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.

The dimensional accuracy of impression materials has been evaluated for a long time, but thus far, digital radiography has not been used for this purpose. The dimensional accuracy of impression materials is very important for the final adaptation of dental prostheses. The objective of this study was to evaluate the effects of different disinfectant solutions and storage times on the dimensional stability of different impression materials by means of digital radiography. Polyether (PE), hydrocolloid (IH), condensation silicone (CS), and addition silicone (AS) materials were used for preparing impressions, taken from an acrylic master model with 2 vertical and 2 horizontal reference points. Water (W), sodium hypochlorite (SH) and a disinfectant solution without aldehyde (Z) were applied on the impressions. Half of the impressions were poured over immediately and half of them - 1 day after. Digital radiography was used to determine the dimensional accuracy of the impression materials. The data was analyzed with a variance analysis and Tukey's multiple comparison test. While PE showed the smallest dimensional changes, IH showed the greatest in all lines. Applying SH and pouring 1 day after caused the greatest dimensional changes in all impression materials. Different disinfectant solutions and storage times had a different effect on the impressions, but the dimensional changes were clinically acceptable.

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.