Application of deep learning for detection of nasal bone fracture on X-ray nasal bone lateral view
Dentomaxillofacial Radiology · 2025
DOI: 10.1093/dmfr/twaf028 ↗Kurz gefasst
Beobachtungsstudie in der Zeitschrift Dentomaxillofacial Radiology, 2025. Verfasst von Tahereh Mortezaei und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral and Maxillofacial Radiology, School of Dentistry, Guilan University of Medical Sciences, Rasht, 41941- 73774, Iran. Hauptthemen laut MEDLINE: Deep Learning, Nasal Bone, Skull Fractures. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 26 Literaturangaben.
Abstract (Originalsprache)
Objectives
This study aimed to assess the efficacy of deep learning applications for the detection of nasal bone fracture on X-ray nasal bone lateral view.
Methods
In this retrospective observational study, 2968 X-ray nasal bone lateral views of trauma patients were collected from a radiology centre, and randomly divided into training, validation, and test sets. Preprocessing included noise reduction by using the Gaussian filter and image resizing. Edge detection was performed using the Canny edge detector. Feature extraction was conducted using the gray-level co-occurrence matrix (GLCM), histogram of oriented gradients (HOG), and local binary pattern (LBP) techniques. Several machine learning algorithms namely CNN, VGG16, VGG19, MobileNet, Xception, ResNet50V2, and InceptionV3 were employed for the classification of images into 2 classes of normal and fracture.
Results
The accuracy was the highest for VGG16 and Swin Transformer (79%) followed by ResNet50V2 and InceptionV3 (0.74), Xception (0.72), and MobileNet (0.71). The AUC was the highest for VGG16 (0.86) followed by VGG19 (0.84), MobileNet and Xception (0.83), and Swin Transformer (0.79).
Conclusions
The tested deep learning models were capable of detecting nasal bone fractures on X-ray nasal bone lateral views with high accuracy. VGG16 was the best model with successful results.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Oral and Maxillofacial Radiology, School of Dentistry, Guilan University of Medical Sciences, Rasht, 41941- 73774, Iran.
- Dental Sciences Research Center, Department of Oral and Maxillofacial Radiology, School of Dentistry, Guilan University of Medical Sciences, Rasht, 41941- 73774, Iran.
- Department of Computer Engineering, Faculty of Engineering, University of Guilan, Rasht, 41996-13776, Iran.
ORCID-Profile: Tahereh Mortezaei, Zahra Dalili Kajan, Seyed Abolghasem Mirroshandel, Mobin Mehrpour, Sara Shahidzadeh
Zitieren
APA
Mortezaei, T., Dalili Kajan, Z., Mirroshandel, S. A., Mehrpour, M., & Shahidzadeh, S. (2025). Application of deep learning for detection of nasal bone fracture on X-ray nasal bone lateral view. Dentomaxillofacial Radiology. https://doi.org/10.1093/dmfr/twaf028
Vancouver
Mortezaei T, Dalili Kajan Z, Mirroshandel SA, Mehrpour M, Shahidzadeh S. Application of deep learning for detection of nasal bone fracture on X-ray nasal bone lateral view. Dentomaxillofacial Radiology. 2025. doi:10.1093/dmfr/twaf028
BibTeX
@article{Mortezaei2025,
author = {Mortezaei, Tahereh and Dalili Kajan, Zahra and Mirroshandel, Seyed Abolghasem and Mehrpour, Mobin and Shahidzadeh, Sara},
title = {Application of deep learning for detection of nasal bone fracture on X-ray nasal bone lateral view},
journal = {Dentomaxillofacial Radiology},
year = {2025},
doi = {10.1093/dmfr/twaf028}
}
EUVIMED