Technical error identification in intraoral radiographs using multiple convolutional neural networks: an exploratory study
Oral Radiology · 2026
DOI: 10.1007/s11282-026-00941-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Oral Radiology, 2026. Verfasst von Mariam Baghdady und 3 weiteren Autor:innen. Beteiligte Einrichtung: Oral and Maxillofacial Radiology, Department of Diagnostic Sciences, College of Dentistry, Kuwait University, P.O. Box: 24923, 13110, Safat, Kuwait. …. Hauptthemen laut MEDLINE: Convolutional Neural Networks, Radiography, Dental, Diagnostic Errors, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: Kuwait University.
Abstract (Originalsprache)
OBJECTIVES: High-quality intraoral radiographs are vital for accurate diagnosis and treatment planning. Operator-dependent errors can compromise image quality and reliability. Artificial intelligence (AI) offers strategies to automate the detection of suboptimal quality radiographs. This study presents the first step towards developing a comprehensive automated radiographic error detection software. METHODS: Five convolutional neural networks (CNNs), GoogLeNet, Places-365 GoogLeNet, NASNet-Mobile, ShuffleNet, and ResNet 50, were compared for their capability to classify radiographs (n = 1600) as error-free (diagnostic), or with errors (cone cut, open-mouth and horizontal overlap). 20% of the images were used for validation, and another 20% for testing. Performance metrics, including sensitivity and specificity, were calculated to compare model performance. RESULTS: The best performance metrics of the CNNs in identifying absence (normal images) or presence of technical errors (cone cut, open-mouth, and overlap errors were, Places-365 GoogLeNet (sensitivity/specificity - 0.75/0.85), GoogLeNet (sensitivity/specificity - 0.91/0.96), ResNet-50 (sensitivity/specificity - 0.86/0.97), and GoogLeNet (sensitivity/specificity - 0.83/0.82), respectively. CONCLUSION: AI-driven technical error detection in intraoral radiographs shows promise. A combination of CNNs may be the best approach to identify radiographic errors. Future research should focus on integrating multiple CNN strategies, employing explainable AI techniques, and expanding the dataset to refine real-time error detection for facilitating widespread clinical adoption.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Oral and Maxillofacial Radiology, Department of Diagnostic Sciences, College of Dentistry, Kuwait University, P.O. Box: 24923, 13110, Safat, Kuwait. mariam.baghdady@ku.edu.kw.
- Oral and Maxillofacial Radiology, Faculty of Dentistry, University of Toronto, 124 Edward Street, Toronto, ON, Canada. mariam.baghdady@ku.edu.kw.
- Discipline of Dental Public Health, Department of Developmental and Preventive Sciences, College of Dentistry, Kuwait University, P.O. Box: 24923, 13110, Safat, Kuwait.
- Department of Orthodontics, Hamdan Bin Mohammed College of Dental Medicine, , Mohammed Bin Rashid University of Medicine and Health Sciences, Dubai Health, P.O Box 505055, Dubai, United Arab Emirates.
- Oudari Consultancy, Konnagar, West Bengal, 712246, India.
Förderung
- Kuwait University
Zitieren
APA
Baghdady, M., Baskaradoss, J. K., Prasad, S., & Bhattacharjee, T. (2026). Technical error identification in intraoral radiographs using multiple convolutional neural networks: an exploratory study. Oral Radiology. https://doi.org/10.1007/s11282-026-00941-7
Vancouver
Baghdady M, Baskaradoss JK, Prasad S, Bhattacharjee T. Technical error identification in intraoral radiographs using multiple convolutional neural networks: an exploratory study. Oral Radiology. 2026. doi:10.1007/s11282-026-00941-7
BibTeX
@article{Baghdady2026,
author = {Baghdady, Mariam and Baskaradoss, Jagan Kumar and Prasad, Sabarinath and Bhattacharjee, Tanmoy},
title = {Technical error identification in intraoral radiographs using multiple convolutional neural networks: an exploratory study},
journal = {Oral Radiology},
year = {2026},
doi = {10.1007/s11282-026-00941-7}
}
EUVIMED