Journal of Korean Dental Science

Korean Academy of Dental Science (대한치의학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning Based Radiographic Classification of Morphology and Severity of Peri-implantitis Bone Defects: A Preliminary Pilot Study

  • 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)
  • Received : 2023.06.13
  • Accepted : 2023.06.28
  • Published : 2023.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: The aim of this study was to evaluate the feasibility of deep learning techniques to classify the morphology and severity of peri-implantitis bone defects based on periapical radiographs. Materials and Methods: Based on a pre-trained and fine-tuned ResNet-50 deep learning algorithm, the morphology and severity of peri-implantitis bone defects on periapical radiographs were classified into six groups (class I/II and slight/moderate/severe). Accuracy, precision, recall, and F1 scores were calculated to measure accuracy. Result: A total of 971 dental images were included in this study. Deep-learning-based classification achieved an accuracy of 86.0% with precision, recall, and F1 score values of 84.45%, 81.22%, and 82.80%, respectively. Class II and moderate groups had the highest F1 scores (92.23%), whereas class I and severe groups had the lowest F1 scores (69.33%). Conclusion: The artificial intelligence-based deep learning technique is promising for classifying the morphology and severity of peri-implantitis. However, further studies are required to validate their feasibility in clinical practice.

Keywords

Acknowledgement

This study was supported by a National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No. 2019R1A2C1083978).

References

  1. Srinivasan M, Meyer S, Mombelli A, Muller F. Dental implants in the elderly population: a systematic review and meta-analysis. Clin Oral Implants Res. 2017; 28: 920-30. https://doi.org/10.1111/clr.12898
  2. Barfeie A, Wilson J, Rees J. Implant surface characteristics and their effect on osseointegration. Br Dent J. 2015; 218: E9.
  3. Liu Y, Rath B, Tingart M, Eschweiler J. Role of implants surface modification in osseointegration: a systematic review. J Biomed Mater Res A. 2020; 108: 470-84. https://doi.org/10.1002/jbm.a.36829
  4. Lee JH, Kim DH, Jeong SN. Comparative assessment of anterior maxillary alveolar ridge preservation with and without adjunctive use of enamel matrix derivative: a randomized clinical trial. Clin Oral Implants Res. 2020; 31: 1-9. https://doi.org/10.1111/clr.13530
  5. Lee JH, Jung EH, Jeong SN. Profilometric, volumetric, and esthetic analysis of guided bone regeneration with L-shaped collagenated bone substitute and connective tissue graft in the maxillary esthetic zone: a case series with 1-year observational study. Clin Implant Dent Relat Res. 2022; 24: 655-63. https://doi.org/10.1111/cid.13116
  6. Jung RE, Zembic A, Pjetursson BE, Zwahlen M, Thoma DS. Systematic review of the survival rate and the incidence of biological, technical, and aesthetic complications of single crowns on implants reported in longitudinal studies with a mean follow-up of 5 years. Clin Oral Implants Res. 2012; 23 (Suppl 6): 2-21. https://doi.org/10.1111/j.1600-0501.2012.02547.x
  7. Pjetursson BE, Asgeirsson AG, Zwahlen M, Sailer I. Improvements in implant dentistry over the last decade: comparison of survival and complication rates in older and newer publications. Int J Oral Maxillofac Implants. 2014; 29(Suppl): 308-24. https://doi.org/10.11607/jomi.2014suppl.g5.2
  8. Di Francesco F, De Marco G, Gironi Carnevale UA, Lanza M, Lanza A. The number of implants required to support a maxillary overdenture: a systematic review and meta-analysis. J Prosthodont Res. 2019; 63: 15-24. https://doi.org/10.1016/j.jpor.2018.08.006
  9. 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. https://doi.org/10.1111/cid.12621
  10. Darby I. Risk factors for periodontitis & peri-implantitis. Periodontol 2000. 2022; 90: 9-12. https://doi.org/10.1111/prd.12447
  11. Berglundh T, Armitage G, Araujo MG, Avila-Ortiz G, Blanco J, Camargo PM, Chen S, Cochran D, Derks J, Figuero E, Hammerle CHF, Heitz-Mayfield LJA, Huynh-Ba G, Iacono V, Koo KT, Lambert F, McCauley L, Quirynen M, Renvert S, Salvi GE, Schwarz F, Tarnow D, Tomasi C, Wang HL, Zitzmann N. Peri-implant diseases and conditions: consensus report of workgroup 4 of the 2017 World Workshop on the Classification of Periodontal and Peri-Implant Diseases and Conditions. J Periodontol. 2018; 89(Suppl 1): S313-8. https://doi.org/10.1002/JPER.17-0739
  12. Papapanou PN, Sanz M, Buduneli N, Dietrich T, Feres M, Fine DH, Flemmig TF, Garcia R, Giannobile WV, Graziani F, Greenwell H, Herrera D, Kao RT, Kebschull M, Kinane DF, Kirkwood KL, Kocher T, Kornman KS, Kumar PS, Loos BG, Machtei E, Meng H, Mombelli A, Needleman I, Offenbacher S, Seymour GJ, Teles R, Tonetti MS. Periodontitis: consensus report of workgroup 2 of the 2017 World Workshop on the Classification of Periodontal and Peri-Implant Diseases and Conditions. J Periodontol. 2018; 89(Suppl 1): S173-82. https://doi.org/10.1002/JPER.17-0721
  13. Dreyer H, Grischke J, Tiede C, Eberhard J, Schweitzer A, Toikkanen SE, Glockner S, Krause G, Stiesch M. Epidemiology and risk factors of peri-implantitis: a systematic review. J Periodontal Res. 2018; 53: 657-81. https://doi.org/10.1111/jre.12562
  14. Nguyen-Hieu T, Borghetti A, Aboudharam G. Peri-implantitis: from diagnosis to therapeutics. J Investig Clin Dent. 2012; 3: 79-94. https://doi.org/10.1111/j.2041-1626.2012.00116.x
  15. Chen X, Wang X, Zhang K, Fung KM, Thai TC, Moore K, Mannel RS, Liu H, Zheng B, Qiu Y. Recent advances and clinical applications of deep learning in medical image analysis. Med Image Anal. 2022; 79: 102444.
  16. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, Sanchez CI. A survey on deep learning in medical image analysis. Med Image Anal. 2017; 42: 60-88. https://doi.org/10.1016/j.media.2017.07.005
  17. Mohammad-Rahimi H, Motamedian SR, Pirayesh Z, Haiat A, Zahedrozegar S, Mahmoudinia E, Rohban MH, Krois J, Lee JH, Schwendicke F. Deep learning in periodontology and oral implantology: a scoping review. J Periodontal Res. 2022; 57: 942-51. https://doi.org/10.1111/jre.13037
  18. Chaurasia A, Namachivayam A, Koca-unsal RB, Lee JH. Deep-learning performance in identifying and classifying dental implant systems from dental imaging: a systematic review and meta-analysis. J Periodontal Implant Sci. 2023. doi: 10.5051/jpis.2300160008 [Epub ahead of print]
  19. Park W, Schwendicke F, Krois J, Huh JK, Lee JH. Identification of dental implant systems using a large-scale multicenter data set. J Dent Res. 2023; 102: 727-33. https://doi.org/10.1177/00220345231160750
  20. 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. Erratum in: Sci Rep. 2023; 13: 6559.
  21. Schwarz F, Herten M, Sager M, Bieling K, Sculean A, Becker J. Comparison of naturally occurring and ligature-induced peri-implantitis bone defects in humans and dogs. Clin Oral Implants Res. 2007; 18: 161-70. Erratum in: Clin Oral Implants Res. 2007; 18: 397.
  22. Monje A, Pons R, Insua A, Nart J, Wang HL, Schwarz F. Morphology and severity of peri-implantitis bone defects. Clin Implant Dent Relat Res. 2019; 21: 635-43. https://doi.org/10.1111/cid.12791
  23. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. arXiv. 2015. doi: 10.48550/arXiv.1512.03385
  24. Sanz M, Chapple IL; Working Group 4 of the VIII European Workshop on Periodontology. Clinical research on peri-implant diseases: consensus report of Working Group 4. J Clin Periodontol. 2012; 39(Suppl 12): 202-6. https://doi.org/10.1111/j.1600-051X.2011.01837.x
  25. Socransky SS, Haffajee AD. Periodontal microbial ecology. Periodontol 2000. 2005; 38: 135-87. https://doi.org/10.1111/j.1600-0757.2005.00107.x
  26. Renvert S, Polyzois IN. Clinical approaches to treat peri-implant mucositis and peri-implantitis. Periodontol 2000. 2015; 68: 369-404. https://doi.org/10.1111/prd.12069
  27. Scarano A, Khater AGA, Gehrke SA, Serra P, Francesco I, Di Carmine M, Tari SR, Leo L, Lorusso F. Current status of peri-implant diseases: a clinical review for evidence-based decision making. J Funct Biomater. 2023; 14: 210.
  28. 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. https://doi.org/10.5051/jpis.2018.48.2.114
  29. 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. https://doi.org/10.1016/j.jdent.2018.07.015
  30. 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. https://doi.org/10.1111/odi.13223
  31. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Paper presented at: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 June 27-30; Las Vegas, NV, USA. p. 770-8.
  32. 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.
  33. 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.