Related Experiment Video
Updated: Jul 24, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
891
Deep learning for diagnostic charting on pediatric panoramic radiographs
International Journal of Computerized Dentistry
|July 7, 2023
Summary
A deep learning (DL) program effectively detected primary teeth, permanent tooth germs, and brackets on pediatric panoramic radiographs. While promising, the AI model showed limitations in identifying fillings and root canal treatments.
Area of Science:
- Dentistry
- Artificial Intelligence
- Medical Imaging
Background:
- Artificial intelligence (AI) systems enhance diagnostic accuracy and efficiency in dentistry.
- Deep learning (DL) models are increasingly applied to analyze medical images.
Purpose of the Study:
- Evaluate a DL program's performance in detecting and classifying dental structures and treatments.
- Assess the diagnostic capabilities of AI on pediatric panoramic radiographs.
Main Methods:
- Utilized YOLOv4, a Convolutional Neural Networks (CNN)-based object detection model.
- Analyzed 4821 anonymized digital panoramic radiographs from pediatric patients (ages 5-13).
- Statistical analysis performed using SPSS version 26.0.
Main Results:
- YOLOv4 achieved high F1 scores for primary teeth (0.95), permanent tooth germs (0.90), and brackets (0.76).
- The model demonstrated limitations in detecting fillings, root canal treatments, and supernumerary teeth.
- The DL architecture provided reliable results with specific limitations.
Conclusions:
- DL-based detection of dental structures and treatments on pediatric radiographs aids early diagnosis of anomalies.
- AI can assist dental practitioners in selecting accurate treatment options, saving time and effort.
