The role of deep learning for periapical lesion detection on panoramic radiographs
Dentomaxillofacial Radiology · 01.11.2023 · 52 (8)
DOI: 10.1259/dmfr.20230118 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 18.10.2023. Verfasst von Berrin Çelik und 3 weiteren Autor:innen. Beteiligte Einrichtung: Oral and Maxillofacial Radiology Department, Faculty of Dentistry, Ankara Yıldırım Beyazıt University, Ankara, Turkey. Hauptthemen laut MEDLINE: Artificial Intelligence, Deep Learning. Die Arbeit wurde bisher 65-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Objective
This work aimed to detect automatically periapical lesion on panoramic radiographs (PRs) using deep learning.
Methods
454 objects in 357 PRs were anonymized and manually labeled. They are then pre-processed to improve image quality and enhancement purposes. The data were randomly assigned into the training, validation, and test folders with ratios of 0.8, 0.1, and 0.1, respectively. The state-of-art 10 different deep learning-based detection frameworks including various backbones were applied to periapical lesion detection problem. Model performances were evaluated by mean average precision, accuracy, precision, recall, F1 score, precision-recall curves, area under curve and several other Common Objects in Context detection evaluation metrics.
Results
Deep learning-based detection frameworks were generally successful in detecting periapical lesions on PRs. Detection performance, mean average precision, varied between 0.832 and 0.953 while accuracy was between 0.673 and 0.812 for all models. F1 score was between 0.8 and 0.895. RetinaNet performed the best detection performance, similarly Adaptive Training Sample Selection provided F1 score of 0.895 as highest value. Testing with external data supported our findings.
Conclusion
This work showed that deep learning models can reliably detect periapical lesions on PRs. Artificial intelligence-based on deep learning tools are revolutionizing dental healthcare and can help both clinicians and dental healthcare system.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Oral and Maxillofacial Radiology Department, Faculty of Dentistry, Ankara Yıldırım Beyazıt University, Ankara, Turkey.
- Electrical Electronics Engineering Department, Faculty of Engineering, Gazi University, Ankara, Turkey.
- Biomedical Calibration and Research Center, Gazi University Hospital, Gazi University, Ankara, Turkey.
ORCID-Profile: Berrin Çelik
Zitieren
APA
Çelik, B., Savaştaer, E. F., Kaya, H. I., & Çelik, M. E. (2023). The role of deep learning for periapical lesion detection on panoramic radiographs. Dentomaxillofacial Radiology, 52(8). https://doi.org/10.1259/dmfr.20230118
Vancouver
Çelik B, Savaştaer EF, Kaya HI, Çelik ME. The role of deep learning for periapical lesion detection on panoramic radiographs. Dentomaxillofacial Radiology. 2023;52(8). doi:10.1259/dmfr.20230118
BibTeX
@article{elik2023,
author = {Çelik, Berrin and Savaştaer, Ertugrul Furkan and Kaya, Halil Ibrahim and Çelik, Mahmut Emin},
title = {The role of deep learning for periapical lesion detection on panoramic radiographs},
journal = {Dentomaxillofacial Radiology},
year = {2023},
volume = {52},
number = {8},
doi = {10.1259/dmfr.20230118}
}
EUVIMED