RESEARCH AND EDUCATION Dual convolutional neural network framework for segmenting dental caries in panoramic radiographs

초록

Statement of problem. Dental caries, a widespread chronic disease, has been difficult to detect, especially in posterior proximal regions. Conventional diagnostic methods, such as visual inspection and radiography, are subjective and inconsistent across clinicians. Purpose. The purpose of this study was to develop and evaluate a deep learning-based method for automated detection and segmentation of dental caries in panoramic radiographs. Material and methods. A deep learning pipeline combining Faster Regions based Convolutional Neural Networks (R-CNN) and U-Net architectures was developed. The Faster R-CNN model was used to detect tooth regions, and the U-Net model segmented carious areas within these regions. Performance differences against comparative models were evaluated for statistical significance using paired t tests (alpha=.05). Results. The proposed method achieved an intersection over union of 0.6075, a dice coefficient of 0.7429, a recall of 0.7309, and a precision of 0.7881. This performance represented an improvement in intersection over union, dice coefficient, and recall over conventional segmentation models, with the difference being statistically significant (P<.05). Conclusions. The results indicated that the proposed deep learning method was effective in detecting and segmenting dental caries in panoramic radiographs and showed potential for improving diagnostic accuracy.

키워드