The purpose of this study is to evaluate and compare the performance of six state-of-the-art convolutional neural network (CNN)-based deep learning models for cervical vertebral maturation (CVM) on lateral cephalometric radiographs, and implement visualization of CVM classification for each model using gradient-weighted class activation map (Grad-CAM) technology. A total of 600 lateral cephalometric radiographs obtained from patients aged 6–19 years between 2013 and 2020 in Pusan National University Dental Hospital were used in this study. ResNet-18, MobileNet-v2, ResNet-50, ResNet-101, Inception-v3, and Inception-ResNet-v2 were tested to determine the optimal pre-trained network architecture. Multi-class classification metrics, accuracy, recall, precision, F1-score, and area under the curve (AUC) values from the receiver operating characteristic (ROC) curve were used to evaluate the performance of the models. All deep learning models demonstrated more than 90% accuracy, with Inception-ResNet-v2 performing the best, relatively. In addition, visualizing each deep learning model using Grad-CAM led to a primary focus on the cervical vertebrae and surrounding structures. The use of these deep learning models in clinical practice will facilitate dental practitioners in making accurate diagnoses and treatment plans.

Bone age is a useful indicator of children's growth and development. Recently, the rapid development of deep-learning technique has shown promising results in estimating bone age. This study aimed to devise a deep-learning approach for accurate bone-age estimation by focusing on the cervical vertebrae on lateral cephalograms of growing children using image segmentation. We included 900 participants, aged 4-18 years, who underwent lateral cephalogram and hand-wrist radiograph on the same day. First, cervical vertebrae segmentation was performed from the lateral cephalogram using DeepLabv3+ architecture. Second, after extracting the region of interest from the segmented image for preprocessing, bone age was estimated through transfer learning using a regression model based on Inception-ResNet-v2 architecture. The dataset was divided into train:test sets in a ratio of 4:1; five-fold cross-validation was performed at each step. The segmentation model possessed average accuracy, intersection over union, and mean boundary F1 scores of 0.956, 0.913, and 0.895, respectively, for the segmentation of cervical vertebrae from lateral cephalogram. The regression model for estimating bone age from segmented cervical vertebrae images yielded average mean absolute error and root mean squared error values of 0.300 and 0.390 years, respectively. The coefficient of determination of the proposed method for the actual and estimated bone age was 0.983. Our method visualized important regions on cervical vertebral images to make a prediction using the gradient-weighted regression activation map technique. Results showed that our proposed method can estimate bone age by lateral cephalogram with sufficiently high accuracy.

Background and Objectives: Patients taking anticoagulants, particularly warfarin and non-vitamin K oral anticoagulants (NOACs), face an elevated risk of postoperative bleeding during minor oral surgeries, highlighting the urgent need to identify reliable predictors for bleeding complications. In this study, we evaluated the effectiveness of predictors of bleeding complications in patients receiving anticoagulants who underwent minor oral surgeries. Materials and Methods: The electronic medical and dental records of 206 patients who underwent oral surgery at the University of Ulsan Hospital between 2015 and 2023 were retrospectively reviewed. Patients were categorized into those taking warfarin and those taking NOACs, and postoperative bleeding was determined. Risk factors were statistically analyzed using the chi-square or Fisher’s exact test and Student’s t-test. Results: Among the 206 patients (86 on warfarin, 120 on NOACs), 84 (36 on warfarin, 48 on NOACs) experienced bleeding complications following their procedures. Time in the therapeutic range (TTR) and international normalized ratio (INR) values were significantly associated with bleeding complications in the warfarin group, while the type of NOAC was associated with bleeding in the NOAC group. Perioperative bleeding was significantly correlated with postoperative bleeding in both groups. Conclusions: Taken together, these findings highlight the correlations between postoperative bleeding and specific factors associated with anticoagulant drugs in patients that underwent oral surgery. Identifying these predictors can improve patient management by enhancing pre- and perioperative assessments, reducing the risk of bleeding, and optimizing surgical outcomes.

The purpose of this study was to measure bone age using an artificial intelligence program based on the Greulich-Pyle (GP) method to find out the bone age corresponding to each stage of cervical vertebral maturation (CVM) and the middle phalanx of the third finger (MP3). This study was conducted on 3,118 patients who visited pediatric dentistry at Kyung Hee University Dental Hospital and Pusan National University Dental Hospital from 2013 to 2021. The CVM stage was divided into 5 stages according to the classification by Baccetti, and the MP3 stage was divided into 5 stages according to the methods of Hägg and Taranger. Based on the GP method, bone age was evaluated using an artificial intelligence program. The pubertal growth spurt in the CVM stage was CVM II and III. The mean bone age in CVM II was 11.00 ± 1.81 years for males and 10.00 ± 1.49 years for females, and in CVM III, 13.00 ± 1.46 years for males and 12.00 ± 1.44 years for females (p < 0.0001). The pubertal growth spurt in the MP3 stage was MP3 - G stage. The bone age at the MP3 - G stage was 13.14 ± 1.07 years for males and 11.40 ± 1.09 years for females (p < 0.0001). Bone age evaluation using artificial intelligence is worth using in clinical practice, and it is expected that a faster and more accurate diagnosis will be possible.

This study aimed to develop a deep-learning model for the automatic classification of mandibular fractures using panoramic radiographs. A pretrained convolutional neural network (CNN) was used to classify fractures based on a novel, clinically relevant classification system. The dataset comprised 800 panoramic radiographs obtained from patients with facial trauma. The model demonstrated robust classification performance across 8 fracture categories, achieving consistently high accuracy and F1 scores. Performance was evaluated using standard metrics, including accuracy, precision, recall, and F1-score. To enhance interpretability and clinical applicability, explainable AI techniques—Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME)—were used to visualize the model’s decision-making process. These findings suggest that the proposed deep learning framework is a reliable and efficient tool for classifying mandibular fractures on panoramic radiographs. Its application may help reduce diagnostic time and improve decision-making in maxillofacial trauma care. Further validation using larger, multi-institutional datasets is recommended to ensure generalizability.

Horizontal ridge deficiency in the posterior mandible often necessitates augmentation to achieve optimal implant placement and ensure long-term functional success. Although recombinant human bone morphogenetic protein-2 (rhBMP-2) and acellular dermal matrix (ADM) have individually been explored for bone regeneration, their combined clinical use-especially under functional loading-remains limited. This report presents two clinical cases involving horizontal ridge augmentation using rhBMP-2-loaded ADM without the use of additional grafting material. Radiographic evaluations at 5-6 months postoperatively confirmed horizontal bone gains of 1.5 mm and 1.7 mm, respectively. The newly formed bone was continuous with the adjacent native bone and fully covered the previously exposed implant threads. No postoperative complications, including peri-implantitis or peri-implant mucositis, were observed during the 13-and 10-month follow-up periods.