Related Experiment Video
Updated: Jul 9, 2026
05:49
Reliability of Artificial Intelligence-Based Cone Beam Computed Tomography Integration with Digital Dental Images
Published on: February 23, 2024
Assessment of artificial intelligence in detecting errors on panoramic radiographs
Tarek Abdallah Abdel Salam1,2, Ahmed Montaser Abdelsalam2, Nada Reda Sholkamy2
1Department of Oral Radiology and Laser, Faculty of Dentistry, Aswan University, Aswan, Egypt.
Imaging Science in Dentistry
|July 8, 2026
Summary
Artificial intelligence (AI) shows promise in detecting errors in dental panoramic radiographs. The Attention Dental X-ray model achieved the highest accuracy, suggesting AI can improve radiographic quality assurance.
Area of Science:
- Radiology
- Artificial Intelligence
- Dental Imaging
Background:
- Panoramic radiography is crucial in dental diagnostics.
- Image quality is essential for accurate diagnosis and treatment planning.
- Errors in panoramic radiographs can lead to misdiagnosis and suboptimal patient care.
Purpose of the Study:
- To evaluate the efficacy of artificial intelligence (AI) in identifying common errors in panoramic radiographs.
- To compare the performance of different deep learning models in detecting specific radiographic errors.
- To explore AI's potential role in enhancing quality assurance in dental radiography.
Main Methods:
- A retrospective analysis of 2,888 anonymized panoramic radiographs was conducted.
- Three deep learning models (Attention Dental X-ray, ResNet50, MobileNet) were developed and trained.
- Model performance was assessed using accuracy, precision, sensitivity, AUC, and F1 score with 5-fold cross-validation.
Main Results:
- The Attention Dental X-ray model outperformed ResNet50 and MobileNet in error detection.
- Attention Dental X-ray achieved 82.7% accuracy in classifying tongue space errors.
- ResNet50 and MobileNet achieved accuracies of 56.9% and 64.1%, respectively.
Conclusions:
- AI models, especially those with attention mechanisms, show significant potential for detecting errors in panoramic radiographs.
- AI can serve as a valuable supplementary tool for improving image quality and reducing radiation exposure.
- Future research should explore real-time AI integration for immediate feedback and automated error correction.
