Detection and classification of mandibular fractures in panoramic radiography using artificial intelligence
Dentomaxillofacial Radiology · 01.09.2024 · 53 (6) · 363-371
DOI: 10.1093/dmfr/twae018 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 23.04.2024. Verfasst von Amir Yari und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral and Maxillofacial Surgery, School of Dentistry, Kashan University of Medical Sciences, Kashan, 8715973474, Iran. Hauptthemen laut MEDLINE: Mandibular Fractures, Radiography, Panoramic, Artificial Intelligence. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Objectives
This study evaluated the performance of the YOLOv5 deep learning model in detecting different mandibular fracture types in panoramic images.
Methods
The dataset of panoramic radiographs with mandibular fractures was divided into training, validation, and testing sets, with 60%, 20%, and 20% of the images, respectively. An equal number of control images without fractures were also distributed among the datasets. The YOLOv5 algorithm was trained to detect six mandibular fracture types based on the anatomical location including symphysis, body, angle, ramus, condylar neck, and condylar head. Performance metrics of accuracy, precision, sensitivity (recall), specificity, dice coefficient (F1 score), and area under the curve (AUC) were calculated for each class.
Results
A total of 498 panoramic images containing 673 fractures were collected. The accuracy was highest in detecting body (96.21%) and symphysis (95.87%), and was lowest in angle (90.51%) fractures. The highest and lowest precision values were observed in detecting symphysis (95.45%) and condylar head (63.16%) fractures, respectively. The sensitivity was highest in the body (96.67%) fractures and was lowest in the condylar head (80.00%) and condylar neck (81.25%) fractures. The highest specificity was noted in symphysis (98.96%), body (96.08%), and ramus (96.04%) fractures, respectively. The dice coefficient and AUC were highest in detecting body fractures (0.921 and 0.942, respectively), and were lowest in detecting condylar head fractures (0.706 and 0.812, respectively).
Conclusion
The trained algorithm achieved promising results in detecting most fracture types, particularly in body and symphysis regions indicating machine learning potential as a diagnostic aid for clinicians.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Oral and Maxillofacial Surgery, School of Dentistry, Kashan University of Medical Sciences, Kashan, 8715973474, Iran.
- Department of Prosthodontics, School of Dentistry, Kashan University of Medical Sciences, Kashan, 8715973474, Iran.
- Department of Periodontics, School of Dentistry, Tehran University of Medical Sciences, Tehran, 1439955991, Iran.
- Department of Oral and Maxillofacial Surgery, School of Dentistry, Shiraz University of Medical Sciences, Shiraz, 7195615878, Iran.
- Department of Prosthodontics, School of Dentistry, Shiraz University of Medical Sciences, Shiraz, 7195615878, Iran.
ORCID-Profile: Amir Yari, Paniz Fasih
Zitieren
APA
Yari, A., Fasih, P., Hosseini Hooshiar, M., Goodarzi, A., & Fattahi, S. F. (2024). Detection and classification of mandibular fractures in panoramic radiography using artificial intelligence. Dentomaxillofacial Radiology, 53(6), 363-371. https://doi.org/10.1093/dmfr/twae018
Vancouver
Yari A, Fasih P, Hosseini Hooshiar M, Goodarzi A, Fattahi SF. Detection and classification of mandibular fractures in panoramic radiography using artificial intelligence. Dentomaxillofacial Radiology. 2024;53(6):363-371. doi:10.1093/dmfr/twae018
BibTeX
@article{Yari2024,
author = {Yari, Amir and Fasih, Paniz and Hosseini Hooshiar, Mohammad and Goodarzi, Ali and Fattahi, Seyedeh Farnaz},
title = {Detection and classification of mandibular fractures in panoramic radiography using artificial intelligence},
journal = {Dentomaxillofacial Radiology},
year = {2024},
volume = {53},
number = {6},
pages = {363--371},
doi = {10.1093/dmfr/twae018}
}
EUVIMED