Background/Objectives: Dental age estimation is a vital component of forensic science, helping to determine the identity and actual age of an individual. However, its effectiveness is challenged by methodological variability and biological differences between individuals. Therefore, to overcome the drawbacks such as the dependence on manual measurements, requiring a lot of time and effort, and the difficulty of routine clinical application due to large sample sizes, we aimed to automatically estimate tooth age from panoramic radiographs (OPGs) using artificial intelligence (AI) algorithms. Methods: Two-Dimensional Deep Convolutional Neural Network (2D-DCNN) and One-Dimensional Deep Convolutional Neural Network (1D-DCNN) techniques were used to extract features from panoramic radiographs and patient records. To perform age estimation using feature information, Genetic algorithm (GA) and Random Forest algorithm (RF) were modified, combined, and defined as Modified Genetic–Random Forest Algorithm (MG-RF). The performance of the system used in our study was analyzed based on the MSE, MAE, RMSE, and R2 values calculated during the implementation of the code. Results: As a result of the applied algorithms, the MSE value was 0.00027, MAE value was 0.0079, RMSE was 0.0888, and R2 score was 0.999. Conclusions: The findings of our study indicate that the AI-based system employed herein is an effective tool for age detection. Consequently, we propose that this technology could be utilized in forensic sciences in the future.
Progressive sinus pneumatization, stable sinus graft height and shrinkage of the graft material after maxillary sinus augmentation represent limitations for clinical practice. Seventy-eight maxillary sinus floor augmentations and 83 dental implant positions were performed on 60 patients. The lateral window approach was used for maxillary sinus floor augmentation. A collagenated porcine bone xenograft (OsteoBiol® Gen-Os®, Tecnoss®, Giaveno, Italy) and a collagen membrane (OsteoBiol® Evolution, Tecnoss®, Giaveno, Italy) were used as grafting materials. Vertical bone gain was analyzed immediately after surgery (T1) and after 4 months (T2) via panoramic radiographic measurements with respect to residual bone height (T0), which was measured preoperatively. Graft height changes were evaluated with respect to implant location, diameter, length, brand and sinus graft width. The mean vertical bone gain per implant following simultaneous maxillary sinus augmentation at sites with a residual bone height of less than 4 mm (11.14 ± 1.87 mm) was the highest among all groups (p < 0.001) at the time of baseline surgery. The mean vertical bone gain at the grafted sinus height was significantly lower at 4 months (13.78 ± 1.24 mm) than at baseline (14.58 ± 1.31 mm) (p < 0.001). Four months after baseline surgery, a statistically significant decrease of 5.49% in the change in graft height was associated with graft contraction (p < 0.001). When the mean graft height changes were compared according to the implant location, diameter, length, brand and sinus graft width, no statistically significant differences were observed (p > 0.05). Within the limits of this retrospective study, collagenated porcine bone xenografts can be used successfully as a sinus augmentation material with simultaneous implant positioning and may contribute to improved graft shrinkage in the short term.
Platelet-rich fibrin (PRF) contains a variety of growth factors and bioactive molecules that play crucial roles in wound healing and angiogenesis. We aimed to evaluate the effects of PRF on tissue thickness and vascularization of the palatal donor site by ultrasound (USG) following subepithelial connective tissue harvesting.
Objectives: To reduce the problems arising from the inability to identify dental implant brands, this study aims to classify various dental implant brands using deep learning algorithms on panoramic radiographs. Methods: Images of 4 different dental implant systems (NucleOSS, Medentika, Nobel, and Implance) were used from a total of 5375 cropped panoramic radiographs. To enhance image clarity and reduce blurriness, the contrast limited adaptive histogram equalization filter was applied. GoogleNet, ResNet-18, VGG16, and ShuffleNet deep learning algorithms were utilized to classify the 4 different dental implant systems. To evaluate the classification performance of the algorithms, Receiver Operating Characteristic (ROC) curves and confusion matrices were generated. Based on these confusion matrices, accuracy, precision, sensitivity, and F1 score were calculated. The Z-test was used to compare the performance metrics across different algorithms. Results: The accuracy rates of the deep learning algorithms were obtained as 96.00% for GoogleNet, 84.40% for ResNet-18, 98.90% for VGG16, and 84.80% for ShuffleNet. A statistically significant difference was found between the accuracy rate of the VGG16 algorithm and those of GoogleNet, ShuffleNet, and ResNet-18 (P < .001, P < .001, and P < .001, respectively). Conclusions: With the achievement of high accuracy rates, deep learning algorithms are considered a valuable and powerful method for identifying dental implant brands.
9 January 2026 in Journal of Oral and Maxillofacial Surgery
Amaç: Bu çalışmanın amacı; sublingual varis (SLV) görülme prevalansını değerlendirmek ve yaş, cinsiyet, hipertansiyon, kalp-damar hastalıkları, kronik öksürük, diyabet ve diğer sistemik hastalıklar, alt ekstremitelerde varis varlığı, hareketli protez kullanımı, sigara kullanımı gibi SLV oluşumu ile daha önce önerilen bazı potansiyel risk faktörleri arasındaki ilişkiyi araştırmaktır. Gereç ve Yöntemler: Bu araştırmaya 362’si kadın (%58.3), 259’u erkek (%41.7) olmak üzere toplamda 621 birey dahil edilmiştir. Katılımcılar rutin klinik muayene için başvuran, sözlü ve yazılı bilgilendirme sonucu çalışmaya katılmayı kabul eden ve çalışmaya dahil edilme kriterlerini sağlayan bireylerdir. Dilin lateral ve ventral yüzeylerden fotoğrafları alındıktan sonra bireylerin demografik ve medikal bilgilerine kör iki ayrı gözlemci tarafından SLV varlığı izlenemeyen ve az izlenenler 0, orta ve ileri derecede izlenenler ise 1 olarak skorlanmıştır. Gözlemciler arası uyumu değerlendirmek için Kappa testi, verilerin analizinde ise pearson ki- kare ve lojistik regresyon analizi uygulanmıştır. Bulgular: Gözlemciler arasındaki uyum Kappa testiyle analiz edilmiş ve çok yüksek uyum tespit edilmiştir (κ=0.918). Çalışmaya dahil edilmiş 621 bireyin 155’inde (%24.9) orta ve ileri derecede SLV olduğu görülmüştür. Cinsiyetler arasında SLV görülme prevalansı açısından bir fark belirlenmezken (p=0.278), yaşla birlikte artış gösterdiği tespit edilmiştir (p=0.000). SLV hipertansiyon (p=0.048), kronik öksürük varlığı (p=0.009) ve alt ekstremitede varis varlığı (p