Journal of Periodontal and Implant Science

  • 제54권5호
  • /
  • Pages.349-358
  • /
  • 2024
  • /
  • 2093-2278(pISSN)
  • /
  • 2093-2286(eISSN)
대한치주과학회 (Korean Academy of Periodontology)
권호 표지
DOI QR코드

DOI QR Code

Deep learning to assess bone quality from panoramic radiographs: the feasibility of clinical application through comparison with an implant surgeon and cone-beam computed tomography

  • Jae-Hong Lee (Department of Periodontology, College of Dentistry and Institute of Oral Bioscience, Jeonbuk National University) ;
  • Jeong-Ho Yun (Department of Periodontology, College of Dentistry and Institute of Oral Bioscience, Jeonbuk National University) ;
  • Yeon-Tae Kim (Department of Periodontology, Daejeon Dental Hospital, Institute of Wonkwang Dental Research, Wonkwang University College of Dentistry)
  • 투고 : 2023.06.01
  • 심사 : 2023.10.05
  • 발행 : 2024.10.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Purpose: Bone quality is one of the most important clinical factors for the primary stability and successful osseointegration of dental implants. This preliminary pilot study aimed to evaluate the clinical applicability of deep learning (DL) for assessing bone quality using panoramic (PA) radiographs compared with an implant surgeon's subjective tactile sense and cone-beam computed tomography (CBCT) values. Methods: In total, PA images of 2,270 edentulous sites for implant placement were selected, and the corresponding CBCT relative gray value measurements and bone quality classification were performed using 3-dimensional dental image analysis software. Based on the pre-trained and fine-tuned ResNet-50 architecture, the bone quality classification of PA images was classified into 4 levels, from D1 to D4, and Spearman correlation analyses were performed with the implant surgeon's tactile sense and CBCT values. Results: The classification accuracy of DL was evaluated using a test dataset comprising 454 cropped PA images, and it achieved an area under the receiving characteristic curve of 0.762 (95% confidence interval [CI], 0.714-0.810). Spearman correlation analysis of bone quality showed significant positive correlations with the CBCT classification (r=0.702; 95% CI, 0.651-0.747; P<0.001) and the surgeon's tactile sense (r=0.658; 95% CI, 0.600-0.708, P<0.001) versus the DL classification. Conclusions: DL classification using PA images showed a significant and consistent correlation with CBCT classification and the surgeon's tactile sense in classifying the bone quality at the implant placement site. Further research based on high-quality quantitative datasets is essential to increase the reliability and validity of this method for actual clinical applications.

키워드

과제정보

This study was supported by a National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No. 2019R1A2C1083978) and research funds for newly appointed professors of Jeonbuk National University in 2023.

참고문헌

  1. Quirynen M, Herrera D, Teughels W, Sanz M. Implant therapy: 40 years of experience. Periodontol 2000 2014;66:7-12.
  2. Lee JH, Kim YT, Jeong SN, Kim NH, Lee DW. Incidence and pattern of implant fractures: a long-term follow-up multicenter study. Clin Implant Dent Relat Res 2018;20:463-9.
  3. Howe MS, Keys W, Richards D. Long-term (10-year) dental implant survival: a systematic review and sensitivity meta-analysis. J Dent 2019;84:9-21.
  4. Park YS, Lee BA, Choi SH, Kim YT. Evaluation of failed implants and reimplantation at sites of previous dental implant failure: survival rates and risk factors. J Periodontal Implant Sci 2022;52:230-41.
  5. Chrcanovic BR, Albrektsson T, Wennerberg A. Bone quality and quantity and dental implant failure: a systematic review and meta-analysis. Int J Prosthodont 2017;30:219-37.
  6. Shapurian T, Damoulis PD, Reiser GM, Griffin TJ, Rand WM. Quantitative evaluation of bone density using the Hounsfield index. Int J Oral Maxillofac Implants 2006;21:290-7.
  7. De Vos W, Casselman J, Swennen GR. Cone-beam computerized tomography (CBCT) imaging of the oral and maxillofacial region: a systematic review of the literature. Int J Oral Maxillofac Implants 2009;38:609-25.
  8. Fokas G, Vaughn VM, Scarfe WC, Bornstein MM. Accuracy of linear measurements on CBCT images related to presurgical implant treatment planning: a systematic review. Clin Oral Implants Res 2018;29 Suppl 16:393-415.
  9. Naitoh M, Hirukawa A, Katsumata A, Ariji E. Evaluation of voxel values in mandibular cancellous bone: relationship between cone-beam computed tomography and multislice helical computed tomography. Clin Oral Implants Res 2009;20:503-6.
  10. Pauwels R, Nackaerts O, Bellaiche N, Stamatakis H, Tsiklakis K, Walker A, et al. Variability of dental cone beam CT grey values for density estimations. Br J Radiol 2013;86:20120135.
  11. Shen D, Wu G, Suk HI. Deep learning in medical image analysis. Annu Rev Biomed Eng 2017;19:221-48.
  12. Lee JH, Kim DH, Jeong SN, Choi SH. Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm. J Periodontal Implant Sci 2018;48:114-23.
  13. Lee JH, Kim DH, Jeong SN, Choi SH. Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm. J Dent 2018;77:106-11.
  14. Lee JH, Kim DH, Jeong SN. Diagnosis of cystic lesions using panoramic and cone beam computed tomographic images based on deep learning neural network. Oral Dis 2020;26:152-8.
  15. Mohammad-Rahimi H, Motamedian SR, Pirayesh Z, Haiat A, Zahedrozegar S, Mahmoudinia E, et al. Deep learning in periodontology and oral implantology: A scoping review. J Periodontal Res 2022;57:942-51.
  16. Lee JH, Kim YT, Lee JB, Jeong SN. Deep learning improves implant classification by dental professionals: a multi-center evaluation of accuracy and efficiency. J Periodontal Implant Sci 2022;52:220-9.
  17. Lee DW, Kim SY, Jeong SN, Lee JH. Artificial intelligence in fractured dental implant detection and classification: evaluation using dataset from two dental hospitals. Diagnostics (Basel) 2021;11:233.
  18. Yong TH, Yang S, Lee SJ, Park C, Kim JE, Huh KH, et al. QCBCT-NET for direct measurement of bone mineral density from quantitative cone-beam CT: a human skull phantom study. Sci Rep 2021;11:15083.
  19. Huang N, Liu P, Yan Y, Xu L, Huang Y, Fu G, et al. Predicting the risk of dental implant loss using deep learning. J Clin Periodontol 2022;49:872-83.
  20. de Oliveira RC, Leles CR, Normanha LM, Lindh C, Ribeiro-Rotta RF. Assessments of trabecular bone density at implant sites on CT images. Oral Surg Oral Med Oral Pathol Oral Radiol Endod 2008;105:231-8.
  21. Misch CE. Contemporary implant dentistry. 2nd ed. St. Louis: Mosby; 1999.
  22. Jeong KI, Kim SG, Oh JS, Jeong MA. Consideration of various bone quality evaluation methods. Implant Dent 2013;22:55-9.
  23. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 Jun 27-30; Las Vegas, USA. Piscataway: IEEE; 2016. p.770-8.
  24. Park W, Schwendicke F, Krois J, Huh JK, Lee JH. Identification of dental implant systems using a largescale multicenter data set. J Dent Res 2023;102:727-33.
  25. Friberg B, Jemt T, Lekholm U. Early failures in 4,641 consecutively placed Branemark dental implants: a study from stage 1 surgery to the connection of completed prostheses. Int J Oral Maxillofac Implants 1991;6:142-6.
  26. Lekholm U, Zarb G. Patient selection and preparation. Tissue integrated prostheses. In: Branemark PI, Zarb GA, Albrektsson T, editors. Osseointegration in clinical dentistry. Chicago: Quintessence Publishing Company; 1985. p.199-209.
  27. Pauwels R, Jacobs R, Singer SR, Mupparapu M. CBCT-based bone quality assessment: are Hounsfield units applicable? Dentomaxillofac Radiol 2015;44:20140238.
  28. Akdeniz BG, Oksan T, Kovanlikaya I, Genc I. Evaluation of bone height and bone density by computed tomography and panoramic radiography for implant recipient sites. J Oral Implantol 2000;26:114-9.
  29. Taguchi A, Tanimoto K, Akagawa Y, Suei Y, Wada T, Rohlin M. Trabecular bone pattern of the mandible. Comparison of panoramic radiography with computed tomography. Dentomaxillofac Radiol 1997;26:85-9.
  30. Guerrero ME, Noriega J, Castro C, Jacobs R. Does cone-beam CT alter treatment plans? Comparison of preoperative implant planning using panoramic versus cone-beam CT images. Imaging Sci Dent 2014;44:121-8.
  31. Rokn A, Rasouli Ghahroudi AA, Daneshmonfared M, Menasheof R, Shamshiri AR. Tactile sense of the surgeon in determining bone density when placing dental implant. Implant Dent 2014;23:697-703.
  32. Lee S, Gantes B, Riggs M, Crigger M. Bone density assessments of dental implant sites: 3. Bone quality evaluation during osteotomy and implant placement. Int J Oral Maxillofac Implants 2007;22:208-12.
  33. Rushton VE, Horner K, Worthington HV. The quality of panoramic radiographs in a sample of general dental practices. Br Dent J 1999;186:630-3.
  34. Dhillon M, Raju SM, Verma S, Tomar D, Mohan RS, Lakhanpal M, et al. Positioning errors and quality assessment in panoramic radiography. Imaging Sci Dent 2012;42:207-12.
  35. van der Stelt PF. Panoramic radiographs in dental diagnostics. Ned Tijdschr Tandheelkd 2016;123:181-7.
  36. Ridao-Sacie C, Segura-Egea JJ, Fernandez-Palacin A, Bullon-Fernandez P, Rios-Santos JV. Radiological assessment of periapical status using the periapical index: comparison of periapical radiography and digital panoramic radiography. Int Endod J 2007;40:433-40.
  37. Lee JH, Jeong SN. Efficacy of deep convolutional neural network algorithm for the identification and classification of dental implant systems, using panoramic and periapical radiographs: a pilot study. Medicine (Baltimore) 2020;99:e20787.
  38. 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 (Basel) 2020;10:910.
  39. Park W, Huh JK, Lee JH. Automated deep learning for classification of dental implant radiographs using a large multi-center dataset. Sci Rep 2023;13:4862.
  40. Molly L. Bone density and primary stability in implant therapy. Clin Oral Implants Res 2006;17 Suppl 2:124-35.