|
Application of Artificial Intelligence in Dental Caries Detection: Advances and Challenges
|
Mitra Montazerlotf   , Mehrdad Hosseini Shakib * , Reza Radfar , Mina Khayamzadeh |
| , mehrdad.shakib@kiau.ac.ir |
|
|
Abstract: (16 Views) |
Background and Aim: Dental caries is the most prevalent chronic disease worldwide, requiring early diagnosis to prevent invasive treatments. Traditional detection methods have limitations, particularly in detecting early lesions. The aim of this study is to review the advances and challenges of artificial intelligence applications in dental caries detection.
Material and Method: A narrative review of articles published between 2015-2025 was conducted using established scientific databases including PubMed, Scopus, Science Direct, IEEE Xplore, Web of Science, and Google Scholar. Study quality was assessed using the QUADAS-2 tool, and data were analyzed based on artificial intelligence methods, imaging modalities, and performance metrics.
Results: Convolutional Neural Networks (CNNs) and their derivatives such as U-Net, Mask R-CNN, and DenseNet are the most widely used algorithms in caries detection. The diagnostic accuracy of these systems was comparable to or better than dental specialists in many cases, particularly for early lesion detection. Artificial intelligence performance across different dental imaging modalities ranged from 71% to 99.2%.
Conclusion: Artificial intelligence demonstrates significant potential for revolutionizing dental caries detection, particularly in identifying early lesions that are crucial for non-invasive preventive interventions. The optimal approach is "assistive artificial intelligence" that serves as a complement to human clinical judgment rather than a replacement. Main challenges include dataset limitations, lack of standardization in methods and reporting, clinical workflow integration problems, need for transparency and explainability, and ethical-legal concerns. Future directions include developing larger and more diverse datasets, multimodal approaches, improving model explanation methods, conducting longitudinal clinical studies, and developing appropriate standards.
|
|
| Keywords: Artificial Intelligence, Dental Caries, Deep Learning, Dental Radiography, Convolutional Neural Network |
|
|
Full-Text [PDF 714 kb]
(13 Downloads)
|
|
Type of Study: Review article |
Subject:
Oral Medicine
|
|
|
|
|
|
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
