Related Experiment Video
Updated: Jan 15, 2026
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
1.3K
Dual convolutional neural network framework for segmenting dental caries in panoramic radiographs
Yeong-Su Lim1, Dohyun Chun2, Jihun Kim3
1Graduate student, Department of Smart Health Science and Technology, Kangwon National University, Chuncheon, Republic of Korea.
The Journal of Prosthetic Dentistry
|October 14, 2025
Summary
A new deep learning method effectively detects and segments dental caries in panoramic radiographs, improving diagnostic accuracy over traditional methods. This AI approach enhances early detection of this widespread oral disease.
Area of Science:
- Artificial Intelligence in Dentistry
- Medical Imaging Analysis
- Deep Learning for Diagnostics
Background:
- Dental caries is a prevalent chronic disease that is challenging to diagnose, particularly in posterior proximal areas.
- Current diagnostic methods like visual inspection and radiography suffer from subjectivity and inter-clinician variability.
Purpose of the Study:
- To develop and validate a deep learning (DL) based automated system for detecting and segmenting dental caries.
- To assess the efficacy of the DL method on panoramic radiographs.
Main Methods:
- A DL pipeline integrating Faster Regions based Convolutional Neural Networks (R-CNN) for tooth detection and U-Net for caries segmentation was implemented.
- Performance was statistically compared against conventional segmentation models using paired t tests.
Main Results:
- The proposed DL method achieved high performance metrics: Intersection over Union (IoU) of 0.6075, Dice coefficient of 0.7429, recall of 0.7309, and precision of 0.7881.
- Significant improvements in IoU, Dice coefficient, and recall were observed compared to traditional segmentation models (P<.05).
Conclusions:
- The developed DL method demonstrates significant effectiveness in detecting and segmenting dental caries from panoramic radiographs.
- This AI-driven approach holds substantial potential for enhancing the accuracy and consistency of dental caries diagnosis.
