Journal of Information Technology Services (한국IT서비스학회지)

Korea Society of IT Services (한국IT서비스학회)
권호 표지
DOI QR코드

DOI QR Code

An Image-to-Image Translation GAN Model for Dental Prothesis Design

치아 보철물 디자인을 위한 이미지 대 이미지 변환 GAN 모델

  • 김태민 ((주)브이엠에스솔루션스 솔루션사업부) ;
  • 김재곤 (인천대학교 산업경영공학과)
  • Received : 2023.09.04
  • Accepted : 2023.10.11
  • Published : 2023.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Traditionally, tooth restoration has been carried out by replicating teeth using plaster-based materials. However, recent technological advances have simplified the production process through the introduction of computer-aided design(CAD) systems. Nevertheless, dental restoration varies among individuals, and the skill level of dental technicians significantly influences the accuracy of the manufacturing process. To address this challenge, this paper proposes an approach to designing personalized tooth restorations using Generative Adversarial Network(GAN), a widely adopted technique in computer vision. The primary objective of this model is to create customized dental prosthesis for each patient by utilizing 3D data of the specific teeth to be treated and their corresponding opposite tooth. To achieve this, the 3D dental data is converted into a depth map format and used as input data for the GAN model. The proposed model leverages the network architecture of Pixel2Style2Pixel, which has demonstrated superior performance compared to existing models for image conversion and dental prosthesis generation. Furthermore, this approach holds promising potential for future advancements in dental and implant production.

Keywords

Acknowledgement

이 논문은 인천대학교 2023년도 자체연구비 지원에 의하여 연구되었음

References

  1. Arjovsky, M., S. Chintala, and L. Bottou, "Wasserstein generative adversarial networks", In PMLR International conference on machine learning (ICML), 2017, 214-223. 
  2. Cheng, X., T. An, W. Liao, N. Dai, Q. Yu, and P. Lu, "Establishment of database with standard 3D tooth crowns based on 3DS MAX", Journal of Biomedical Engineering, Vol.26, No.4, 2009, 866-868. 
  3. Deng, J., J. Guo, N. Xue, and S. Zafeiriou. "Arcface: Additive angular margin loss for deep face recognition", In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 4690-4699. 
  4. Fan, H.., H. Su, and L. Guibas, "A point set generation network for 3D object recon- struction from a single image", In Proceeding of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), 2017, 605-613. 
  5. Goodfellow, I., J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial networks", Communications of the ACM, Vol.64, No.11, 2020, 139-144.  https://doi.org/10.1145/3422622
  6. Hore, A. and D. Ziou, "Image quality metrics: PSNR vs. SSIM", In IEEE 20th International Conference on Pattern Recognition (ICPR), 2010, 2366-2369. 
  7. Hwang, J., Azernikov, S., Efros, A., and Yu, S., "Learning beyond human expertise with generative models for dental restorations", arXiv preprint, arXiv:1804.00064, 2018. 
  8. Iizuka, S., E. Simo-Serra, and H. Ishikawa, "Globally and locally consistent image completion", ACM Transactions on Graphics(ToG), Vol.36, No.4, 2017, 1-14.  https://doi.org/10.1145/3072959.3073659
  9. Isola, P., J. Zhu, T. Zhou, and A. Efros, "Imageto-image translation with conditional adversarial networks", In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2017, 1125-1134. 
  10. Karras, T., S. Laine, and T. Aila, "A style-based generator architecture for generative adversarial networks", In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2019, 4401-4410. 
  11. Kazeminia, M., A. Abdi, S. Shohaimi, R. Jalali, A. Vaisi-Raygani, N. Salari, and M. Mohammadi, "Dental caries in primary and permanent teeth in children's worldwide, 1995 to 2019: A systematic review and meta-analysis", Head & Face Medicine, Vol.16, No.1, 2020, 1-21.  https://doi.org/10.1186/s13005-020-0215-7
  12. Lee, H., N. Thoummala, H. Park, S. Ham, J. Yu, J. Hwang, S. Heo, and S. Kim, "AI-Based Dental Prostheses Fabrication Using Generative Adversarial Networks", Quantitative Bio-Science, Vol.40, No.1, 2021, 39-44. 
  13. Lee, S., K. Son, J. Park, J. Lee, S. Kang, R. Wijesinghe, P. Kim, J. Hwang, S. Park, B. Yun, M. Jeon, K. Lee, and J. Kim, "Non-ionized, high-resolution measurement of internal and marginal discrepancies of dental prosthesis using optical coherence tomography", IEEE Access, Vol.7, 2018, 6209- 6218.  https://doi.org/10.1109/ACCESS.2018.2889341
  14. Mirza, M., and S. Osindero, "Conditional generative adversarial nets", arXiv preprint, arXiv:1411.1784, 2014. 
  15. Richardson, E., Y. Alaluf, O. Patashnik, Y. Nitzan, Y. Azar, S. Shapiro, and D. CohenOr, "Encoding in style: a stylegan encoder for image-to-image translation", In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2021, 2287-2296. 
  16. Ronneberger, O., P. Fischer, and T. Brox, "U-net: Convolutional networks for bio- medical image segmentation", In International Conference on Medical image computing and computer-assisted intervention (MICCAI), 2015, 234-241. 
  17. Sara, U., M. Akter, and M. Uddin, "Image quality assessment through FSIM, SSIM, MSE and PSNR-A comparative study", Journal of Computer and Communications, Vol.7, No.3, 2019, 8-18.  https://doi.org/10.4236/jcc.2019.73002
  18. Tian, S., Huang, R., Li, Z., Fiorenza, L., Dai, N., Sun, Y., and Ma, H., "A Dual Discriminator Adversarial Learning Approach for Dental Occlusal Surface Reconstruction", Journal of Healthcare Engineering, 2022. 
  19. Tian, S., M. Wang, F. Yuan, N. Dai, Y. Sun, W. Xie, and J. Qin, "Efficient computer- aided design of dental inlay restoration: a deep adversarial framework", IEEE Transactions on Medical Imaging, Vol. 40, No.9, 2021, 2415-2427.  https://doi.org/10.1109/TMI.2021.3077334
  20. Tian, S., M. Wang, N. Dai, H. Ma, L. Li, L. Fiorenza, Y. Sun, and Y. Li, "DCPR-GAN: dental crown prosthesis restoration using twostage generative adversarial networks", IEEE Journal of Biomedical and Health Informatics, Vol.26, No.1, 2021, 151-160.  https://doi.org/10.1109/JBHI.2021.3119394
  21. Wang, C., C. Xu, C. Wang, and D. Tao, "Perceptual adversarial networks for image-to-image transformation", IEEE Transactions on Image Processing, Vol.27, No.8, 2018, 4066-4079.  https://doi.org/10.1109/TIP.2018.2836316
  22. Wang, T., M. Liu, J. Zhu, A. Tao, J. Kautz, and B. Catanzaro, "High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs", In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2018, 8798-8807. 
  23. Wang, Z., A. Bovik, H. Sheikh, and E. Simoncelli, "Image quality assessment: from error visibility to structural similarity", IEEE transactions on image processing, Vol.13, No.4, 2004, 600-612.  https://doi.org/10.1109/TIP.2003.819861
  24. Yu, J., Z. Lin, J. Yang, X. Shen, X. Lu, and T. Huang, "Free-form image inpainting with gated convolution", In Proceedings of the IEEE/CVF international conference on computer vision (ICCV), 2019, 4471-4480. 
  25. Yu, J., Z. Lin, J. Yang, X. Shen, X. Lu, and T. Huang, "Generative image inpainting with contextual attention", In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2018, 5505-5514. 
  26. Yuan, F., N. Dai, S. Tian, B. Zhang, Y. Sun, Q. Yu, and H. Liu, "Personalized design technique for the dental occlusal surface based on conditional generative adversarial networks", International Journal for Numerical Methods in Biomedical Engineering, Vol.36, No.5, 2020, e3321. 
  27. Zhang, L., L. Zhang, X. Mou, and D. Zhang, "FSIM: A feature similarity index for image quality assessment", IEEE TranSactions on Image Processing, Vol.20, No.8, 2011, 2378-2386.  https://doi.org/10.1109/TIP.2011.2109730
  28. Zhang, R., P. Isola, A. Efros, E. Schechtman, and O. Wang, "The unreasonable effe- ctiveness of deep features as a perceptual metric", In Proceeding of the IEEE conference on computer vision and pattern recognition (CVPR), 2018, 585-595.