Related Experiment Video
Updated: Jul 6, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
865
Deep learning for tooth identification and enumeration in panoramic radiographs.
Soroush Sadr1, Hossein Mohammad-Rahimi2,3, Mohammad Soroush Ghorbanimehr4
1Department of Endodontics, School of Dentistry, Hamadan University of Medical Sciences, Hamadan, Iran.
Dental Research Journal
|January 3, 2024
Summary
This study introduces a two-step deep learning method for automatic tooth numbering in panoramic radiographs, achieving 95% accuracy in tooth enumeration. This AI approach aids dentists in accurate dental diagnosis and identification.
Area of Science:
- Dentistry
- Artificial Intelligence
- Medical Imaging
Background:
- Accurate tooth identification and enumeration are crucial first steps in dental diagnosis.
- Panoramic radiographs are commonly used for their wide field of view and low radiation dose.
- Automating tooth numbering in radiographs can reduce diagnostic errors.
Purpose of the Study:
- To evaluate the accuracy of a novel two-step deep learning framework for automated tooth identification and enumeration in panoramic radiographs.
- To assess the performance of a deep learning model in detecting quadrants and numbering teeth.
Main Methods:
- A retrospective observational study involving 1007 panoramic radiographs labeled by experienced dentists.
- Image preprocessing using contrast-limited adaptive histogram equalization.
- A two-step deep learning approach utilizing a faster region-based convolutional neural network for quadrant detection and subsequent tooth numbering.
Main Results:
- Quadrant detection achieved 100% average precision (AP50).
- Tooth enumeration demonstrated 95% average precision (AP50).
- The deep learning framework yielded high accuracy in automatic tooth enumeration.
Conclusions:
- The developed two-step deep learning framework shows promising results for automatic tooth enumeration on panoramic radiographs.
- Further validation on diverse datasets and in real-world clinical settings is recommended.
- This AI-driven approach has the potential to enhance diagnostic efficiency and accuracy in dentistry.
