Background: The aim of our study is to provide successful automatic segmentation of various objects on orthopantomographs (OPGs). Methods: 8138 OPGs obtained from the archives of the Department of Dentomaxillofacial Radiology were included. OPGs were converted into PNGs and transferred to the segmentation tool’s database. All teeth, crown–bridge restorations, dental implants, composite–amalgam fillings, dental caries, residual roots, and root canal fillings were manually segmented by two experts with the manual drawing semantic segmentation technique. Results: The intra-class correlation coefficient (ICC) for both inter- and intra-observers for manual segmentation was excellent (ICC > 0.75). The intra-observer ICC was found to be 0.994, while the inter-observer reliability was 0.989. No significant difference was detected amongst observers (p = 0.947). The calculated DSC and accuracy values across all OPGs were 0.85 and 0.95 for the tooth segmentation, 0.88 and 0.99 for dental caries, 0.87 and 0.99 for dental restorations, 0.93 and 0.99 for crown–bridge restorations, 0.94 and 0.99 for dental implants, 0.78 and 0.99 for root canal fillings, and 0.78 and 0.99 for residual roots, respectively. Conclusions: Thanks to faster and automated diagnoses on 2D as well as 3D dental images, dentists will have higher diagnosis rates in a shorter time even without excluding cases.

The study aimed to generate a fused deep learning algorithm that detects and classifies the relationship between the mandibular third molar and mandibular canal on orthopantomographs. Radiographs (n = 1880) were randomly selected from the hospital archive. Two dentomaxillofacial radiologists annotated the data via MATLAB and classified them into four groups according to the overlap of the root of the mandibular third molar and mandibular canal. Each radiograph was segmented using a U-Net-like architecture. The segmented images were classified by AlexNet. Accuracy, the weighted intersection over union score, the dice coefficient, specificity, sensitivity, and area under curve metrics were used to quantify the performance of the models. Also, three dental practitioners were asked to classify the same test data, their success rate was assessed using the Intraclass Correlation Coefficient. The segmentation network achieved a global accuracy of 0.99 and a weighted intersection over union score of 0.98, average dice score overall images was 0.91. The classification network achieved an accuracy of 0.80, per class sensitivity of 0.74, 0.83, 0.86, 0.67, per class specificity of 0.92, 0.95, 0.88, 0.96 and AUC score of 0.85. The most successful dental practitioner achieved a success rate of 0.79. The fused segmentation and classification networks produced encouraging results. The final model achieved almost the same classification performance as dental practitioners. Better diagnostic accuracy of the combined artificial intelligence tools may help to improve the prediction of the risk factors, especially for recognizing such anatomical variations.

Background and Objectives: This retrospective study aims to evaluate the prevalence, radiographic features, and clinical relevancy of the accessory canals (AC) of the canalis sinuosus (CS) in patients referred for implant surgery. Materials and Methods: Cone-beam computed tomography (CBCT) images of the patients were collected and ACs were evaluated. Age, sex, bilateral distribution, localization, diameter, distance to the buccal cortical plate, distance to the crest of the alveolar ridge, terminal ending localization, and the presence of tooth or implant were recorded. Ninety-one patients who were eligible for this study were enrolled. Results: A total of 188 ACs were found in 91 patients with 86 bilateral and 5 unilateral distributions. The mean age of the patients was 45.39. All ACs had a terminal ending at the palatal cortical border. All parameters showed a non-normal distribution; thus, the Mann–Whitney U test was preferred. Bilateral AC distribution (p = 0.761), AC distance to the crest of the alveolar ridge (p = 0.614), AC distance to the buccal cortical plate (p = 0.105), and AC diameter (p = 0.423) showed no significant difference between females and males. According to our study, a CS might be an anatomical structure rather than an anatomical variation, as all patients had at least one AC of the CS. It can be inferred that the detection of ACs will be achievable once clinicians are aware of these structures with continuous regular anatomy reworks and with small voxel-sized CBCT devices. Conclusion: This study was conducted to find the features and prevalence of the CS, and it was found that the CS is an anatomical structure rather than an anatomical variation. This argument is in line with the information on the CS in Gray’s Anatomy, 42nd Edition. Impaired healings and complications of the CS can be avoided if clinicians follow the American Academy of Oral and Maxillofacial Radiology guidelines regarding pre-operative implant examination. Otherwise, avertible complications may cause significant impairments in quality of life.

In this study, we compared the bone-healing effects of the local application of platelet-rich fibrin (PRF) and hyaluronic acid (HA) to bilateral tibial fractures in rats. Twenty-three adult male Sprague-Dawley rats were used. Twenty-two animals were randomly allocated to a control group (n = 6) and 2 study groups: PRF (n = 8) and HA (n = 8). The 23rd rat was used as a donor to obtain PRF. Each group was divided into 2 subgroups for histomorphometric and radiologic assessments at 2 and 6 weeks. Foreign body reaction, necrosis, inflammation, new bone formation, and fibrosis were investigated as bone healing parameters in terms of histopathologic analysis. The difference between the groups for these parameters was evaluated. The radiologic evaluation was performed by comparing the 3-dimensional reconstruction images of the fracture sites between the study and control groups. Histomorphometric evaluation showed that at 2 weeks postoperatively, the control group showed lesser bone formation (26.1 ± 6.6%) when compared to the study (HA: 54.7 ± 9.7%; PRF: 75.3 ± 19.2%) groups and PRF group showed highest total ossification. At 6 weeks postoperatively the PRF group showed lesser total ossification (50.7 ± 28.2%) when compared to control (76.3 ± 21.7%) and HA group. The HA (88.8 ± 13.3%) showed highest total ossification. In the control group, fibrosis was more prominent at week 6, whereas in the HA and PRF groups the amount of ossification increased. In contrast to histopathologic healing, radiologic bone healing did not differ significantly among the study and control groups 2 weeks after surgery, whereas at 6 weeks, the results of radiologic bone formation were in accordance with those of histopathologic bone healing.