The assessment of alveolar bone loss, a crucial element of the periodontium, plays a vital role in the diagnosis of periodontitis and the prognosis of the disease. In dentistry, artificial intelligence (AI) applications have demonstrated practical and efficient diagnostic capabilities, leveraging machine learning and cognitive problem-solving functions that mimic human abilities. This study aims to evaluate the effectiveness of AI models in identifying alveolar bone loss as present or absent across different regions. To achieve this goal, alveolar bone loss models were generated using the PyTorch-based YOLO-v5 model implemented via CranioCatch software, detecting periodontal bone loss areas and labeling them using the segmentation method on 685 panoramic radiographs. Besides general evaluation, models were grouped according to subregions (incisors, canines, premolars, and molars) to provide a targeted evaluation. Our findings reveal that the lowest sensitivity and F1 score values were associated with total alveolar bone loss, while the highest values were observed in the maxillary incisor region. It shows that artificial intelligence has a high potential in analytical studies evaluating periodontal bone loss situations. Considering the limited amount of data, it is predicted that this success will increase with the provision of machine learning by using a more comprehensive data set in further studies.

Bite-wing radiographs are one of the most used intraoral radiography techniques in dentistry. AI is extremely important in terms of more efficient patient care in the field of dentistry. The aim of this study was to perform a diagnostic evaluation on bite-wing radiographs with an AI model based on CNNs. In this study, 500 bite-wing radiographs in the radiography archive of Eskişehir Osmangazi University, Faculty of Dentistry, Department of Oral and Maxillofacial Radiology were used. The CranioCatch labeling program (CranioCatch, Eskisehir, Turkey) with tooth decays, crowns, pulp, restoration material, and root-filling material for five different diagnoses were made by labeling the segmentation technique. The U-Net architecture was used to develop the AI model. F1 score, sensitivity, and precision results of the study, respectively, caries 0.8818–0.8235–0.9491, crown; 0.9629–0.9285–1, pulp; 0.9631–0.9843–0.9429, with restoration material; and 0.9714–0.9622–0.9807 was obtained as 0.9722–0.9459–1 for the root filling material. This study has shown that an AI model can be used to automatically evaluate bite-wing radiographs and the results are promising. Owing to these automatically prepared charts, physicians in a clinical intense tempo will be able to work more efficiently and quickly.

To evaluate the effect of various tube voltage (kV) settings on the accuracy of cone-beam computed tomography (CBCT) images in measuring trabecular microstructure and cortical morphology, using micro-CT (μCT) as the reference. Ten bone samples of sheep mandibles were scanned using both μCT and CBCT at three different tube voltage settings (80, 85, and 90 kV). Identical regions of interest (ROIs) on trabecular and cortical bones were analyzed in all images. Measurements of trabecular microstructure included bone volume fraction (BV/TV), trabecular thickness (Tb.Th) and space (Tb.Sp), while thickness (Ct.Th) and area (Ct.Ar) of cortical bone were measured to determine cortical morphology. Measurements were compared using paired t-test, while agreement between measurements of two modalities was assessed using Bland–Altman analysis. One-way ANOVA was used to determine differences in measurements of CBCT images at different kVs (p < 0.01). Compared to μCT, CBCT overestimated trabecular parameters and Ct.Th but underestimated Ct.Ar, with high agreement observed between the methods. Significant differences were found for all measurements except BV/TV and Ct.Ar at all kVs. No differences were observed between CBCT measurements at different tube potentials. The tube voltage of CBCT has minimal impact on the measurement accuracy of most microstructural parameters. BV/TV and Ct.Ar measurements may be particularly preferred for bone evaluations using CBCT images.

Dental fillings, frequently used in dentistry to address various dental tissue issues, may pose problems when not aligned with the anatomical contours and physiology of dental and periodontal tissues. Our study aims to detect the prevalence and distribution of normal and overhanging filling restorations using a deep CNN architecture trained through supervised learning, on panoramic radiography images. A total of 10480 fillings and 2491 overhanging fillings were labeled using CranioCatch software from 2473 and 1850 images, respectively. After the data obtaining phase, validation (80%), training 10%), and test-groups (10%) were formed from images for both labelling. The YOLOv5x architecture was used to develop the AI model. The model’s performance was assessed through a confusion matrix and sensitivity, precision, and F1 score values of the model were calculated. For filling, sensitivity is 0.95, precision is 0.97, and F1 score is 0.96; for overhanging were determined to be 0.86, 0.89, and 0.87, respectively. The results demonstrate the capacity of the YOLOv5 algorithm to segment dental radiographs efficiently and accurately and demonstrate proficiency in detecting and distinguishing between normal and overhanging filling restorations.