Study on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentation

Abstract Traditional dental prosthetics require a significant amount of work, labor, and time. To simplify the process, a method to convert teeth scan images, scanned using an intraoral scanner, into 3D images for design was developed. Furthermore, several studies have used deep learning to automate...

Full description

Saved in:
Bibliographic Details
Main Authors: Soo-Yeon Jeong, Eun-Jeong Bae, Hyun Soo Jang, SeongJu Na, Sun-Young Ihm
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-78190-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846171925728985088
author Soo-Yeon Jeong
Eun-Jeong Bae
Hyun Soo Jang
SeongJu Na
Sun-Young Ihm
author_facet Soo-Yeon Jeong
Eun-Jeong Bae
Hyun Soo Jang
SeongJu Na
Sun-Young Ihm
author_sort Soo-Yeon Jeong
collection DOAJ
description Abstract Traditional dental prosthetics require a significant amount of work, labor, and time. To simplify the process, a method to convert teeth scan images, scanned using an intraoral scanner, into 3D images for design was developed. Furthermore, several studies have used deep learning to automate dental prosthetic processes. Tooth images are required to train deep learning models, but they are difficult to use in research because they contain personal patient information. Therefore, we propose a method for generating virtual tooth images using image-to-image translation (pix2pix) and contextual reconstruction fill (CR-Fill). Various virtual images can be generated using pix2pix, and the images are used as training images for CR-Fill to compare the real image with the virtual image to ensure that the teeth are well-shaped and meaningful. The experimental results demonstrate that the images generated by the proposed method are similar to actual images. In addition, only using virtual images as training data did not perform well; however, using both real and virtual images as training data yielded nearly identical results to using only real images as training data.
format Article
id doaj-art-e924f5feb0de4867afe6a570d0d2d7fc
institution Kabale University
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e924f5feb0de4867afe6a570d0d2d7fc2024-11-10T12:26:47ZengNature PortfolioScientific Reports2045-23222024-11-0114111210.1038/s41598-024-78190-zStudy on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentationSoo-Yeon Jeong0Eun-Jeong Bae1Hyun Soo Jang2SeongJu Na3Sun-Young Ihm4Division of Software Engineering, Pai Chai UniversityDepartment of Dental Technology, Bucheon UniversityITCEN COREDepartment of Computer Engineering, Pai Chai UniversityDepartment of Computer Engineering, Pai Chai UniversityAbstract Traditional dental prosthetics require a significant amount of work, labor, and time. To simplify the process, a method to convert teeth scan images, scanned using an intraoral scanner, into 3D images for design was developed. Furthermore, several studies have used deep learning to automate dental prosthetic processes. Tooth images are required to train deep learning models, but they are difficult to use in research because they contain personal patient information. Therefore, we propose a method for generating virtual tooth images using image-to-image translation (pix2pix) and contextual reconstruction fill (CR-Fill). Various virtual images can be generated using pix2pix, and the images are used as training images for CR-Fill to compare the real image with the virtual image to ensure that the teeth are well-shaped and meaningful. The experimental results demonstrate that the images generated by the proposed method are similar to actual images. In addition, only using virtual images as training data did not perform well; however, using both real and virtual images as training data yielded nearly identical results to using only real images as training data.https://doi.org/10.1038/s41598-024-78190-zData augmentationGAN (generative adversarial network)Image inpaintingCR-FillPix2pix
spellingShingle Soo-Yeon Jeong
Eun-Jeong Bae
Hyun Soo Jang
SeongJu Na
Sun-Young Ihm
Study on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentation
Scientific Reports
Data augmentation
GAN (generative adversarial network)
Image inpainting
CR-Fill
Pix2pix
title Study on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentation
title_full Study on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentation
title_fullStr Study on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentation
title_full_unstemmed Study on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentation
title_short Study on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentation
title_sort study on virtual tooth image generation utilizing cf fill and pix2pix for data augmentation
topic Data augmentation
GAN (generative adversarial network)
Image inpainting
CR-Fill
Pix2pix
url https://doi.org/10.1038/s41598-024-78190-z
work_keys_str_mv AT sooyeonjeong studyonvirtualtoothimagegenerationutilizingcffillandpix2pixfordataaugmentation
AT eunjeongbae studyonvirtualtoothimagegenerationutilizingcffillandpix2pixfordataaugmentation
AT hyunsoojang studyonvirtualtoothimagegenerationutilizingcffillandpix2pixfordataaugmentation
AT seongjuna studyonvirtualtoothimagegenerationutilizingcffillandpix2pixfordataaugmentation
AT sunyoungihm studyonvirtualtoothimagegenerationutilizingcffillandpix2pixfordataaugmentation