A deep learning approach to permanent tooth germ detection on pediatric panoramic radiographs.

Purpose: The aim of this study was to assess the performance of a deep learning system for permanent tooth germ detection on pediatric panoramic radiographs. Materials and Methods: In total, 4518 anonymized panoramic radiographs of children between 5 and 13 years of age were collected. YOLOv4, a convolutional neural network (CNN)-based object detection model, was used to automatically detect permanent tooth germs. Panoramic images of children processed in LabelImg were trained and tested in the YOLOv4 algorithm. True-positive, false-positive, and false-negative rates were calculated. A confusion matrix was used to evaluate the performance of the model. Results: The YOLOv4 model, which detected permanent tooth germs on pediatric panoramic radiographs, provided an average precision value of 94.16% and an F1 value of 0.90, indicating a high level of significance. The average YOLOv4 inference time was 90 ms. Conclusion: The detection of permanent tooth germs on pediatric panoramic X-rays using a deep learning-based approach may facilitate the early diagnosis of tooth deficiency or supernumerary teeth and help dental practitioners find more accurate treatment options while saving time and effort.

Anatomical and Morphological Assessment of Nasopalatine Canal in Pediatric and Adolescent Population via Cone Beam Computed Tomography.

INTRODUCTION: Anatomical and morphological structure of nasopalatine canal (NPC) is important for surgical techniques carried out on the maxilla. The aim of the present study was to analyze the anatomical and morphological characteristics of the NPC among pediatric and adolescent population using cone beam computed tomography (CBCT). MATERIALS AND METHODS: A total of 437 cases were analyzed using CBCT images in this retrospective, cross-sectional study. Shape was analyzed as hourglass, cone, funnel, banana, cylindrical, and tree branch like. Number of foramina Stenson (FS) was evaluated through coronal, axial, and sagittal views. Landmark evaluation involved; diameter of FS, diameter of incisive foramen, diameter at the mid-canal length, NPC length, and narrowest buccal bone thickness. Pathology presence near NPC was evaluated to determine alterations on the landmark metrics. RESULTS: Nasopalatine canal shape distribution revealed 32% hourglass, 9.6% conic, 10.8% funnel, 11.9% banana, 29.5% cylindrical and 6.2% tree branch. Number of FS (P = 0.021; P < 0.05), diameter of FS (P = 0.041; p < 0.05), NPC length (P: 0.020; P < 0.05), and narrowest buccal bone thickness from the mid-canal length was significantly higher in males (P: 0.000; P < 0.05). Diameter of incisive foramen and diameter at the mid-canal length revealed no significance among genders (P1 = 0.318, P2 = 0.105; P > 0.05). Incidence of pathology near NPC is 20.8% and was not affected by gender (P = 0,192; P > 0.05). CONCLUSIONS: The current study demonstrates significant variations of NPC morphology among patients. Therefore, CBCT analysis is highly recommended for clinicians to reduce the complications in oral and maxillofacial surgery practices and to provide better surgical outcomes.