respectively. The Area under curve (AUC) was reported at 0.98. The test loss was reported at 0.2170. The deep learning model (ResNet101V2) can accurately detect the FI in axial CBCT images. However, since our study was preliminary in nature and carried out with relatively smaller dataset, a study with larger dataset will further confirm the accuracy of deep learning models.

Background: Interprofessional education (IPE) encompasses integration, communication, mutual trust and shared decision-making with a common goal of improved patient care and safety. Despite its crucial role, IPE has not gained its anticipated popularity. This study aims to determine the impact of an online educational intervention about IPE on medical, dental and health sciences students in the University of Sharjah (UoS).Methods: This quasi-experimental research was conducted in three phases; a pre-intervention phase where the Readiness for Interprofessional Learning Scale (RIPLS) inventory was administered online to the medical, dental and health sciences students of UoS; an intervention phase where an online workshop was organized via Microsoft Teams®; and a post-intervention phase where RIPLS was used to gather the students’ attitudes towards IPE. The independentttest was used to compare the responses between genders and junior and senior students. A paired samplettest was used to determine the impact of the intervention on the students’ understandings and attitudes about IPE.Results: Out of 800 invited students, 530 students responded to the pre-intervention RIPLS survey. A comparison of the pre-post intervention for the RIPLS subscales of teamwork and collaboration, professional identification, and professional roles showed a significant improvement of students’ attitudes withp-values 0.03, 0.00 and 0.00, respectively. All workshop moderators scored a median of 4 or 5 to the essential elements of IPE during intervention except for a median of 3 for group dynamics.Conclusion: The present data, derived from the application of a brief online educational intervention, underpins the readiness and positive attitudes of undergraduate medical students towards IPE. The positive impact of online intervention necessitates the development of a structured and unified IPE curriculum to enhance the receptiveness and application of IPE in the medical field.

The objective of the present study was to determine the accuracy of machine learning (ML) models in the detection of mesiobuccal (MB2) canals in axial cone-beam computed tomography (CBCT) sections. A total of 2500 CBCT scans from the oral radiology department of University Dental Hospital, Sharjah were screened to obtain 277 high-resolution, small field-of-view CBCT scans with maxillary molars. Among the 277 scans, 160 of them showed the presence of MB2 orifice and the rest (117) did not. Two-dimensional axial images of these scans were then cropped. The images were classified and labelled as N (absence of MB2) and M (presence of MB2) by 2 examiners. The images were embedded using Google's Inception V3 and transferred to the ML classification model. Six different ML models (logistic regression [LR], naïve Bayes [NB], support vector machine [SVM], K-nearest neighbours [Knn], random forest [RF], neural network [NN]) were then tested on their ability to classify the images into M and N. The classification metrics (area under curve [AUC], accuracy, F1-score, precision) of the models were assessed in 3 steps. NN (0.896), LR (0.893), and SVM (0.886) showed the highest values of AUC with specified target variables (steps 2 and 3). The highest accuracy was exhibited by LR (0.849) and NN (0.848) with specified target variables. The highest precision (86.8%) and recall (92.5%) was observed with the SVM model. The success rates (AUC, precision, recall) of ML algorithms in the detection of MB2 were remarkable in our study. It was also observed that when the target variable was specified, significant success rates such as 86.8% in precision and 92.5% in recall were achieved. The present study showed promising results in the ML-based detection of MB2 canal using axial CBCT slices.

There is growing evidence that use of E-portfolios has a positive effect on learning experience. However, literature has not shown sufficient data about the effectiveness of E-portfolios in medical education. This study was conducted to assess the acceptability and potential impacts of E-portfolio use for undergraduate radiography students. This cross-sectional quantitative study was conducted during the academic year 2016-2017 on students studying clinical courses. A self-administered questionnaire was distributed to the selected cohort of students. All participants completed the consent form before answering the questionnaire. Of 75 students, 66 completed the survey (response rate; 88%). Students' experience, students' learning support, and the challenges of E-portfolio use were identified. Forty-one (62%) students perceived that E-portfolios facilitated the effective organization of their work, and 40 (61%) agreed that E-portfolios enhanced their professional skills. In contrast, the students perceived a negative correlation between students' learning support and future utilization of E-portfolios (correlation coefficient -0.394, p = 0.05). Future utilization of E-portfolios was found to be positively correlated with challenges and commitment to deadlines, with correlation coefficients of 0.371 and 0.152, respectively. The study found that continuous technical support for E-portfolios throughout the course had a potential role in enhancing learning experience. Appropriate training for integrating E-portfolios into teaching and learning can potentially enrich the educational environment. Student and faculty feedback is the main cornerstone for E-portfolio success.

The volume of the inferior turbinates (IT) and the lining of the maxillary sinuses are important parameters when assessing sino-nasal diseases. However, no radiographic studies have investigated the correlation between these parameters. The present study was conducted to analyze the association between IT volumes and thickness of maxillary sinus mucosal lining. A retrospective evaluation of the cone-beam computed tomography (CBCT) scans of 100 adult subjects was carried out by two radiologists. The scans were assigned to two groups (Group 1 & 2) based on the radiographic evidence of maxillary sinus lining in the CBCT scans. Group 1 consisted of 50 CBCT scans of subjects with no evidence of maxillary sinus mucosal lining, whereas Group 2 consisted of 50 subjects with evidence of maxillary sinus mucosal lining. The scans in the Group 2 were further sub-classified into five categories, based on the thickness of the maxillary sinus mucosal lining. Vesalius 3D software was used to evaluate the total volume of inferior nasal turbinates by the two radiologists and a mean volume was obtained for each study subject. The intraclass correlation coefficient (ICC) between the volumetric estimations performed by the two radiologist was 0.87. Analysis of the results revealed that there was no significant gender-based difference (Group 1, P = 0.67 and Group 2, P = 0.95) in the total turbinate volume in either of the study groups. The total turbinate volume did not show any significant correlation (Group 1, r = 0.24 and Group 2, r = 0.12) with the age. There was a significant increase (P = 0.001) in the total turbinate volume of the subjects in Group 2 compared to Group 1. Regression analysis revealed that the thickness of sinus lining correlated significantly (P = 0.001) with the total turbinate volume. An increase in the total turbinate volume has been associated with an increase in the thickness of the maxillary sinus mucosal lining. The data from this study will be useful for post-operative follow-up of inferior turbinates and maxillary sinus lining after the turbinate volume reduction procedures.