Abstract
Dentists need experience with clinical cases to practice specialized skills. However, the need to protect patient's private information limits their ability to utilize intraoral images obtained from clinical cases. In this study, since generating realistic images could make it possible to utilize intraoral images, progressive growing of generative adversarial networks are used to generate intraoral images. A total of 35,254 intraoral images were used as training data with resolutions of 128 × 128, 256 × 256, 512 × 512, and 1024 × 1024. The results of the training datasets with and without data augmentation were compared. The Sliced Wasserstein Distance was calculated to evaluate the generated images. Next, 50 real images and 50 generated images for each resolution were randomly selected and shuffled. 12 pediatric dentists were asked to observe these images and assess whether they were real or generated. The d prime of the 1024 × 1024 images was significantly higher than that of the other resolutions. In conclusion, generated intraoral images with resolutions of 512 × 512 or lower were so realistic that the dentists could not distinguish whether they were real or generated. This implies that the generated images can be used in dental education or data augmentation for deep learning, without privacy restrictions.
Highlights
Dentists need experience with clinical cases to practice specialized skills
We describe the generation of full-color intraoral images using progressive growing of generative adversarial networks (PGGAN) and evaluate the generated intraoral images in terms of both quantity performance and visual quality assessed by pediatric dentists
The images generated by PGGAN trained with augmented real images were not evaluated because the boundaries of the images were clearly different from the boundaries of the real images as described above, so only the images generated by PGGAN trained without augmented real images were evaluated
Summary
Dentists need experience with clinical cases to practice specialized skills. the need to protect patient’s private information limits their ability to utilize intraoral images obtained from clinical cases. Generated intraoral images with resolutions of 512 × 512 or lower were so realistic that the dentists could not distinguish whether they were real or generated This implies that the generated images can be used in dental education or data augmentation for deep learning, without privacy restrictions. Dental clinicians need to study as many intraoral images as they can to increase their accuracy in oral examinations This is especially true for pediatric dentistry since the oral environment of children drastically changes as children grow. The need to protect a patient’s private information restricts the use of intraoral images obtained in clinical cases For this reason, sharing as many intraoral images as possible among different hospitals is difficult[5]. We describe the generation of full-color intraoral images using progressive growing of generative adversarial networks (PGGAN) and evaluate the generated intraoral images in terms of both quantity performance and visual quality assessed by pediatric dentists
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
