Related Experiment Video
Updated: Sep 16, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
1.0K
Automatic identification of dental implant brands with deep learning algorithms
H Yuce1, G Acıkgoz1, S Al-Jumaili2
1Department of Oral, Dental and Maxillofacial Radiology, Faculty of Dentistry, Pamukkale University, Denizli 20160, Turkey.
Dento Maxillo Facial Radiology
|July 8, 2025
Summary
Deep learning algorithms accurately identify dental implant brands on panoramic radiographs. VGG16 achieved 98.9% accuracy, demonstrating AI
Area of Science:
- Artificial Intelligence in Dentistry
- Medical Imaging Analysis
- Machine Learning Applications
Background:
- Accurate identification of dental implant brands is crucial for patient care and treatment planning.
- Current methods for dental implant identification can be challenging and time-consuming.
- The development of automated identification systems is needed to improve efficiency and reduce errors.
Purpose of the Study:
- To classify various dental implant brands using deep learning algorithms.
- To evaluate the performance of different deep learning models in identifying dental implants from panoramic radiographs.
- To establish a reliable AI-based method for dental implant brand identification.
Main Methods:
- Utilized 5,375 cropped panoramic radiographs from four dental implant systems (NucleOSS, Medentika, Nobel, Implance).
- Applied Contrast Limited Adaptive Histogram Equalization (CLAHE) for image enhancement.
- Employed GoogleNet, ResNet-18, VGG16, and ShuffleNet deep learning algorithms for classification.
- Evaluated performance using ROC curves, confusion matrices, accuracy, precision, sensitivity, and F1 scores.
Main Results:
- VGG16 achieved the highest accuracy at 98.90%.
- GoogleNet showed 96.00% accuracy, while ShuffleNet and ResNet-18 achieved 84.80% and 84.40%, respectively.
- VGG16 demonstrated statistically significant superior accuracy compared to other tested algorithms (p < 0.001).
Conclusions:
- Deep learning algorithms, particularly VGG16, are highly effective for identifying dental implant brands.
- AI-powered analysis of panoramic radiographs offers a powerful and accurate solution for dental implant identification.
- This technology has the potential to significantly improve dental practice workflows and patient outcomes.
