Evaluating the success of an artificial intelligence algorithm in identifying fixed partial dentures on panoramic radiographs

Evaluating the Success of an Artificial Intelligence Algorithm in Identifying Fixed Partial Dentures on Panoramic Radiographs Objective: This study aimed to automatically classify zirconia veneer and metal-supported porcelain veneer restorations on panoramic radiographs using an artificial intelligence-based model. Unlike previous studies that mainly focused on classifying types of restorations (e.g., crowns, fillings, implants), this research concentrated on material-based differentiation, aiming to provide a more specific contribution to clinical decision support systems. Method: Panoramic radiographs obtained from the archive of Süleyman Demirel University, Faculty of Dentistry were used in this study. Radiographs with poor image quality and missing teeth were excluded from the study. At the end of the preprocessing process, a total of 593 cropped ROI (Region of Interest) images labelled by the expert using ImageJ software were included in the analysis. In order to reduce class imbalance, data augmentation was applied only for images in the zirconium veneer class. By using various image processing techniques such as rotation, reflection and brightness change, the number of samples in the zirconium class was increased and thus a balanced data set was obtained with a close number of samples for both classes. For model training, the pre-trained VGG16 architecture was used with transfer learning method and the final layers were retrained and fine-tuned. The model was configured to focus only on the classification task. The entire dataset was randomly split into 70% training, 20% validation and 10% testing. The classification performance of the model was evaluated based on key performance metrics such as accuracy, F1 score, sensitivity and specificity. Results: The model correctly classified 90 out of 94 images in the test dataset, achieving an overall accuracy rate of 96%. For both classes, the precision, recall, and F1-score values were measured in the range of 95% to 96%. Additionally, the Area Under the Curve (AUC) of the ROC curve was calculated as 0.994, and the Average Precision (AP) score was determined to be 0.995. According to the confusion matrix results, only 4 images were misclassified, consisting of 2 false positives and 2 false negatives. Conclusion: As a result of the study, it was observed that the artificial intelligence model developed in this study was able to distinguish zirconium veneers and metal-supported porcelain veneers with high accuracy. This material-based classification approach is remarkable in terms of both technical success and clinical applicability as one of the first in the literature. The performance values achieved by the model show that artificial intelligence has a significant discrimination in this specific task. In this respect, the study provides a unique and usable basis for future clinical decision support systems. Keywords:Artificial Intelligence, Zirconium Veneer, Metal Supported Porcelain Veneer