This study aimed to evaluate the accuracy of automated deep learning (DL) algorithm for identifying and classifying various types of dental implant systems (DIS) using a large-scale multicenter dataset. Dental implant radiographs of pos-implant surgery were collected from five college dental hospitals and 10 private dental clinics, and validated by the National Information Society Agency and the Korean Academy of Oral and Maxillofacial Implantology. The dataset contained a total of 156,965 panoramic and periapical radiographic images and comprised 10 manufacturers and 27 different types of DIS. The accuracy, precision, recall, F1 score, and confusion matrix were calculated to evaluate the classification performance of the automated DL algorithm. The performance metrics of the automated DL based on accuracy, precision, recall, and F1 score for 116,756 panoramic and 40,209 periapical radiographic images were 88.53%, 85.70%, 82.30%, and 84.00%, respectively. Using only panoramic images, the DL algorithm achieved 87.89% accuracy, 85.20% precision, 81.10% recall, and 83.10% F1 score, whereas the corresponding values using only periapical images achieved 86.87% accuracy, 84.40% precision, 81.70% recall, and 83.00% F1 score, respectively. Within the study limitations, automated DL shows a reliable classification accuracy based on large-scale and comprehensive datasets. Moreover, we observed no statistically significant difference in accuracy performance between the panoramic and periapical images. The clinical feasibility of the automated DL algorithm requires further confirmation using additional clinical datasets.

Objective: To assess changes in hyoid, tongue, pharyngeal airway, and head posture in patients who had mandibular setback surgery by intraoral vertical ramus osteotomy (IVRO) and to investigate the influence of LeFort I osteotomy. Materials and Methods: Sixty patients with skeletal Class III malocclusion were evaluated. All patients had mandibular setback surgery via IVRO, and 45 patients had additional maxillary impaction surgery via LeFort I osteotomy. Lateral cephalograms were taken before, immediately after, approximately 1 month after, and at least 1 year after surgery. Parameters indicating the hyoid, tongue, pharyngeal airway, and head posture were evaluated. Results: The hyoid significantly moved inferoposteriorly immediately after surgery and relapsed superoanteriorly during observation periods. The tongue significantly moved posteriorly during all periods. The final position of the hyoid and tongue was significantly posterior, and the final pharyngeal airway was significantly narrower compared with its presurgical position. Significant cervical hyperflection occurred during observation periods and was strongly correlated with anterior movement of the hyoid. The hyoid and tongue showed similar positions regardless of the presence of different genders or LeFort I osteotomy after the long-term observation period. Conclusions: The hyoid and tongue moved posteriorly after mandibular setback surgery via IVRO, and there was a tendency to relapse back to its original position. However, the final pharyngeal airway width remained narrower after the long-term observation period. Based on our results, careful monitoring of the airway may be needed after mandibular setback surgery via IVRO.

Huh JK, et al. Restor Dent Endod. 2013 Aug;38(3):160-166. http://dx.doi.org/10.5395/rde.2013.38.3.160

Jeong CH, et al. J Korean Assoc Oral Maxillofac Surg. 2018 Oct;44(5):212-219. https://doi.org/10.5125/jkaoms.2018.44.5.212

The goal of this study was to develop a deep learning-based algorithm to predict temporomandibular joint (TMJ) disc perforation based on the findings of magnetic resonance imaging (MRI) and to validate its performance through comparison with previously reported results. The study objects were obtained by reviewing medical records from January 2005 to June 2018. 299 joints from 289 patients were divided into perforated and non-perforated groups based on the existence of disc perforation confirmed during surgery. Experienced observers interpreted the TMJ MRI images to extract features. Data containing those features were applied to build and validate prediction models using random forest and multilayer perceptron (MLP) techniques, the latter using the Keras framework, a recent deep learning architecture. The area under the receiver operating characteristic (ROC) curve (AUC) was used to compare the performances of the models. MLP produced the best performance (AUC 0.940), followed by random forest (AUC 0.918) and disc shape alone (AUC 0.791). The MLP and random forest were also superior to previously reported results using MRI (AUC 0.808) and MRI-based nomogram (AUC 0.889). Implementing deep learning showed superior performance in predicting disc perforation in TMJ compared to conventional methods and previous reports.