Search

Objectives: Since the formation of skeletal malocclusions is closely linked to general craniofacial development, it is crucial to understand the anatomy and growth patterns of the skull base. This study aimed to assess the morphometry of the occipital condyle (OC) on CBCT scans of Class III skeletal malocclusion subjects and compare the findings with those of skeletal Class I malocclusion subjects. Methods: A retrospective analysis was performed on CBCT images based on predefined inclusion and exclusion criteria. The sample consisted of 76 CBCT images of 38 skeletal Class III patients and 38 skeletal Class I patients. CBCT scans were used to measure mesiodistal width, sagittal length, coronal height, effective height of OC, and sagittal OC angle. Statistical analyses were conducted with RStudio software. Results: Significant differences were found in sagittal OC angle and sagittal length of OC between the study groups (p < 0.001). In other metrics, such as coronal height of OC, effective OC height, and mesiodistal width of OC between the groups, no significant differences were found. Class III malocclusions exhibited significantly reduced sagittal OC angle and sagittal length of OC compared to Class I malocclusions. The left side showed a significantly larger sagittal OC angle than the right side (p = 0.002). Conclusions: This preliminary study identified reduced sagittal angle and sagittal length of OC in patients with Class III skeletal malocclusion. Clinicians should recognize potential differences in OC morphometry in patients with skeletal malocclusions. Future studies involving larger populations are recommended to further investigate the relationship between skeletal malocclusions and posterior cranial base structures, including the OC.

Objective: Before dental procedures, hand-wrist radiographs are used to plan treatment time and determine skeletal maturity. This study aims to determine gender from hand-wrist radiographs using different deep-learning methods.Methods: The left hand-wrist radiographs of 1044 individuals (534 males and 510 females) were pre-processed to clarify the image and adjust the contrast. In the gender classification problem, AlexNet, VGG16 and VGG19 transfer learning methods were both used as separate classifiers, and the features taken from these methods were combined and given to the support vector machine (SVM) classifier.Results: The results revealed that image analysis and deep learning techniques provided 91.1% accuracy in gender determination.Conclusion: Hand-wrist radiographs exhibited sexual dimorphism and could be used in gender prediction.Keywords: Deep learning; İmage analysis; Hand-wrist radiographs; Gender determination