Related Experiment Video
Updated: Jun 28, 2025
05:37
Experimental Model of Ligature-Induced Peri-Implantitis in Mice
Published on: May 17, 2024
2.2K
Establishing a novel deep learning model for detecting peri-implantitis
Wei-Fang Lee1,2, Min-Yuh Day3, Chih-Yuan Fang1,4
1School of Dentistry, Taipei Medical University, Taipei, Taiwan.
Journal of Dental Sciences
|April 15, 2024
Summary
Artificial intelligence, specifically deep learning, can effectively identify peri-implantitis from dental X-rays. This AI model accurately detects marginal bone loss and classifies peri-implantitis severity, aiding dental professionals in diagnosing implant issues.
Area of Science:
- Dental radiology
- Artificial intelligence in medicine
- Machine learning for medical imaging
Background:
- Peri-implantitis diagnosis relies heavily on periapical radiographs.
- Artificial intelligence (AI) shows promise in analyzing radiographic images.
- Accurate diagnosis is crucial for managing implant complications.
Purpose of the Study:
- To develop a deep learning model for differentiating marginal bone loss around implants.
- To classify the severity of peri-implantitis using AI.
- To assess the efficacy of AI in analyzing periapical radiographs for peri-implantitis.
Main Methods:
- A dataset of 800 periapical radiographic images was utilized.
- Images were divided into training, validation, and test sets for deep learning.
- The YOLOv7 object detection algorithm was employed to identify peri-implantitis.
Main Results:
- The deep learning model achieved high classification performance.
- Specificity: 100%
- Precision: 100%
- Recall: 94.44%
- F1 score: 97.10%
Conclusions:
- Deep learning-based object detection can identify implants in periapical radiographs.
- This AI system shows potential to assist dentists and patients with implant-related problems.
- Further training with diverse implant systems is recommended for enhanced clinical application.
