Imaging Science in Dentistry

  • 제53권3호
  • /
  • Pages.199-207
  • /
  • 2023
  • /
  • 2233-7822(pISSN)
  • /
  • 2233-7830(eISSN)
대한영상치의학회 (Korean Academy of Oral and Maxillofacial Radiology)
권호 표지
DOI QR코드

DOI QR Code

Determining the reliability of diagnosis and treatment using artificial intelligence software with panoramic radiographs

  • 투고 : 2023.05.24
  • 심사 : 2023.07.10
  • 발행 : 2023.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Purpose: The objective of this study was to evaluate the accuracy and effectiveness of an artificial intelligence (AI) program in identifying dental conditions using panoramic radiographs(PRs), as well as to assess the appropriateness of its treatment recommendations. Materials and Methods: PRs from 100 patients(representing 4497 teeth) with known clinical examination findings were randomly selected from a university database. Three dentomaxillofacial radiologists and the Diagnocat AI software evaluated these PRs. The evaluations were focused on various dental conditions and treatments, including canal filling, caries, cast post and core, dental calculus, fillings, furcation lesions, implants, lack of interproximal tooth contact, open margins, overhangs, periapical lesions, periodontal bone loss, short fillings, voids in root fillings, overfillings, pontics, root fragments, impacted teeth, artificial crowns, missing teeth, and healthy teeth. Results: The AI demonstrated almost perfect agreement (exceeding 0.81) in most of the assessments when compared to the ground truth. The sensitivity was very high (above 0.8) for the evaluation of healthy teeth, artificial crowns, dental calculus, missing teeth, fillings, lack of interproximal contact, periodontal bone loss, and implants. However, the sensitivity was low for the assessment of caries, periapical lesions, pontic voids in the root canal, and overhangs. Conclusion: Despite the limitations of this study, the synthesized data suggest that AI-based decision support systems can serve as a valuable tool in detecting dental conditions, when used with PR for clinical dental applications.

키워드

참고문헌

  1. Chartrand G, Cheng PM, Vorontsov E, Drozdzal M, Turcotte S, Pal CJ, et al. Deep learning: a primer for radiologists. Radiographics 2017; 37: 2113-31. https://doi.org/10.1148/rg.2017170077
  2. Hung K, Montalvao C, Tanaka R, Kawai T, Bornstein MM. The use and performance of artificial intelligence applications in dental and maxillofacial radiology: a systematic review. Dentomaxillofac Radiol 2020; 49: 20190107.
  3. Burt JR, Torosdagli N, Khosravan N, RaviPrakash H, Mortazi A, Tissavirasingham F, et al. Deep learning beyond cats and dogs: recent advances in diagnosing breast cancer with deep neural networks. Br J Radiol 2018; 91: 20170545.
  4. Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 2016; 35: 1285-98. https://doi.org/10.1109/TMI.2016.2528162
  5. Kim DH, MacKinnon T. Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clin Radiol 2018; 73: 439-45. https://doi.org/10.1016/j.crad.2017.11.015
  6. Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 2017; 39: 640-51. https://doi.org/10.1109/TPAMI.2016.2572683
  7. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. arXiv:1505.04597 [Preprint]. 2015 [cited 2023 May 20]. Available from https://arxiv.org/abs/1505.04597.
  8. Lee H, Tajmir S, Lee J, Zissen M, Yeshiwas BA, Alkasab TK, et al. Fully automated deep learning system for bone age assessment. J Digit Imaging 2017; 30: 427-41. https://doi.org/10.1007/s10278-017-9955-8
  9. Becker AS, Marcon M, Ghafoor S, Wurnig MC, Frauenfelder T, Boss A. Deep learning in mammography: diagnostic accuracy of a multipurpose image analysis software in the detection of breast cancer. Invest Radiol 2017; 52: 434-40. https://doi.org/10.1097/RLI.0000000000000358
  10. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542: 115-8. https://doi.org/10.1038/nature21056
  11. Rezaei M, Yang H, Meinel C. Deep neural network with l2-norm unit for brain lesions detection. arXiv:1708.05221 [Preprint]. 2017 [cited 2023 May 20]. Available from https://arxiv.org/abs/1708.05221. https://doi.org/10.1007/978-3-319-70093-9_85
  12. Miki Y, Muramatsu C, Hayashi T, Zhou X, Hara T, Katsumata A, et al. Classification of teeth in cone-beam CT using deep convolutional neural network. Comput Biol Med 2017; 80: 24-9. https://doi.org/10.1016/j.compbiomed.2016.11.003
  13. Tuzoff DV, Tuzova LN, Bornstein MM, Krasnov AS, Kharchenko MA, Nikolenko SI, et al. Tooth detection and numbering in panoramic radiographs using convolutional neural networks. Dentomaxillofac Radiol 2019; 48: 20180051.
  14. Chen H, Zhang K, Lyu P, Li H, Zhang L, Wu J, et al. A deep learning approach to automatic teeth detection and numbering based on object detection in dental periapical films. Sci Rep 2019; 9: 3840.
  15. Orhan K, Bayrakdar IS, Ezhov M, Kravtsov A, Ozyurek T. Evaluation of artificial intelligence for detecting periapical pathosis on cone-beam computed tomography scans. Int Endod J 2020; 53: 680-9. https://doi.org/10.1111/iej.13265
  16. Orhan K, Bilgir E, Bayrakdar IS, Ezhov M, Gusarev M, Shumilov E. Evaluation of artificial intelligence for detecting impacted third molars on cone-beam computed tomography scans. J Stomatol Oral Maxillofac Surg 2021; 122: 333-7. https://doi.org/10.1016/j.jormas.2020.12.006
  17. Kurt Bayrakdar S, Orhan K, Bayrakdar IS, Bilgir E, Ezhov M, Gusarev M, et al. A deep learning approach for dental implant planning in cone-beam computed tomography images. BMC Med Imaging 2021; 21: 86.
  18. 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
  19. Lee JS, Adhikari S, Liu L, Jeong HG, Kim H, Yoon SJ. Osteoporosis detection in panoramic radiographs using a deep convolutional neural network-based computer-assisted diagnosis system: a preliminary study. Dentomaxillofac Radiol 2019; 48: 20170344.
  20. Poedjiastoeti W, Suebnukarn S. Application of convolutional neural network in the diagnosis of jaw tumors. Health Inform Res 2018; 24: 236-41. https://doi.org/10.4258/hir.2018.24.3.236
  21. Song IS, Shin HK, Kang JH, Kim JE, Huh KH, Yi WJ, et al. Deep learning-based apical lesion segmentation from panoramic radiographs. Imaging Sci Dent 2022; 52: 351-7. https://doi.org/10.5624/isd.20220078
  22. Widyaningrum R, Candradewi I, Aji NR, Aulianisa R. Comparison of Multi-Label U-Net and Mask R-CNN for panoramic radiograph segmentation to detect periodontitis. Imaging Sci Dent 2022; 52: 383-91. https://doi.org/10.5624/isd.20220105
  23. Khazaei M, Mollabashi V, Khotanlou H, Farhadian M. Sex determination from lateral cephalometric radiographs using an automated deep learning convolutional neural network. Imaging Sci Dent 2022; 52: 239-44. https://doi.org/10.5624/isd.20220016
  24. He K, Gkioxari G, Dollar P, Girshick R. Mask R-CNN. IEEE Trans Pattern Anal Mach Intell 2020; 42: 386-97. https://doi.org/10.1109/TPAMI.2018.2844175
  25. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. arXiv: 1512.03385 [Preprint]. 2017 [cited 2023 May 20]. Available from https://arxiv.org/abs/1512.03385.
  26. Zhaowei C, Vasconcelos N. Cascade R-CNN: Delving into high quality object detection. arXiv: 1712.00726 [Preprint]. 2018 [cited 2023 May 20]. Available from https://arxiv.org/abs/1712.00726.
  27. Mishra A. Contrast limited adaptive histogram equalization (CLAHE) approach for enhancement of the microstructures of friction stir welded joints. arXiv: 2109.00886 [Preprint]. 2021 [cited 2023 May 20]. Available from https://arxiv.org/abs/2109.00886.
  28. Wei Z, Duan C, Song X, Tian Y, Wang H. AMRNet: chips augmentation in aerial images object detection. arXiv:2009.07168 [Preprint]. 2020 [cited 2023 May 20]. Available from https://arxiv.org/abs/2009.07168.
  29. Anwar SM, Majid M, Qayyum A, Awais M, Alnowami M, Khan MK. Medical image analysis using convolutional neural networks: a review. J Med Syst 2018; 42: 226.
  30. Cicek O, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net learning dense volumetric segmentation from sparse annotation. arXiv: 1606.06650 [Preprint]. 2016 [cited 2023 May 20]. Available from https://arxiv.org/abs/1606.06650.
  31. Minnema J, van Eijnatten M, Hendriksen AA, Liberton N, Pelt DM, Batenburg KJ, et al. Segmentation of dental cone-beam CT scans affected by metal artifacts using a mixed-scale dense convolutional neural network. Med Phys 2019; 46: 5027-35. https://doi.org/10.1002/mp.13793
  32. Ezhov M, Gusarev M, Golitsyna M, Yates JM, Kushnerev E, Tamimi D, et al. Clinically applicable artificial intelligence system for dental diagnosis with CBCT. Sci Rep 2021; 11: 15006.
  33. Kositbowornchai S, Plermkamon S, Tangkosol T. Performance of an artificial neural network for vertical root fracture detection: an ex vivo study. Dent Traumatol 2013; 29: 151-5. https://doi.org/10.1111/j.1600-9657.2012.01148.x
  34. Hiraiwa T, Ariji Y, Fukuda M, Kise Y, Nakata K, Katsumata A, et al. A deep learning artificial intelligence system for assessment of root morphology of the mandibular first molar on panoramic radiography. Dentomaxillofac Radiol 2019; 48: 20180218.
  35. Kim J, Lee HS, Song IS, Jung KH. DeNTNet: Deep Neural Transfer Network for the detection of periodontal bone loss using panoramic dental radiographs. Sci Rep 2019; 9: 17615.
  36. Lin PL, Lai YH, Huang PW. An effective classification and numbering system for dental bitewing radiographs using teeth region and contour information. Pattern Recognit 2010; 43: 1380-92. https://doi.org/10.1016/j.patcog.2009.10.005
  37. Hosntalab M, Aghaeizadeh Zoroofi R, Abbaspour Tehrani-Fard A, Shirani G. Classification and numbering of teeth in multi-slice CT images using wavelet-Fourier descriptor. Int J Comput Assist Radiol Surg 2010; 5: 237-49. https://doi.org/10.1007/s11548-009-0389-8
  38. Arik SO, Ibragimov B, Xing L. Fully automated quantitative cephalometry using convolutional neural networks. J Med Imaging (Bellingham) 2017; 4: 014501.
  39. Machiulskiene V, Campus G, Carvalho JC, Dige I, Ekstrand KR, Jablonski-Momeni A, et al. Terminology of dental caries and dental caries management: consensus report of a workshop organized by ORCA and Cariology Research Group of IADR. Caries Res 2020; 54: 7-14. https://doi.org/10.1159/000503309
  40. Mathur VP, Dhillon JK. Dental caries: a disease which needs attention. Indian J Pediatr 2018; 85: 202-6. https://doi.org/10.1007/s12098-017-2381-6
  41. Pitts NB, Zero DT, Marsh PD, Ekstrand K, Weintraub JA, Ramos-Gomez F, et al. Dental caries. Nat Rev Dis Primers 2017; 3: 17030.
  42. Yilmaz H, Keles S. Recent methods for diagnosis of dental caries in dentistry. Meandros Med Dent J 2018; 19: 1-8. https://doi.org/10.4274/meandros.21931
  43. Cantu AG, Gehrung S, Krois J, Chaurasia A, Rossi JG, Gaudin R, et al. Detecting caries lesions of different radiographic extension on bitewings using deep learning. J Dent 2020; 100: 103425.
  44. Prados-Privado M, Garcia Villalon J, Martinez-Martinez CH, Ivorra C, Prados-Frutos JC. Dental caries diagnosis and detection using neural networks: a systematic review. J Clin Med 2020; 9: 3579.
  45. Devlin H, Yuan J. Object position and image magnification in dental panoramic radiography: a theoretical analysis. Dentomaxillofac Radiol 2013; 42: 29951683.
  46. 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