Related Experiment Video
Updated: Aug 15, 2026
05:49
Reliability of Artificial Intelligence-Based Cone Beam Computed Tomography Integration with Digital Dental Images
Published on: February 23, 2024
Artificial Intelligence in the Imaging-Based Analysis of Third Molars: A Systematic Review
Ana L S Sandim1, Letícia S de Andrade2, Ronaldo Luis Almeida de Carvalho3
1Master's Student, Postgraduate Program in Clinical Dentistry, Federal University of Juiz de Fora, Juiz de Fora, Minas Gerais, Brazil.
Summary
Artificial intelligence (AI) shows promise in analyzing third molar images for detection and classification. However, complex tasks like surgical planning require further development and validation for clinical use.
Area of Science:
- Dentistry
- Medical Imaging
- Artificial Intelligence
Background:
- Artificial intelligence (AI) is increasingly applied to dental imaging analysis.
- Third molar (wisdom tooth) imaging analysis presents unique challenges.
- This review synthesizes evidence on AI for third molar imaging.
Purpose of the Study:
- Evaluate AI methods for third molar detection.
- Assess AI for third molar classification.
- Examine AI's role in surgical planning for third molars.
Main Methods:
- Systematic review of PubMed, Scopus, and Web of Science databases.
- Included studies developing, validating, or evaluating AI for third molar imaging.
- Assessed risk of bias and applicability using QUADAS-2 tool.
Main Results:
- 32 studies met eligibility criteria, primarily using convolutional neural networks (CNNs) and panoramic radiography.
- AI demonstrated varied performance in detection, segmentation, classification, and surgical difficulty prediction.
- Methodological heterogeneity and limited external validation were noted, especially for complex tasks.
Conclusions:
- AI shows potential for third molar detection and classification in dental imaging.
- Further methodological refinement and external validation are needed for complex tasks.
- Clinical integration of AI for third molar analysis requires further assessment.
