EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel Deep Learning Approach for Classification of Abnormal Teeth in Panoramic X-rays

Huda Mohammed, Hind Majeed, Bushra Abdul Razzaq Al-mafrachi, Mustafa S. Al-Khaffaf, Aymen Saad

International Journal of Theoretical & Applied Computational Intelligence · 2025

DOI: 10.65278/ijtaci.2025.7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Theoretical & Applied Computational Intelligence, 2025. Verfasst von Huda Mohammed und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dental professionals identify common dental conditions, including caries, with panoramic and periapical radiographs, which dentists typically inspect manually. Manual diagnosis can miss abnormal teeth because of inexperience or a heavy workload, which motivates the use of computer vision and data-driven image enhancement. Convolutional Neural Networks (CNNs), with their multiple convolutional layers, are recognized for their high classification accuracy and are among the most effective methods for diagnosing dental abnormalities, although they require substantial image datasets for adequate training. This study modifies the output layers of ResNet-50 and MobileNetV2 and proposes a Lightweight Convolutional Neural Network (LWCNN) to classify panoramic dental X-rays from the public DENTEX dataset into four categories. Unsharp filtering, histogram equalization, and image complement are applied to enhance the images. With the enhanced images, the LWCNN achieves the highest testing accuracy (96.60%), followed by MobileNetV2 (96.50%) and ResNet-50 (93.20%), showing that the LWCNN can successfully aid in the classification of abnormal teeth.

Zitieren

APA

Mohammed, H., Majeed, H., Al-mafrachi, B. A. R., Al-Khaffaf, M. S., & Saad, A. (2025). A Novel Deep Learning Approach for Classification of Abnormal Teeth in Panoramic X-rays. International Journal of Theoretical & Applied Computational Intelligence. https://doi.org/10.65278/ijtaci.2025.7

Vancouver

Mohammed H, Majeed H, Al-mafrachi BAR, Al-Khaffaf MS, Saad A. A Novel Deep Learning Approach for Classification of Abnormal Teeth in Panoramic X-rays. International Journal of Theoretical & Applied Computational Intelligence. 2025. doi:10.65278/ijtaci.2025.7

BibTeX
@article{Mohammed2025,
  author = {Mohammed, Huda and Majeed, Hind and Al-mafrachi, Bushra Abdul Razzaq and Al-Khaffaf, Mustafa S. and Saad, Aymen},
  title = {A Novel Deep Learning Approach for Classification of Abnormal Teeth in Panoramic X-rays},
  journal = {International Journal of Theoretical & Applied Computational Intelligence},
  year = {2025},
  doi = {10.65278/ijtaci.2025.7}
}
Kostenlos starten →