Imaging Science in Dentistry

Korean Academy of Oral and Maxillofacial Radiology (대한영상치의학회)
권호 표지
DOI QR코드

DOI QR Code

Convolutional neural networks for automated tooth numbering on panoramic radiographs: A scoping review

  • Ramadhan Hardani Putra (Department of Dentomaxillofacial Radiology, Faculty of Dental Medicine, Universitas Airlangga) ;
  • Eha Renwi Astuti (Department of Dentomaxillofacial Radiology, Faculty of Dental Medicine, Universitas Airlangga) ;
  • Aga Satria Nurrachman (Department of Dentomaxillofacial Radiology, Faculty of Dental Medicine, Universitas Airlangga) ;
  • Dina Karimah Putri (Department of Dentomaxillofacial Radiology, Faculty of Dental Medicine, Universitas Airlangga) ;
  • Ahmad Badruddin Ghazali (Oral Radiology Unit, Department of Oral Maxillofacial Surgery and Oral Diagnosis, Kulliyyah of Dentistry, International Islamic University Malaysia) ;
  • Tjio Andrinanti Pradini (Faculty of Dental Medicine, Universitas Airlangga) ;
  • Dhinda Tiara Prabaningtyas (Faculty of Dental Medicine, Universitas Airlangga)
  • Received : 2023.03.08
  • Accepted : 2023.07.14
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: The objective of this scoping review was to investigate the applicability and performance of various convolutional neural network (CNN) models in tooth numbering on panoramic radiographs, achieved through classification, detection, and segmentation tasks. Materials and Methods: An online search was performed of the PubMed, Science Direct, and Scopus databases. Based on the selection process, 12 studies were included in this review. Results: Eleven studies utilized a CNN model for detection tasks, 5 for classification tasks, and 3 for segmentation tasks in the context of tooth numbering on panoramic radiographs. Most of these studies revealed high performance of various CNN models in automating tooth numbering. However, several studies also highlighted limitations of CNNs, such as the presence of false positives and false negatives in identifying decayed teeth, teeth with crown prosthetics, teeth adjacent to edentulous areas, dental implants, root remnants, wisdom teeth, and root canal-treated teeth. These limitations can be overcome by ensuring both the quality and quantity of datasets, as well as optimizing the CNN architecture. Conclusion: CNNs have demonstrated high performance in automated tooth numbering on panoramic radiographs. Future development of CNN-based models for this purpose should also consider different stages of dentition, such as the primary and mixed dentition stages, as well as the presence of various tooth conditions. Ultimately, an optimized CNN architecture can serve as the foundation for an automated tooth numbering system and for further artificial intelligence research on panoramic radiographs for a variety of purposes.

Keywords

References

  1. Ossowska A, Kusiak A, Swietlik D. Artificial intelligence in dentistry - narrative review. Int J Environ Res Public Health 2022; 19: 3449.
  2. Izzetti R, Nisi M, Aringhieri G, Crocetti L, Graziani F, Nardi C. Basic knowledge and new advances in panoramic radiography imaging techniques: a narrative review on what dentists and radiologists should know. Appl Sci(Basel) 2021; 11: 7858.
  3. Rozylo-Kalinowska I. Panoramic radiography in dentistry. In: Imaging techniques in dental radiology. Cham; Springer: 2020. p. 43-56.
  4. Thanathornwong B, Suebnukarn S. Automatic detection of periodontal compromised teeth in digital panoramic radiographs using faster regional convolutional neural networks. Imaging Sci Dent 2020; 50: 169-74. https://doi.org/10.5624/isd.2020.50.2.169
  5. Havale R, Sheetal BS, Patil R, Hemant Kumar R, Anegundi RT, Inushekar KR. Dental notation for primary teeth: a review and suggestion of a novel system. Eur J Paediatr Dent 2015; 16: 163-6.
  6. Forrest A. Forensic odontology in DVI: current practice and recent advances. Forensic Sci Res 2019; 4: 316-30. https://doi.org/10.1080/20961790.2019.1678710
  7. Muller A, Mertens SM, Gostemeyer G, Krois J, Schwendicke F. Barriers and enablers for artificial intelligence in dental diagnostics: a qualitative study. J Clin Med 2021; 10: 1612.
  8. Mosadeghrad AM. Factors influencing healthcare service quality. Int J Health Policy Manag 2014; 3: 77-89. https://doi.org/10.15171/ijhpm.2014.65
  9. Joda T, Yeung AW, Hung K, Zitzmann NU, Bornstein MM. Disruptive innovation in dentistry: what it is and what could be next. J Dent Res 2021; 100: 448-53. https://doi.org/10.1177/0022034520978774
  10. Yasaka K, Abe O. Deep learning and artificial intelligence in radiology: current applications and future directions. PLoS Med 2018; 15: e1002707.
  11. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional. In: Pereira F, Burges CJ, Bottou L, Weinberger KQ. Advances in Neural Information Processing Systems 25 (NIPS 2012). San Mateo: Morgan Kaufmann Publishers; 2012.
  12. Soffer S, Ben-Cohen A, Shimon O, Amitai MM, Greenspan H, Klang E. Convolutional neural networks for radiologic images: a radiologist's guide. Radiology 2019; 290: 590-606. https://doi.org/10.1148/radiol.2018180547
  13. Schwendicke F, Golla T, Dreher M, Krois J. Convolutional neural networks for dental image diagnostics: a scoping review. J Dent 2019; 91: 103226.
  14. Putra RH, Doi C, Yoda N, Astuti ER, Sasaki K. Current applications and development of artificial intelligence for digital dental radiography. Dentomaxillofac Radiol 2022; 51: 20210197.
  15. Roosanty A, Widyaningrum R, Diba SF. Artificial intelligence based on Convolutional Neural Network for detecting dental caries on bitewing and periapical radiographs. J Radiol Dentomaksilofas Indones 2022; 6: 89-94. https://doi.org/10.32793/jrdi.v6i2.867
  16. Musri N, Christie B, Ichwan SJ, Cahyanto A. Deep learning convolutional neural network algorithms for the early detection and diagnosis of dental caries on periapical radiographs: a systematic review. Imaging Sci Dent 2021; 51: 237-42. https://doi.org/10.5624/isd.20210074
  17. 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
  18. 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.
  19. Nadal C, Sas C, Doherty G. Technology acceptance in mobile health: scoping review of definitions, models, and measurement. J Med Internet Res 2020; 22: e17256.
  20. Daudt HM, van Mossel C, Scott SJ. Enhancing the scoping study methodology: a large, inter-professional team's experience with Arksey and O'Malley's framework. BMC Med Res Methodol 2013; 13: 48.
  21. 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.
  22. Kim C, Kim D, Jeong H, Yoon SJ, Youm S. Automatic tooth detection and numbering using a combination of a CNN and heuristic algorithm. Appl Sci(Basel) 2020; 10: 5624.
  23. Mahdi FP, Motoki K, Kobashi S. Optimization technique combined with deep learning method for teeth recognition in dental panoramic radiographs. Sci Rep 2020; 10: 19261.
  24. Bilgir E, Bayrakdar IS, Celik O, Orhan K, Akkoca F, Saglam H, et al. An artificial intelligence approach to automatic tooth detection and numbering in panoramic radiographs. BMC Med Imaging 2021; 21: 124.
  25. Kilic MC, Bayrakdar IS, Celik O, Bilgir E, Orhan K, Aydin OB, et al. Artificial intelligence system for automatic deciduous tooth detection and numbering in panoramic radiographs. Dentomaxillofac Radiol 2021; 50: 20200172.
  26. Lin SY, Chang HY. Tooth numbering and condition recognition on dental panoramic radiograph images using CNNs. IEEE Access 2021; 9: 166008-26.
  27. Prados-Privado M, Garcia Villalon J, Blazquez Torres A, Martinez-Martinez CH, Ivorra C. A convolutional neural network for automatic tooth numbering in panoramic images. Biomed Res Int 2021; 2021: 3625386.
  28. Vinayahalingam S, Goey RS, Kempers S, Schoep J, Cherici T, Moin DA, et al. Automated chart filing on panoramic radiographs using deep learning. J Dent 2021; 115: 103864.
  29. Yuksel AE, Gultekin S, Simsar E, Ozdemir SD, Gundogar M, Tokgoz SB, et al. Dental enumeration and multiple treatment detection on panoramic X-rays using deep learning. Sci Rep 2021; 11: 12342.
  30. Chandrashekar G, AlQarni S, Bumann EE, Lee Y. Collaborative deep learning model for tooth segmentation and identification using panoramic radiographs. Comput Biol Med 2022; 148: 105829.
  31. Choi HR, Siadari TS, Kim JE, Huh KH, Yi WJ, Lee SS, et al. Automatic detection of teeth and dental treatment patterns on dental panoramic radiographs using deep neural networks. Forensic Sci Res 2022; 7: 456-66. https://doi.org/10.1080/20961790.2022.2034714
  32. Mima Y, Nakayama R, Hizukuri A, Murata K. Tooth detection for each tooth type by application of faster R-CNNs to divided analysis areas of dental panoramic X-ray images. Radiol Phys Technol 2022; 15: 170-6. https://doi.org/10.1007/s12194-022-00659-1
  33. Shirsat S, Abraham S. Tooth detection from panoramic radiographs using deep learning. In: Srirama SN, Lin JC, Bhatnagar R, Agarwal S, Reddy PK. Big Data Analytics: 9th International Conference on Big Data Analytics Proceedings. Berlin: Springer-Verlag; 2021. p. 54-63.
  34. Su Y, Li D, Chen X. Lung nodule detection based on faster R-CNN framework. Comput Methods Programs Biomed 2021; 200: 105866.
  35. Gavrilescu R, Zet C, Fosalau C, Skoczylas M, Cotovanu D. Faster R-CNN: an approach to real-time object detection. In: 2018 International Conference and Exposition on Electrical and Power Engineering (EPE). Iasi, Romania: IEEE; 2018. p. 0165-8. Available from https://ieeexplore.ieee.org/document/8559776.
  36. Shih KH, Chiu CT, Lin JA, Bu YY. Real-time object detection with reduced region proposal network via multi-feature concatenation. IEEE Trans Neural Netw Learn Syst 2020; 31: 2164-73. https://doi.org/10.1109/TNNLS.2019.2929059
  37. Wang C, Peng Z. Design and implementation of an object detection system using faster R-CNN. In: 2019 International Conference on Robots & Intelligent System (ICRIS). Haikou, China: IEEE; 2019. p. 204-6. Available from https://ieeexplore.ieee.org/abstract/document/8806291.
  38. Bharati P, Pramanik A. Deep learning techniques - R-CNN to mask R-CNN: a survey. In: Computational Intelligence in Pattern Recognition. Springer; 2020. p. 657-68.
  39. Zhang Y, Chu J, Leng L, Miao J. Mask-refined R-CNN: a network for refining object details in instance segmentation. Sensors(Basel) 2020; 20: 1010.
  40. Hu Y, Huber A, Anumula J, Liu SC. Overcoming the vanishing gradient problem in plain recurrent networks [Internet]. arXiv 2018; 1801.06105 [cited 2023 Mar 8]. Available from https://arxiv.org/abs/1801.06105v3.
  41. Zhang K, Sun M, Han TX, Yuan X, Guo L, Liu T. Residual networks of residual networks: Multilevel residual networks. IEEE Trans Circuits Syst Video Technol 2018; 28: 1303-14. https://doi.org/10.1109/TCSVT.2017.2654543
  42. Wickramasinghe CS, Marino DL, Manic M. ResNet autoencoders for unsupervised feature learning from high-dimensional data: deep models resistant to performance degradation. IEEE Access 2021; 9: 40511-20. https://doi.org/10.1109/ACCESS.2021.3064819
  43. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition [Internet]. arXiv 2015; 1512.03385v1 [cited 2023 Mar 8]. Available from https://arxiv.org/abs/1512.03385.
  44. Mukhometzianov R, Carrillo J. CapsNet comparative performance evaluation for image classification [Internet]. arXiv 2018: 1805.11195. Available from https://arxiv.org/abs/1805.11195.
  45. Hu J, Shen L, Albanie S, Sun G, Vedaldi A. Gather-Excite: exploiting feature context in convolutional neural networks [Internet]. arXiv 2019; 1810.12348 [cited 2023 Mar 8]. Available from https://arxiv.org/abs/1810.12348.
  46. Ding X, Zhang X, Ma N, Han J, Ding G, Sun J. RepVGG: making VGG-style convnets great again [Internet]. arXiv 2021; 2101.03697 [cited 2023 Mar 8]. Available from https://arxiv.org/abs/2101.03697.
  47. Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, Liang J. UNet++: a nested u-net architecture for medical image segmentation [Internet]. arXiv 2018; 1807.10165 [cited 2023 Mar 8]. Avaiable from https://arxiv.org/abs/1807.10165.
  48. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation [Internet]. arXiv 2015; 1505.04597 [cited cited 2023 Mar 8]. Avaiable from https://arxiv.org/abs/1505.04597.
  49. Chen X, Williams BM, Vallabhaneni SR, Czanner G, Williams R, Zheng Y. Learning active contour models for medical image segmentation. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA; 2019. p. 11624-32.
  50. Patil DD, Deore SG. Medical image segmentation: a review. Int J Comput Sci Mob Comput 213; 2: 22-7.
  51. Fan J, Zhang Z, Song C, Tan T. Learning integral objects with intra-class discriminator for weakly-supervised semantic segmentation. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020, p. 4282-91.
  52. 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
  53. Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data 2021; 8: 53.