Related Experiment Video
Updated: Jan 4, 2026
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
1.3K
Convolutional neural networks for dental image diagnostics: A scoping review
Falk Schwendicke1, Tatiana Golla1, Martin Dreher1
1Department of Operative and Preventive Dentistry, Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Germany.
Journal of Dentistry
|November 10, 2019
Summary
Convolutional neural networks (CNNs) show promise in dental diagnostics, often performing comparably to dentists in research. Further studies are needed to ensure their safety and generalizability for clinical use.
Area of Science:
- Dental Imaging and Diagnostics
- Artificial Intelligence in Healthcare
- Machine Learning Applications
Background:
- Convolutional Neural Networks (CNNs) are increasingly utilized for medical image analysis.
- Dental diagnostics presents a growing area for AI-driven solutions.
- A comprehensive understanding of current CNN applications in dentistry is needed.
Purpose of the Study:
- To conduct a scoping review of studies applying CNNs to dental imagery.
- To explore the use cases, methodologies, and findings of CNN applications in dentistry.
- To identify trends and gaps in the research landscape.
Main Methods:
- A systematic search of major scientific databases (PubMed, IEEE Xplore, arXiv) was performed.
- Included full-text articles and conference proceedings reporting CNN use on dental images.
- Thirty-six studies published between 2015-2019 were analyzed.
Main Results:
- Studies covered general dentistry, cariology, endodontics, periodontology, orthodontics, and radiology.
- Common tasks included detection, segmentation, and classification of anatomical structures and pathologies like caries.
- Panoramic and periapical radiographs, along with CT scans, were the most frequent image types.
- CNN performance was often comparable to dentists, but applicability and impact on treatment were not assessed.
- Methodological diversity and varied outcome metrics hindered cross-study comparisons.
Conclusions:
- CNNs are prevalent in dental image diagnostics research, demonstrating potential for diagnostic assistance.
- Rigorous, standardized, and comparable methodologies are essential to validate CNNs' usefulness, safety, and generalizability.
- Further research is required to establish evidence-based practice for routine clinical integration.
