Related Experiment Video
Updated: May 25, 2025
07:14
Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities
Published on: May 24, 2022
4.3K
Deep Learning-Assisted Diagnostic System: Apices and Odontogenic Sinus Floor Level Analysis in Dental Panoramic
Pei-Yi Wu1, Yuan-Jin Lin2, Yu-Jen Chang3
1Department of Periodontics, Division of Dentistry, Taoyuan Chang Gung Memorial Hospital, Taoyuan City 333034, Taiwan.
Bioengineering (Basel, Switzerland)
|February 26, 2025
Summary
Artificial intelligence aids dentists in diagnosing odontogenic sinusitis, a condition often misdiagnosed. This AI system uses deep learning models to accurately identify odontogenic sinusitis from dental radiographs, improving patient outcomes.
Area of Science:
- Dentistry
- Medical Imaging
- Artificial Intelligence
Background:
- Odontogenic sinusitis, caused by dental issues, mimics general sinusitis, leading to delayed diagnosis.
- Accurate early detection is crucial to prevent complications and ensure timely treatment.
Purpose of the Study:
- To develop and evaluate an AI-powered image processing technique for accurate odontogenic sinusitis diagnosis.
- To enhance diagnostic accuracy using deep learning models on dental radiographs.
Main Methods:
- Image processing fused with contrast limited adaptive histogram equalization, Min-Max normalization, and RGB mapping.
- Deep learning models, including YOLOv11n for tooth detection and YOLOv8n-cls for classification, were employed.
- Evaluation of diagnostic accuracy in both simulated and clinical settings.
Main Results:
- YOLOv11n achieved 98.2% accuracy in detecting odontogenic sinusitis tooth positions.
- YOLOv8n-cls demonstrated a 96.1% classification accuracy, a 16.9% improvement over non-enhanced methods.
- Clinical application showed 97.6% accuracy for odontogenic sinusitis and 95.8% for non-odontogenic sinusitis.
Conclusions:
- The developed AI system provides reliable auxiliary support for precise odontogenic sinusitis diagnosis.
- This technique reduces radiation exposure compared to CT imaging.
- The AI approach significantly improves diagnostic accuracy, outperforming existing methods.
