In the present study, the structural, morphological, and in vivo biocompatibility of un-doped and boron (B)-doped strontium apatite (SrAp) nanoparticles were investigated. Biomaterials were fabricated using the hydrothermal process. The structural and morphological characterizations of the fabricated nanoparticles were performed by XRD, FT-IR, FE-SEM, and EDX. Their biocompatibility was investigated by placing them in defects in rat tibiae in vivo. The un-doped and B-doped SrAp nanoparticles were successfully fabricated. The produced nanoparticles were in the shape of nano-rods, and the dimensions of the nano-rods decreased as the B ratio increased. It was observed that the structural and morphological properties of strontium apatite nanoparticles were affected by the contribution of B. A stoichiometric Sr/P ratio of 1.67 was reached in the 5% B-doped sample (1.68). The average crystallite sizes were 34.94 nm, 39.70 nm, 44.93 nm, and 48.23 nm in un-doped, 1% B-doped, 5% B-doped, and 10% B-doped samples, respectively. The results of the in vivo experiment revealed that the new bone formation and osteoblast density were higher in the groups with SrAp nanoparticles doped with different concentrations of B than in the control group, in which the open defects were untreated. It was observed that this biocompatibility and the new bone formation were especially elevated in the B groups, which added high levels of strontium were added. The osteoblast density was higher in the group in which the strontium element was placed in the opened bone defect compared with the control group. However, although new bone formation was slightly higher in the strontium group than in the control group, the difference was not statistically significant. Furthermore, the strontium group had the highest amount of fibrotic tissue formation. The produced nanoparticles can be used in dental and orthopedic applications as biomaterials.

Objectives: This study aimed to develop and validate a hybrid deep learning model combining Convolutional Neural Networks (CNN) and Vision Transformers (ViT) to automatically classify maxillary sinus membrane morphologies on Cone-Beam Computed Tomography (CBCT) images, distinguishing between Normal, Flat, Polypoid, and Obstruction types. Methods: A dataset of 959 CBCT images was collected and categorized into four morphological classes: Normal, Flat, Polypoid and Obstruction. A custom hybrid model was developed, integrating a lightweight residual CNN for local feature extraction, learnable weighted feature fusion with a bidirectional feature pyramid network and a Transformer encoder for global context modeling. The performance of proposed model was compared against six different architectures, including ResNet50, MobileNetV3L and standard ViT models, using accuracy, precision, recall and F1-score metrics. Results: The proposed hybrid model achieved the highest overall accuracy of 98.44%, outperforming six strong CNN and ViT models including ResNet50 (97.92%) and ViT-B16 (86.46%) models. In class-wise analysis, the model demonstrated superior diagnostic capability, particularly for the “Obstruction” class, achieving 100% accuracy. High discrimination was also observed for “Flat” (98.21%) and “Polypoid” (98.04%) morphologies, confirming the model’s sensitivity to shape-based features. Conclusions: The proposed hybrid CNN-ViT model successfully classifies maxillary sinus membrane morphologies with high accuracy, effectively overcoming the limitations of standard ViT models on limited datasets. Detection of membrane morphology is vital for predicting surgical risks like membrane perforation and post-operative sinusitis. This model serves as a reliable clinical decision support tool, enabling clinicians to objectively assess specific risk factors before implant surgery and sinus floor elevation.

Background and Objective: The aim of this study was to evaluate the effects of enamel matrix protein, platelet-rich fibrin (PRF), and bone graft on new bone formation beyond the skeletal system by creating calvarial bone defects in rats. The effects were assessed using histopathological and immunohistochemical analyses. Materials and Methods: In this study, calvarial bone defects were created in male Sprague Dawley rats weighing 500–550 g. The animals were randomly divided into seven groups: Control (n = 13), Emdogain (EMD, n = 13), Emdogain + Bone Graft (EMD + BG, n = 13), Platelet-Rich Fibrin (PRF, n = 13), PRF + Bone Graft (PRF + BG, n = 13), Bone Graft (BG, n = 13), and PRF + Emdogain + Bone Graft (PRF + EMD + BG, n = 13). An additional group of 36 rats was used for PRF preparation. Titanium domes were placed on the calvarial bone defects, and the animals were sacrificed after three months. Bone samples were evaluated histopathologically for new bone formation, numbers of osteoblasts and osteoclasts, angiogenesis, and fibrosis. Immunohistochemical analysis of bone formation was performed using OPG and RANKL staining kits. Data were analyzed statistically. Results: The PRF group showed a significantly higher level of moderate new bone formation compared with the PRF + BG, EMD + BG, and PRF + EMD + BG groups (p ≤ 0.05). No significant differences were observed among the groups in terms of fibrosis or angiogenesis (p > 0.05). Similarly, OPG and RANKL levels, as well as the OPG/RANKL ratio, did not differ significantly between groups (p > 0.05). Conclusions: Based on the findings of this study, the combined use of Emdogain, PRF, and bone graft appears to have beneficial effects on enhancing bone formation in calvarial defects.

Background/Objectives: The aim of this study is to test different convolutional neural network (CNN) and Transformer-based models to detect and classify vertical misfit at the abutment-prosthesis interface on panoramic radiographs, and to develop a hybrid deep learning model enhanced with attention mechanisms. Methods: A dataset consisting of a total of 566 images, manually classified as 249 ‘fit’ and 317 ‘misfit’ cases by two experts, was created. Images were resized to 224 × 224 and divided into training, validation, and test groups. The deep learning model yielding the most successful results was determined as the backbone; a hybrid model was developed by integrating three different attention modules (SE, CBAM, and ECA) into this structure. Model performance was evaluated using accuracy, precision, sensitivity, and F1 score metrics. Results: CNN-based models (RegNetY-800MF, ConvNeXt-Tiny, EfficientNetV2-S, ResNet50) performed better than Transformer-based models (DeiT, Swin-Tiny) in all metrics. The proposed hybrid model exhibited the highest success among all tested models with a 99.12% accuracy rate. This model reached a 100% precision value in the misfit group and yielded no false positive results. The F1 scores of the hybrid model were recorded as 99.01% for the fit group and 99.21% for the misfit group. Conclusions: The findings of this study demonstrate that attention-enhancing deep learning frameworks have the potential to significantly improve the diagnostic utility of routine panoramic radiographs. It shows that panoramic imaging, when supported by advanced artificial intelligence, can provide valuable diagnostic support in detecting vertical misfit. The developed model has the potential to become a reliable clinical decision support system.