Journal of Korean Society of Industrial and Systems Engineering (산업경영시스템학회지)

Society of Korea Industrial and System Engineering (한국산업경영시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Real-time Tooth Region Detection in Intraoral Scanner Images with Deep Learning

딥러닝을 이용한 구강 스캐너 이미지 내 치아 영역 실시간 검출

  • Na-Yun, Park (Department of Industrial and Management Engineering, Incheon National University) ;
  • Ji-Hoon Kim (Department of Industrial and Management Engineering, Incheon National University) ;
  • Tae-Min Kim (Department of Industrial and Management Engineering, Incheon National University) ;
  • Kyeong-Jin Song (Department of Industrial and Management Engineering, Incheon National University) ;
  • Yu-Jin Byun (Department of Industrial and Management Engineering, Incheon National University) ;
  • Min-Ju Kang․ (Department of Industrial and Management Engineering, Incheon National University) ;
  • Kyungkoo Jun (Department of Embedded Systems Engineering, Incheon National University) ;
  • Jae-Gon Kim (Department of Industrial and Management Engineering, Incheon National University)
  • 박나윤 (인천대학교 산업경영공학과) ;
  • 김지훈 (인천대학교 산업경영공학과) ;
  • 김태민 (인천대학교 산업경영공학과) ;
  • 송경진 (인천대학교 산업경영공학과) ;
  • 변유진 (인천대학교 산업경영공학과) ;
  • 강민주 (인천대학교 산업경영공학과) ;
  • 전경구 (인천대학교 임베디드시스템공학과) ;
  • 김재곤 (인천대학교 산업경영공학과)
  • Received : 2023.09.01
  • Accepted : 2023.09.13
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In the realm of dental prosthesis fabrication, obtaining accurate impressions has historically been a challenging and inefficient process, often hindered by hygiene concerns and patient discomfort. Addressing these limitations, Company D recently introduced a cutting-edge solution by harnessing the potential of intraoral scan images to create 3D dental models. However, the complexity of these scan images, encompassing not only teeth and gums but also the palate, tongue, and other structures, posed a new set of challenges. In response, we propose a sophisticated real-time image segmentation algorithm that selectively extracts pertinent data, specifically focusing on teeth and gums, from oral scan images obtained through Company D's oral scanner for 3D model generation. A key challenge we tackled was the detection of the intricate molar regions, common in dental imaging, which we effectively addressed through intelligent data augmentation for enhanced training. By placing significant emphasis on both accuracy and speed, critical factors for real-time intraoral scanning, our proposed algorithm demonstrated exceptional performance, boasting an impressive accuracy rate of 0.91 and an unrivaled FPS of 92.4. Compared to existing algorithms, our solution exhibited superior outcomes when integrated into Company D's oral scanner. This algorithm is scheduled for deployment and commercialization within Company D's intraoral scanner.

Keywords

Acknowledgement

This work was supported by the Korea Institute for Advancement of Technology (KIAT) grant funded by the Korea Government (MOTIE) (P0008691, HRD Program for Industrial Innovation).

References

  1. Bae, E., Jeong, J., Son, Y., and Lim, J., A study on virtual tooth image generation using deep learning-based on the number of learning, Journal of Technologic Dentistry, 2020, Vol. 42, No. 1, pp. 1-8. https://doi.org/10.14347/kadt.2020.42.1.1
  2. Behera, S.K., Rath, A.K., and Sethy, P.K., Fruits yield estimation using Faster R-CNN with MIoU, Multimedia Tools and Applications, 2021, Vol. 80, pp. 19043-19056. https://doi.org/10.1007/s11042-021-10704-7
  3. Choi, H.S., Moon, J.E., and Kim, S.H., The application of CAD/CAM in dentistry, The Journal of the Korean Dental Association, 2012, Vol. 50, No.3, pp. 110-117. https://doi.org/10.22974/jkda.2012.50.3.001
  4. Corbella, S., Srinivas, S., and Cabitza, F., Applications of deep learning in dentistry. Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology, 2021, Vol. 132, No. 2, pp. 225-238. https://doi.org/10.1016/j.oooo.2020.11.003
  5. He, K., Gkioxari, G., Dollar, P., and Girshick, R., Mask r-cnn, In Proceedings of the IEEE international conference on computer vision, 2017, pp. 2961-2969.
  6. Holder, C.J. and Shafique, M., On efficient real- time semantic segmentation: A survey, https://doi.org/10.48550/arXiv.2206.08605.
  7. Hong, Y., Pan, H., Sun, W., and Jia, Y., Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes, arXiv preprint arXiv:210 1.06085.
  8. Huang, M. Y., Son, K., Lee, W. S., and Lee, K. B., Comparison of the accuracy of intraoral scanner by three-dimensional analysis in single and 3-unit bridge abutment model: In vitro study, The Journal of Korean Academy of Prosthodontics, 2019, Vol. 57, No. 2, pp. 102-109. https://doi.org/10.4047/jkap.2019.57.2.102
  9. Kim, J.H., Kim, J.H., and Kim, H.Y., A study on common errors in digital impressions:(An Example of CEREC $^{(R)}$^{(R)} $ AC), Journal of Technologic Dentistry, 2011, Vol. 33, No. 3, pp. 211-218.
  10. Kim, Y.G., A study on the life expectancy of the dental prosthesis, Journal of Oral Medicine and Pain, 1995, Vol. 20, No. 2, pp. 317-325.
  11. Liu, X., Song, L., Liu, S., and Zhang, Y., A review of deep-learning-based medical image segmentation methods, Sustainability, 2021, Vol. 13, No. 3, pp. 1224.
  12. Pyo, S.W., Park, Y.B., Kim, J.H., Moon, H.S., and Lee, K.W., Maxillary anterior all ceramic restoration using digital impression and CAD/CAM, The Journal of Korean Academy of Prosthodontics, 2011, Vol. 49, No. 3, pp. 263-269. https://doi.org/10.4047/jkap.2011.49.3.263
  13. Rad, A.E., Rahim, M.S., and Norouzi, A., Digital dental X-ray image segmentation and feature extraction, Telkomnika Indonesian Journal of Electrical Engineering, 2013, Vol. 11, No. 6, pp. 3109-3114. https://doi.org/10.11591/telkomnika.v11i6.2655
  14. Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van, D., and Hassabis, D., Mastering the game of Go with deep neural networks and tree search, Nature, 2016, Vol. 529, No. 7587, pp. 484-489. https://doi.org/10.1038/nature16961
  15. Xu, J., Xiong, Z., and Bhattacharyya, S.P., PIDNet: A real-time semantic segmentation network inspired by PID controllers, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19529-19539.
  16. Yang, Y., Xie, R., Jia, W., Chen, Z., Yang, Y., Xie, L., and Jiang, B., Accurate and automatic tooth image segmentation model with deep convolutional neural networks and level set method, Neurocomputing, 2021, Vol. 419, pp. 108-125. https://doi.org/10.1016/j.neucom.2020.07.110
  17. Zhao, H., Shi, J., Qi, X., Wang, X. and Jia, J., Pyramid scene parsing network, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2881-2890.
  18. Zhao, M., Ma, L., Tan, W., and Nie, D., Interactive tooth segmentation of dental models, In 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, 2006, pp. 654-657.
  19. Zhu, G., Piao, Z., and Kim, S.C., Tooth detection and segmentation with mask R-CNN, In 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), 2020, pp. 070-072.