Related Experiment Video
Updated: May 5, 2026
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
Published on: August 5, 2021
Development and evaluation of an artificial intelligence (AI) model for detecting dental caries from 3D intraoral
Walaa Magdy Ahmed1, Amr Ahmed Azhari1, Rabab Alnakhli2
1Assistant Professor, Department of Restorative Dentistry, Faculty of Dentistry, King Abdulaziz University, Jeddah, Saudi Arabia.
Statement Of Problem:
Intraoral scanners and artificial intelligence (AI) have been widely used for caries detection because they save time and improve the caries diagnosis process. However, early caries detection remains a challenge, and dentists rely on subjective methods for diagnosis.
Purpose:
The purpose of this clinical trial was to develop and evaluate the performance of an AI model for caries detection by integrating intraoral scans of permanent teeth with the traditional diagnostic clinical examination method to enhance diagnostic performance and reduce subjectivity. The developed model was compared with conventional caries detection methods.
Material And Methods:
This clinical trial was conducted at the King Abdulaziz University Dental Hospital in Jeddah, Saudi Arabia. Participants were randomly selected, and 66 intraoral scans were obtained. The AI model was evaluated using intersection over union (IoU), F-score, sensitivity, specificity, overall accuracy, and confusion matrix.
Results:
The model achieved an average IoU score of 0.78, demonstrating a high level of overlap and accuracy in caries detection. The F-score of 0.85 indicated a strong balance between accuracy and recall. With a sensitivity of 91% and a specificity of 88%, the model effectively identified 91% of caries. Its overall accuracy of 89.5% underscores its success in detecting caries across intraoral scans.
Conclusions:
The use of novel automated techniques combined with conventional diagnostic methods can improve the accuracy of caries detection, aiding successful treatment planning and decision-making and leading to better outcomes.
