The purpose of the paper was the assessment of the success of an artificial intelligence (AI) algorithm formed on a deep‐convolutional neural network (D‐CNN) model for the segmentation of apical lesions on dental panoramic radiographs. A total of 470 anonymized panoramic radiographs were used to progress the D‐CNN AI model based on the U‐Net algorithm (CranioCatch, Eskisehir, Turkey) for the segmentation of apical lesions. The radiographs were obtained from the Radiology Archive of the Department of Oral and Maxillofacial Radiology of the Faculty of Dentistry of Eskisehir Osmangazi University. A U‐Net implemented with PyTorch model (version 1.4.0) was used for the segmentation of apical lesions. In the test data set, the AI model segmented 63 periapical lesions on 47 panoramic radiographs. The sensitivity, precision, and F1‐score for segmentation of periapical lesions at 70% IoU values were 0.92, 0.84, and 0.88, respectively. AI systems have the potential to overcome clinical problems. AI may facilitate the assessment of periapical pathology based on panoramic radiographs.

The assessment of alveolar bone loss, a crucial element of the periodontium, plays a vital role in the diagnosis of periodontitis and the prognosis of the disease. In dentistry, artificial intelligence (AI) applications have demonstrated practical and efficient diagnostic capabilities, leveraging machine learning and cognitive problem-solving functions that mimic human abilities. This study aims to evaluate the effectiveness of AI models in identifying alveolar bone loss as present or absent across different regions. To achieve this goal, alveolar bone loss models were generated using the PyTorch-based YOLO-v5 model implemented via CranioCatch software, detecting periodontal bone loss areas and labeling them using the segmentation method on 685 panoramic radiographs. Besides general evaluation, models were grouped according to subregions (incisors, canines, premolars, and molars) to provide a targeted evaluation. Our findings reveal that the lowest sensitivity and F1 score values were associated with total alveolar bone loss, while the highest values were observed in the maxillary incisor region. It shows that artificial intelligence has a high potential in analytical studies evaluating periodontal bone loss situations. Considering the limited amount of data, it is predicted that this success will increase with the provision of machine learning by using a more comprehensive data set in further studies.

Objectives: The aim of this study was to detect alveolar bone loss from dental panoramic radiographic images using artificial intelligence systems. Material and Methods: A total of 2276 panoramic radiographic images were used in this study. While 1137 of them belong to cases with bone destruction, 1139 were periodontally healthy. The dataset is divided into three parts as training (n=1856) , validation (n=210) and testing set (n= 210). All images in the data set were resized to 1472x718 pixels before training. A random sequence was created using the open-source python programming language and OpenCV, NumPy, Pandas, and Matplotlib libraries effectively. A pre-trained Google Net Inception v3 CNN network was used for preprocessing and data sets were trained using transfer learning. Diagnostic performance was evaluated with the confusion matrix using sensivitiy, specificity, precision, accuracy and F1 score. Results: Of the 105 cases with bone loss, 99 were detected by the AI system. Sensitivity was 0.94, specificity 0.88, precision 0.89, accuracy 0.91 and F1 score 0.91. Conclusion: The convolutional neural network model is successful in determining periodontal bone losses. It can be used as a system to facilitate the work of physicians in diagnosis and treatment planning in the future.

Objectives: The present study aimed to evaluate the performance of a Faster Region-based Convolutional Neural Network (R-CNN) algorithm for tooth detection and numbering on periapical images. Methods: The data sets of 1686 randomly selected periapical radiographs of patients were collected retrospectively. A pre-trained model (GoogLeNet Inception v3 CNN) was employed for pre-processing, and transfer learning techniques were applied for data set training. The algorithm consisted of: (1) the Jaw classification model, (2) Region detection models, and (3) the Final algorithm using all models. Finally, an analysis of the latest model has been integrated alongside the others. The sensitivity, precision, true-positive rate, and false-positive/negative rate were computed to analyze the performance of the algorithm using a confusion matrix. Results: An artificial intelligence algorithm (CranioCatch, Eskisehir-Turkey) was designed based on R-CNN inception architecture to automatically detect and number the teeth on periapical images. Of 864 teeth in 156 periapical radiographs, 668 were correctly numbered in the test data set. The F1 score, precision, and sensitivity were 0.8720, 0.7812, and 0.9867, respectively. Conclusion: The study demonstrated the potential accuracy and efficiency of the CNN algorithm for detecting and numbering teeth. The deep learning-based methods can help clinicians reduce workloads, improve dental records, and reduce turnaround time for urgent cases. This architecture might also contribute to forensic science.