TY - JOUR
T1 - Pano-GAN
T2 - A Deep Generative Model for Panoramic Dental Radiographs
AU - Pedersen, Søren
AU - Jain, Sanyam
AU - Chavez, Mikkel
AU - Ladehoff, Viktor
AU - de Freitas, Bruna Neves
AU - Pauwels, Ruben
PY - 2025/2/2
Y1 - 2025/2/2
N2 - 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.
AB - 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.
KW - artificial intelligence
KW - deep learning
KW - dental radiography
KW - generative adversarial networks
KW - panoramic radiography
UR - http://www.scopus.com/inward/record.url?scp=85219237246&partnerID=8YFLogxK
U2 - 10.3390/jimaging11020041
DO - 10.3390/jimaging11020041
M3 - Journal article
C2 - 39997543
SN - 2313-433X
VL - 11
JO - Journal of Imaging
JF - Journal of Imaging
IS - 2
M1 - 41
ER -