PURPOSE: The nasopalatine canal is a well-known, important anatomical structure in the anterior maxilla, but this region contains many accessory canals. The canalis sinuosus (CS) is one of these canals; it contains the anterior superior alveolar nerve, along with veins and arteries. The purpose of this study was to evaluate the CS using conebeam computed tomography (CBCT) in patients with maxillary impacted canines. MATERIALS AND METHODS: A total of 111 patients admitted to the Istanbul Medipol University School of Dentistry for the exposure, orthodontic treatment, and/or extraction of an impacted canine were included in this study. CBCT images were obtained for these patients under standard conditions. Axial, coronal, and sagittal sections were evaluated to assess the prevalence of CS, the direction and diameter of the canal, its relation with the impacted canine, and its distance from the alveolar crest. Further, possible correlations with patient gender and age were analyzed. RESULTS: The CS could be detected bilaterally in all the evaluated tomography images. The mean canal diameter was significantly larger in males than in females (P=.001). The CS ran significantly closer to the impacted canine when the canal was located horizontally (P=.03). Variations of the canal, such as accessory canals, were identified in 6 patients. CONCLUSION: CS is an anatomical entity that may resemble periapical lesions and other anatomical structures. Evaluation with CBCT prior to surgical procedures in the anterior maxilla will help to prevent overlooking such anatomical structures and to decrease possible surgical complications.
Arteries ; Cone-Beam Computed Tomography* ; Cuspid ; Dentistry ; Female ; Humans ; Male ; Maxilla ; Maxillary Nerve ; Prevalence ; Tooth, Impacted ; Veins

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.