Objectives: A separated endodontic instrument is one of the challenging complications of root canal treatment. The purpose of this study was to compare two deep learning methods that are convolutional neural network (CNN) and long short-term memory (LSTM) to detect the separated endodontic instruments on dental radiographs. Methods: Panoramic radiographs from the hospital archive were retrospectively evaluated by two dentists. A total of 915 teeth, of which 417 are labeled as “separated instrument” and 498 are labeled as “healthy root canal treatment” were included. A total of six deep learning models, four of which are some varieties of CNN (Raw-CNN, Augmented-CNN, Gabor filtered-CNN, Gabor-filtered-augmented-CNN) and two of which are some varieties of LSTM model (Raw-LSTM, Augmented-LSTM) were trained based on several feature extraction methods with an applied or not applied an augmentation procedure. The diagnostic performances of the models were compared in terms of accuracy, sensitivity, specificity, positive- and negative-predictive value using 10-fold cross-validation. A McNemar’s tests was employed to figure out if there is a statistically significant difference between performances of the models. Receiver operating characteristic (ROC) curves were developed to assess the quality of the performance of the most promising model (Gabor filtered-CNN model) by exploring different cut-off levels in the last decision layer of the model. Results: The Gabor filtered-CNN model showed the highest accuracy (84.37 ± 2.79), sensitivity (81.26 ± 4.79), positive-predictive value (84.16 ± 3.35) and negative-predictive value (84.62 ± 4.56 with a confidence interval of 80.6 ± 0.0076. McNemar’s tests yielded that the performance of the Gabor filtered-CNN model significantly different from both LSTM models (p < 0.01). Conclusions: Both CNN and LSTM models were achieved a high predictive performance on to distinguish separated endodontic instruments in radiographs. The Gabor filtered-CNN model without data augmentation gave the best predictive performance.

The study aimed to generate a fused deep learning algorithm that detects and classifies the relationship between the mandibular third molar and mandibular canal on orthopantomographs. Radiographs (n = 1880) were randomly selected from the hospital archive. Two dentomaxillofacial radiologists annotated the data via MATLAB and classified them into four groups according to the overlap of the root of the mandibular third molar and mandibular canal. Each radiograph was segmented using a U-Net-like architecture. The segmented images were classified by AlexNet. Accuracy, the weighted intersection over union score, the dice coefficient, specificity, sensitivity, and area under curve metrics were used to quantify the performance of the models. Also, three dental practitioners were asked to classify the same test data, their success rate was assessed using the Intraclass Correlation Coefficient. The segmentation network achieved a global accuracy of 0.99 and a weighted intersection over union score of 0.98, average dice score overall images was 0.91. The classification network achieved an accuracy of 0.80, per class sensitivity of 0.74, 0.83, 0.86, 0.67, per class specificity of 0.92, 0.95, 0.88, 0.96 and AUC score of 0.85. The most successful dental practitioner achieved a success rate of 0.79. The fused segmentation and classification networks produced encouraging results. The final model achieved almost the same classification performance as dental practitioners. Better diagnostic accuracy of the combined artificial intelligence tools may help to improve the prediction of the risk factors, especially for recognizing such anatomical variations.

Background: The aim of this investigation was to evaluate the length, thickness, sagittal and transvers angulations and the morphological variations of the stylohyoid complex (SHC), to assess their probable assosiations with age and gender, and to investigate the prevalence of it in a wide range of a Turkish sub-population by using cone beam computed tomograph (CBCT), thereby conducting dentist and maxillofacial surgeons. Methods: The CBCT images of the 1000 patients were evaluated retrospectively. The length, thickness, sagittal and transverse angulations, morphological variations and ossification degrees of SHC were evaluated on multiplanar reconstructions (MPR) and 3D volume rendering (3DVR) images. The data were analyzed statistically by using nonparametric tests, Pearson’s correlation coefficient, Student’s t test, Chi-square test and one-way ANOVA. Statistical significance was considered at p < 0.05. Results: It was determined that 684 (34.2%) of all 2000 SHCs were elongated (>35 mm). The mean saggital angle value was measured as 72,24° and the mean transverse angle value was 70,81°. Scalariform shape, elongated type and nodular calcification pattern have the highest mean age values between the morphological groups respectively. Calcified outline was the most prevalent calcification pattern in males. There was no correlation between length and the calcification pattern groups while scalariform shape and pseudoarticular type were the longest variations. Conclusions: We observed that as the anterior sagittal angle gets wider, SHC tends to get longer. The most observed morphological variations were linear shape, elongated type and calcified outline pattern. Detailed studies on the classification will contribute to the literature. Background: The aim of this investigation was to evaluate the length, thickness, sagittal and transvers angulations and the morphological variations of the stylohyoid complex (SHC), to assess their probable assosiations with age and gender, and to investigate the prevalence of it in a wide range of a Turkish sub-population by using cone beam computed tomograph (CBCT), thereby conducting dentist and maxillofacial surgeons. Methods: The CBCT images of the 1000 patients were evaluated retrospectively. The length, thickness, sagittal and transverse angulations, morphological variations and ossification degrees of SHC were evaluated on multiplanar reconstructions (MPR) and 3D volume rendering (3DVR) images. The data were analyzed statistically by using nonparametric tests, Pearson’s correlation coefficient, Student’s t test, Chi-square test and one-way ANOVA. Statistical significance was considered at p < 0.05. Results: It was determined that 684 (34.2%) of all 2000 SHCs were elongated (>35 mm). The mean saggital angle value was measured as 72,24° and the mean transverse angle value was 70,81°. Scalariform shape, elongated type and nodular calcification pattern have the highest mean age values between the morphological groups respectively. Calcified outline was the most prevalent calcification pattern in males. There was no correlation between length and the calcification pattern groups while scalariform shape and pseudoarticular type were the longest variations. Conclusions: We observed that as the anterior sagittal angle gets wider, SHC tends to get longer. The most observed morphological variations were linear shape, elongated type and calcified outline pattern. Detailed studies on the classification will contribute to the literature.