EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Pano-GAN: A Deep Generative Model for Panoramic Dental Radiographs

Søren Pedersen, Sanyam Jain iD, Mikkel Chavez, Viktor Ladehoff, Bruna Neves de Freitas iD, Ruben Pauwels iD

Journal of Imaging · 02.02.2025 · 11 (2) · 41

DOI: 10.3390/jimaging11020041 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 02.02.2025. Verfasst von Søren Pedersen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Bachelor's Degree Programme in Data Science, Aarhus University, Nordre Ringgade 1, 8000 Aarhus, Denmark. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Independent Research Fund Denmark.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents the development of a generative adversarial network (GAN) for the generation of synthetic dental panoramic radiographs. While this is an exploratory study, the ultimate aim is to address the scarcity of data in dental research and education. A deep convolutional GAN (DCGAN) with the Wasserstein loss and a gradient penalty (WGAN-GP) was trained on a dataset of 2322 radiographs of varying quality. The focus of this study was on the dentoalveolar part of the radiographs; other structures were cropped out. Significant data cleaning and preprocessing were conducted to standardize the input formats while maintaining anatomical variability. Four candidate models were identified by varying the critic iterations, number of features and the use of denoising prior to training. To assess the quality of the generated images, a clinical expert evaluated a set of generated synthetic radiographs using a ranking system based on visibility and realism, with scores ranging from 1 (very poor) to 5 (excellent). It was found that most generated radiographs showed moderate depictions of dentoalveolar anatomical structures, although they were considerably impaired by artifacts. The mean evaluation scores showed a trade-off between the model trained on non-denoised data, which showed the highest subjective quality for finer structures, such as the mandibular canal and trabecular bone, and one of the models trained on denoised data, which offered better overall image quality, especially in terms of clarity and sharpness and overall realism. These outcomes serve as a foundation for further research into GAN architectures for dental imaging applications.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencedeep learningdental radiographygenerative adversarial networkspanoramic radiography

Autor:innen und Institutionen

  • Bachelor's Degree Programme in Data Science, Aarhus University, Nordre Ringgade 1, 8000 Aarhus, Denmark.
  • Department of Dentistry and Oral Health, Aarhus University, Vennelyst Boulevard 9, 8000 Aarhus, Denmark.
  • Aarhus Institute of Advanced Studies, Aarhus University, Høegh-Guldbergs Gade 6B, 8000 Aarhus, Denmark.

ORCID-Profile: Sanyam Jain, Bruna Neves de Freitas, Ruben Pauwels

Förderung

  • Independent Research Fund Denmark

Zitieren

APA

Pedersen, S., Jain, S., Chavez, M., Ladehoff, V., de Freitas, B. N., & Pauwels, R. (2025). Pano-GAN: A Deep Generative Model for Panoramic Dental Radiographs. Journal of Imaging, 11(2), 41. https://doi.org/10.3390/jimaging11020041

Vancouver

Pedersen S, Jain S, Chavez M, Ladehoff V, de Freitas BN, Pauwels R. Pano-GAN: A Deep Generative Model for Panoramic Dental Radiographs. Journal of Imaging. 2025;11(2):41. doi:10.3390/jimaging11020041

BibTeX
@article{Pedersen2025,
  author = {Pedersen, Søren and Jain, Sanyam and Chavez, Mikkel and Ladehoff, Viktor and de Freitas, Bruna Neves and Pauwels, Ruben},
  title = {Pano-GAN: A Deep Generative Model for Panoramic Dental Radiographs},
  journal = {Journal of Imaging},
  year = {2025},
  volume = {11},
  number = {2},
  pages = {41},
  doi = {10.3390/jimaging11020041}
}
Kostenlos starten →