Journal of Dental Rehabilitation and Applied Science (구강회복응용과학지)

Korean Academy of Stomatognathic Function and Occlusion (대한턱관절교합학회)
권호 표지
DOI QR코드

DOI QR Code

Deep learning algorithms for identifying 79 dental implant types

79종의 임플란트 식별을 위한 딥러닝 알고리즘

  • Hyun-Jun, Kong (Department of Prosthodontics, College of Dentistry, Wonkwang University) ;
  • Jin-Yong, Yoo (HERIBio Co. Ltd.) ;
  • Sang-Ho, Eom (HERIBio Co. Ltd.) ;
  • Jun-Hyeok, Lee (Korea Platform Service Technology Co. Ltd.)
  • 공현준 (원광대학교 치과대학 치과보철학교실) ;
  • 유진용 ((주)헤리바이오) ;
  • 엄상호 ((주)헤리바이오) ;
  • 이준혁 ((주)한국플랫폼서비스기술)
  • Received : 2022.10.21
  • Accepted : 2022.11.09
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: This study aimed to evaluate the accuracy and clinical usability of an identification model using deep learning for 79 dental implant types. Materials and Methods: A total of 45396 implant fixture images were collected through panoramic radiographs of patients who received implant treatment from 2001 to 2020 at 30 dental clinics. The collected implant images were 79 types from 18 manufacturers. EfficientNet and Meta Pseudo Labels algorithms were used. For EfficientNet, EfficientNet-B0 and EfficientNet-B4 were used as submodels. For Meta Pseudo Labels, two models were applied according to the widen factor. Top 1 accuracy was measured for EfficientNet and top 1 and top 5 accuracy for Meta Pseudo Labels were measured. Results: EfficientNet-B0 and EfficientNet-B4 showed top 1 accuracy of 89.4. Meta Pseudo Labels 1 showed top 1 accuracy of 87.96, and Meta pseudo labels 2 with increased widen factor showed 88.35. In Top5 Accuracy, the score of Meta Pseudo Labels 1 was 97.90, which was 0.11% higher than 97.79 of Meta Pseudo Labels 2. Conclusion: All four deep learning algorithms used for implant identification in this study showed close to 90% accuracy. In order to increase the clinical applicability of deep learning for implant identification, it will be necessary to collect a wider amount of data and develop a fine-tuned algorithm for implant identification.

목적: 본 연구는 79종의 치과 임플란트에 대해 딥러닝을 이용한 식별 모델의 정확도와 임상적 유용성을 평가하는 것을 목적으로 하였다. 연구 재료 및 방법: 2001년부터 2020년까지 30개 치과에서 임플란트 치료를 받은 환자들의 파노라마 방사선 사진에서 총 45396개의 임플란트 고정체 이미지를 수집했다. 수집된 임플란트 이미지는 18개 제조사의 79개 유형이었다. 모델 학습을 위해 EfficientNet 및 Meta Pseudo Labels 알고리즘이 사용되었다. EfficientNet은 EfficientNet-B0 및 EfficientNet-B4가 하위 모델로 사용되었으며, Meta Pseudo Labels는 확장 계수에 따라 두 가지 모델을 적용했다. EfficientNet에 대해 Top 1 정확도를 측정하고 Meta Pseudo Labels에 대해 Top 1 및 Top 5 정확도를 측정하였다. 결과: EfficientNet-B0 및 EfficientNet-B4는 89.4의 Top 1 정확도를 보였다. Meta Pseudo Labels 1은 87.96의 Top 1 정확도를 보였고, 확장 계수가 증가한 Meta Pseudo Labels 2는 88.35를 나타냈다. Top 5 정확도에서 Meta Pseudo Labels 1의 점수는 97.90으로 Meta Pseudo Labels 2의 97.79보다 0.11% 높았다. 결론: 본 연구에서 임플란트 식별에 사용된 4가지 딥러닝 알고리즘은 모두 90%에 가까운 정확도를 보였다. 임플란트 식별을 위한 딥러닝의 임상적 적용 가능성을 높이려면 더 많은 데이터를 수집하고 임플란트에 적합한 미세 조정 알고리즘의 개발이 필요하다.

Keywords

Acknowledgement

This research was financially supported by the Ministry of Science and ICT of Korea through the Institute of Information and Communications Technology Planning and Evaluation in 2021(No.20210012430012002, Setting up Big data of dental case and Developing dental implant identification system based on Deep learning technology).

References

  1. Hammerle CH, Glauser R. Clinical evaluation of dental implant treatment. Periodontol 2000 2004;34:230-9. https://doi.org/10.1046/j.0906-6713.2003.003434.x
  2. Romeo E, Lops D, Margutti E, Ghisolfi M, Chiapasco M, Vogel G. Long-term survival and success of oral implants in the treatment of full and partial arches: a 7-year prospective study with the ITI dental implant system. Int J Oral Maxillofac Implants 2004;19:247-59.
  3. Grossmann Y, Nissan J, Levin L. Clinical effectiveness of implant-supported removable partial dentures: a review of the literature and retrospective case evaluation. J Oral Maxillofac Surg 2009;67:1941-6. https://doi.org/10.1016/j.joms.2009.04.081
  4. Simonis P, Dufour T, Tenenbaum H. Long-term implant survival and success: a 10-16-year follow-up of non-submerged dental implants. Clin Oral Implants Res 2010;21:772-7. https://doi.org/10.1111/j.1600-0501.2010.01912.x
  5. Hadj Said M, Le Roux MK, Catherine JH, Lan R. Development of an artificial intelligence model to identify a dental implant from a radiograph. Int J Oral Maxillofac Implants 2020;36:1077-82.
  6. Misch K, Wang HL. Implant surgery complications: etiology and treatment. Implant Dent 2008;17:159-68. https://doi.org/10.1097/ID.0b013e3181752f61
  7. Annibali S, Ripari M, LA Monaca G, Tonoli F, Cristalli MP. Local complications in dental implant surgery: prevention and treatment. Oral Implantol 2008;1:21-33.
  8. Nedir R, Bischof M, Szmukler-Moncler S, Belser UC, Samson J. Prosthetic complications with dental implants: from an up-to-8-year experience in private practice. Int J Oral Maxillofac Implants 2006;21:919-28.
  9. Sahiwal IG, Woody RD, Benson BW, Guillen GE. Radiographic identification of nonthreaded endosseous dental implants. J Prosthet Dent 2002;87:552-62. https://doi.org/10.1067/mpr.2002.124431
  10. Sewerin I. Identification of dental implants on radiographs. Quintessence Int 1992;23:611-8.
  11. Chan HP, Samala RK, Hadjiiski LM, Zhou C. Deep learning in medical image analysis. Adv Exp Med Biol 2020;1213:3-21. https://doi.org/10.1007/978-3-030-33128-3_1
  12. Hwang JJ, Jung YH, Cho BH, Heo MS. An overview of deep learning in the field of dentistry. Imaging Sci Dent 2019;49:1-7. https://doi.org/10.5624/isd.2019.49.1.1
  13. Lee JH, Kim YT, Lee JB, Jeong SN. A performance comparison between automated deep learning and dental professionals in classification of dental implant systems from dental imaging: a multi-center study. Diagnostics 2020;10:910.
  14. Takahashi T, Nozaki K, Gonda T, Mameno T, Wada M, Ikebe K. Identification of dental implants using deep learning-pilot study. Int J Implant Dent 2020;6:53.
  15. Sukegawa S, Yoshii K, Hara T, Yamashita K, Nakano K, Yamamoto N, Nagatsuka H, Furuki Y. Deep neural networks for dental implant system classification. Biomolecules 2020;10:984.
  16. Kim JE, Nam NE, Shim JS, Jung YH, Cho BH, Hwang JJ. Transfer learning via deep neural networks for implant fixture system classification using periapical radiographs. J Clin Med 2020;9:1117.
  17. Tan M, Le QV. Efficientnet: rethinking model scaling for convolutional neural networks. Proc Mach Learn Res 2019;97:6105-14.
  18. Michelinakis G, Sharrock A, Barclay CW. Identification of dental implants through the use of Implant Recognition Software (IRS). Int Dent J 2006;56:203-8. https://doi.org/10.1111/j.1875-595X.2006.tb00095.x
  19. Zheng Q, Yang M, Tian X, Jiang N, Wang D. A full stage data augmentation method in deep convolutional neural network for natural image classification. Discrete Dyn Nat Soc 2020;1:1-11. https://doi.org/10.1155/S1026022697000022
  20. Truhlar RS, Morris HF, Ochi S. A review of panoramic radiography and its potential use in implant dentistry. Implant Dent 1993;2:122-30. https://doi.org/10.1097/00008505-199305000-00010
  21. Kayal RA. Distortion of digital panoramic radiographs used for implant site assessment. J Orthod Sci 2016;5:117-20.