Related Experiment Video
Updated: Sep 12, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
991
Toward Precision Diagnosis of Maxillofacial Pathologies by Artificial Intelligence Algorithms: A Systematic Review
Meysam Rahmanzadeh1, Auob Rustamzadeh2, Enam Alhagh Gorgich3
1Department of Dentistry School, Alborz University of Medical Sciences, Karaj, Iran.
Journal of Maxillofacial and Oral Surgery
|August 4, 2025
Summary
Artificial intelligence, including machine learning and deep learning, enhances oral and maxillofacial disease diagnosis using advanced imaging like CBCT. These AI tools show high accuracy, often surpassing human radiologists in identifying dental and odontogenic disorders.
Area of Science:
- Oral and Maxillofacial Radiology
- Artificial Intelligence in Medicine
- Medical Imaging Analysis
Background:
- Oral and maxillofacial diseases require accurate and timely diagnosis for effective management.
- Advanced imaging techniques like computed tomography (CT) and cone-beam computed tomography (CBCT) provide detailed anatomical information.
- The integration of artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), offers new avenues for improving diagnostic capabilities.
Purpose of the Study:
- To review the application of AI algorithms (ML and DL) in the diagnosis and management of oral and maxillofacial diseases.
- To evaluate the role of advanced imaging techniques (CT, CBCT) in conjunction with AI for improved diagnostic accuracy.
- To highlight the potential of AI in interpreting complex maxillofacial pathologies from radiographic data.
Main Methods:
- A comprehensive literature search was conducted across major databases: Web of Science, PubMed, Scopus, and Google Scholar.
- The review focused on studies published between 2010 and 2024, utilizing keywords related to radiography, MRI, CT, CBCT, ML, DL, and maxillofacial pathology.
- Emphasis was placed on studies reporting clinical applications and diagnostic performance metrics of AI in oral and maxillofacial imaging.
Main Results:
- Deep learning algorithms achieved high diagnostic accuracy for vertical root fractures (e.g., 89.0% for premolars) and CBCT image evaluation (93%).
- Specific DL architectures like GoogLeNet Inception v3 demonstrated superior performance (AUC 0.914) on CBCT compared to panoramic radiography (AUC 0.847) for certain pathologies.
- CBCT imaging showed higher diagnostic accuracy (91.4%) than panoramic images (84.6%), particularly for odontogenic cystic lesions. DL models also showed strong performance in lymph node classification.
Conclusions:
- Cone-beam computed tomography (CBCT) offers superior anatomical detail crucial for diagnosing oral and dentomaxillofacial disorders.
- Deep learning algorithms exhibit high accuracy and sensitivity in diagnosing various dental and odontogenic conditions.
- AI-powered diagnostic tools show potential to match or exceed the performance of human radiologists in specific maxillofacial imaging tasks.
Keywords:
Artificial intelligenceCone-beam computed tomographyDiagnosisMaxillofacial pathologyRadiology
