Objectives: This paper evaluates the potential of using deep learning approaches for the detection of degenerative bone changes in the mandibular condyle. The aim of this study is to enable the detection and diagnosis of mandibular condyle degenerations, which are difficult to observe and diagnose on panoramic radiographs, using deep learning methods. Methods: A total of 3875 condylar images were obtained from panoramic radiographs. Condylar bone changes were represented by flattening, osteophyte, and erosion, and images in which two or more of these changes were observed were labeled as “other”. Due to the limited number of images containing osteophytes and erosion, two approaches were used. In the first approach, images containing osteophytes and erosion were combined into the “other” group, resulting in three groups: normal, flattening, and deformation (“deformation” encompasses the “other” group, together with osteophyte and erosion). In the second approach, images containing osteophytes and erosion were completely excluded, resulting in three groups: normal, flattening, and other. The study utilizes a range of advanced deep learning algorithms, including Dense Networks, Residual Networks, VGG Networks, and Google Networks, which are pre-trained with transfer learning techniques. Model performance was evaluated using datasets with different distributions, specifically 70:30 and 80:20 training-test splits. Results: The GoogleNet architecture achieved the highest accuracy. Specifically, with the 80:20 split of the normal-flattening-deformation dataset and the Adamax optimizer, an accuracy of 95.23% was achieved. The results demonstrate that CNN-based methods are highly successful in determining mandibular condyle bone changes. Conclusions: This study demonstrates the potential of deep learning, particularly CNNs, for the accurate and efficient detection of TMJ-related condylar bone changes from panoramic radiographs. This approach could assist clinicians in identifying patients requiring further intervention. Future research may involve using cross-sectional imaging methods and training the right and left condyles together to potentially increase the success rate. This approach has the potential to improve the early detection of TMJ-related condylar bone changes, enabling timely referrals and potentially preventing disease progression.

Early diagnosis of dental caries has become increasingly important in recent years. It reduces irreversible tooth loss, treatment costs and treatment time. However, since the examination of dental caries is carried out visually by experts on radiographic images, the analysis process is quite exhausting for the experts. In addition, visual analysis may miss early-stage caries due to the workload in the clinical environment. In this study, an automatic caries diagnosis system is proposed to support the expert and to reduce the clinical workload by using panoramic images. The proposed DenseNet121-C model, based on deep learning models, generates results with its configured classifier for caries detection. The dataset prepared for the study includes 14498 tooth images automatically cropped from panoramic images. The proposed model achieved the highest performance on the test set with 93.17% accuracy, 89.43% precision, 85.84% recall, and 87.49% F1-score. Considering the high results of the current study, dentists can spend more time on treatment during dental examinations, thanks to the model’s ability to distinguish between caries and non-caries teeth. The results obtained were compared with the Mask R-CNN results. In addition, the performance of the deep learning architectures was investigated on an unbalanced dataset.

The purpose of this study was to investigate changes in bone trabecular structure during adolescence using the fractal analysis (FA) method on hand–wrist radiographs (HWRs) and to evaluate the relationship of these changes with pubertal growth stages. HWRs of healthy individuals aged 8–18 years were included (N = 600). Pubertal stages were determined by the Fishman method and divided into 10 groups (early puberty [EP], pre-peak [PRPK], peak [PK], post-peak [PTPK], late puberty [LP]). FA was performed using FIJI (ImageJ) software and the BoneJ plugin on circular regions of interest (ROIs) selected from the first metacarpal bone head and distal radius. Image processing steps were applied according to the White and Rudolph method. Differences between groups were statistically evaluated. Fractal dimension (FD) values of the distal radius (RAFAM) and metacarpal bone head (MAFAM) showed significant differences according to pubertal growth stages (p < 0.05). The highest FD value was observed in the LP group, and the lowest FD value was observed in the EP group (except MAFAM in females). FD generally increased from EP to LP in the whole population, but a significant decrease was observed in all groups during the PK period. This decrease was more pronounced in RAFAM of males. These findings suggest a potential decrease of bone mechanical properties in the PK, which is found the be more suitable for orthodontic treatment in the literature. FA on HWRs is a useful and sensitive tool for quantitatively assessing pubertal changes in trabecular bone microarchitecture. The findings demonstrate a significant decrease in FD in both bone regions during the pubertal growth spurt, particularly at the peak period. This may indicate a temporary reduction in bone mechanical strength during this critical stage and could contribute to increased distal radius fracture incidence. Clinically, the relationship between FD and pubertal stages suggests this method could serve as a valuable biomarker in orthodontic treatment planning, allowing for optimized timing of interventions. Furthermore, it may aid in pediatric fracture risk assessment, potentially leading to preventative strategies for high-risk individuals.

Objectives: Fractal analysis is a method employed in the medical and dental fields to examine the microarchitecture of bone tissue on a range of radiographic images. For this, it is achieved through the utilization of diverse image-processing techniques and mathematical operations. In the context of periodontal diseases, the evaluation of bone tissue plays a pivotal role in diagnosing the disease. The objective of this study was to analyze the mandibular bone of individuals with periodontitis stage II grade B on panoramic X-ray images using the fractal analysis method. Methods: In this study, the angulus region, the premolar/molar region, and the incisive region of the mandibular bone were identified as relevant regions for fractal analysis on panoramic images of 50 healthy individuals and 50 patients diagnosed with periodontitis stage II grade B by a specialist periodontologist. Consequently, fractal dimensions were calculated for 300 regions of interest across a total of 100 images. Fractal analysis was conducted using the Image J program, a freely available software, using the White and Rudolph method. The fractal dimension was measured in three regions of the mandible, and the results were statistically analyzed with Python using the independent groups’ t-test to evaluate the fractal dimension in the patient and control groups. Results: The statistical tests revealed no significant difference between the patient and control groups in terms of fractal dimensions in the angulus and molar regions (p>0.05). However, a difference was observed between the groups in the incisive region (p<0.05). Conclusion: The microarchitecture of bone tissue in the mandible is adversely affected by periodontal disease. Fractal analysis can provide supplementary data for evaluating bone in the field of periodontology.