Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study
Acta Odontologica Scandinavica · 06.01.2025 · 84 · 18-25
DOI: 10.2340/aos.v84.42599 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Odontologica Scandinavica, online erschienen am 06.01.2025. Verfasst von Zeynep Seyda Yavsan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatric Dentistry, Tekirdag Namik Kemal University, Tekirdag, Turkey. ylmzynpsyda@gmail.com. Hauptthemen laut MEDLINE: Dental Caries, Neural Networks, Computer, Algorithms. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Kinderkrankenpflege
Abstract (Originalsprache)
Objectives
Approximal caries diagnosis in children is difficult, and artificial intelligence-based research in pediatric dentistry is scarce. To create a convolutional neural network (CNN)-based diagnostic system for the prompt and efficient identification of approximal caries in pediatric patients aged 5–12 years. Materials and methods: Pediatric patients’ digital periapical radiographic images were collected to create a unique dataset. Various augmentation methods were used, and approximal caries in the augmented images were labeled by a pediatric dentist to minimize labeling errors. The dataset consisted of 830 data labeled for approximal caries on 415 images, which were divided into 80% training and 20% testing sets. After comparing 13 detection algorithms, including the latest YOLOv8, the most appropriate one was selected for the proposed system, which was then evaluated based on various performance metrics.
Results
The proposed detection system achieved a precision of 91.2%, an accuracy of 90.8%, a recall of 89.3%, and an F1 value of 90.24% after 300 iterations, utilizing a learning rate of 0.01.
Conclusion
Approximal caries has been successfully detected with the developed system. Future efforts will focus on augmenting the dataset and expanding the sample size to enhance the efficacy of the system.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Pediatric Dentistry, Tekirdag Namik Kemal University, Tekirdag, Turkey. ylmzynpsyda@gmail.com.
- Department of Computer Engineering, Necmettin Erbakan University, Konya, Turkey.
- Department of Electrical and Electronics Engineering, Hitit University, Corum, Turkey.
- Electronic and Department of Electronics and Automation, Tekirdag Namik Kemal University, Tekirdag, Turkey.
ORCID-Profile: Zeynep Seyda Yavsan, Hediye Orhan, Enes Efe, Emrehan Yavsan
Zitieren
APA
Yavsan, Z. S., Orhan, H., Efe, E., & Yavsan, E. (2025). Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study. Acta Odontologica Scandinavica, 84, 18-25. https://doi.org/10.2340/aos.v84.42599
Vancouver
Yavsan ZS, Orhan H, Efe E, Yavsan E. Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study. Acta Odontologica Scandinavica. 2025;84:18-25. doi:10.2340/aos.v84.42599
BibTeX
@article{Yavsan2025,
author = {Yavsan, Zeynep Seyda and Orhan, Hediye and Efe, Enes and Yavsan, Emrehan},
title = {Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study},
journal = {Acta Odontologica Scandinavica},
year = {2025},
volume = {84},
pages = {18--25},
doi = {10.2340/aos.v84.42599}
}
EUVIMED