ABSTRACT
INTRODUCTION: To evaluate, by cone-beam computed tomography (CBCT), the change in thickness and height of the alveolar bone and interdental septum in the anterior mandible after orthodontic treatment for dental crowding using tooth extraction. MATERIAL AND METHODS: The sample consisted of 48 mandibular incisors from adult patients who presented with Class I malocclusion and required orthodontic treatment with the extraction of mandibular premolars. CBCT images were taken before starting the treatment (T1) and three months after treatment (T2). The following measurements were evaluated: width and height of the alveolar bone and the interdental septum, the distance between the cementoenamel junction and the bone ridges (F-CEJ-MBC and L-CEJ-MBC), as well as the vertical positioning and inclination of the incisor, using the Lingual Plane as the reference point. The paired Student's t-test and Pearson correlation were used with a significance level of 5%. RESULTS: A significant increase was observed in the distance L-CEJ-MBC, which shows the appearance of bone dehiscence. The degree of dental crowding was not a risk factor for the development of dehiscence. The decrease in the incisor inclination and intrusion was related to the formation of dehiscence on the lingual surface. CONCLUSION: The variation in the incisor's inclination and intrusion during the treatment of dental crowding using tooth extraction are related to the formation of bone dehiscence on its lingual surface.
ABSTRACT
PURPOSE: To develop and evaluate the accuracy of a computer-assisted system based on artificial intelligence for detecting and identifying dental implant brands using digital periapical radiographs. MATERIALS AND METHODS: A total of 1,800 digital periapical radiographs of dental implants from three distinct manufacturers (f1 = 600, f2 = 600, and f3 = 600) were split into training dataset (n = 1,440 [80%]) and testing dataset (n = 360 [20%]) groups. The images were evaluated by software developed by means of convolutional neural networks (CNN), with the aim of identifying the manufacturer of the dental implants contained in them. Accuracy, sensitivity, specificity, positive and negative predictive values, and the receiver operating characteristic (ROC) curve were calculated for detection and diagnostic performance of the CNN algorithm. RESULTS: At the final epoch (25), system accuracy values of 99.78% were obtained for group training data, 99.36% for group testing data, and 85.29% for validation data. The latter value corresponded to the actual accuracy of carrying out the system learning process. CONCLUSION: This study demonstrated the effectiveness of CNN for identifying dental implant manufacturers, which was proven to be a precise method of great clinical significance.
Subject(s)
Artificial Intelligence , Dental Implants , Algorithms , Neural Networks, Computer , ROC CurveABSTRACT
Objective: To conduct a morphometric evaluation of the incisive canal, adjacent structures, and their anatomic variations in Brazilian individuals.Methods: A retrospective study was conducted using a sample of 157 multislice computed tomography images of adult Brazilian individuals of both sexes (20-96 years). The exam was performed with the RadiAnt DICOM Viewer 4.0.1 (64-bit) software that uses the DICOM PACS standard for visualization of medical and dental images.Results: The values for length and height of the canal, thickness of the palatine bone plate, and latero-lateral diameter of the incisive foramen were higher in men than in women (p < 0.05).Conclusion: The findings of this study demonstrated morphometric differences for the following parameters: latero-lateral diameter; width of canals at all levels measured; palatine bone plate height; canal length and palatine bone plate thickness in relation to the male and female sexes in the Brazilian population.
