Imaging Science in Dentistry

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

DOI QR Code

Evaluation of deep learning and convolutional neural network algorithms for mandibular fracture detection using radiographic images: A systematic review and meta-analysis

  • Mahmood Dashti (Dentofacial Deformities Research Center, Research Institute of Dental Sciences, Shahid Beheshti University of Medical Sciences) ;
  • Sahar Ghaedsharaf (Department of Oral and Maxillofacial Radiology, School of Dentistry, Shahid Beheshti University of Medical Sciences) ;
  • Shohreh Ghasemi (Department of Trauma and Craniofacial Reconstruction, Queen Mary College) ;
  • Niusha Zare (Department of Operative Dentistry, University of Southern California) ;
  • Elena-Florentina Constantin (Dental School, Carol Davila University of Medical Sciences) ;
  • Amir Fahimipour (Discipline of Oral Surgery, Medicine and Diagnostics, School of Dentistry, Faculty of Medicine and Health, Westmead Centre for Oral Health, The University of Sydney) ;
  • Neda Tajbakhsh (School of Dentistry, Islamic Azad University Tehran, Dental Branch) ;
  • Niloofar Ghadimi (Department of Oral and Maxillofacial Radiology, Dental School, Islamic Azad University of Medical Sciences)
  • Received : 2024.03.01
  • Accepted : 2024.06.04
  • Published : 2024.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: The use of artificial intelligence (AI) and deep learning algorithms in dentistry, especially for processing radiographic images, has markedly increased. However, detailed information remains limited regarding the accuracy of these algorithms in detecting mandibular fractures. Materials and Methods: This meta-analysis was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Specific keywords were generated regarding the accuracy of AI algorithms in detecting mandibular fractures on radiographic images. Then, the PubMed/Medline, Scopus, Embase, and Web of Science databases were searched. The Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool was employed to evaluate potential bias in the selected studies. A pooled analysis of the relevant parameters was conducted using STATA version 17 (StataCorp, College Station, TX, USA), utilizing the metandi command. Results: Of the 49 studies reviewed, 5 met the inclusion criteria. All of the selected studies utilized convolutional neural network algorithms, albeit with varying backbone structures, and all evaluated panoramic radiography images. The pooled analysis yielded a sensitivity of 0.971 (95% confidence interval [CI]: 0.881-0.949), a specificity of 0.813 (95% CI: 0.797-0.824), and a diagnostic odds ratio of 7.109 (95% CI: 5.27-8.913). Conclusion: This review suggests that deep learning algorithms show potential for detecting mandibular fractures on panoramic radiography images. However, their effectiveness is currently limited by the small size and narrow scope of available datasets. Further research with larger and more diverse datasets is crucial to verify the accuracy of these tools in in practical dental settings.

Keywords

Acknowledgement

During the preparation of this work, the authors used ChatGPT 4 (OpenAI, San Francisco, CA, USA) to improve the flow and grammar of the manuscript. After using this tool, the authors reviewed and edited the content as needed. The authors take full responsibility for the content of the publication.

References

  1. Agrawal P, Nikhade P. Artificial intelligence in dentistry: past, present, and future. Cureus 2022; 14: e27405.
  2. Toh TS, Dondelinger F, Wang D. Looking beyond the hype: applied AI and machine learning in translational medicine. EBioMedicine. 2019; 47: 607-15. https://doi.org/10.1016/j.ebiom.2019.08.027
  3. Chen YW, Stanley K, Att W. Artificial intelligence in dentistry: current applications and future perspectives. Quintessence Int 2020; 51: 248-57.
  4. Schmidhuber J. Deep learning in neural networks: an overview. Neural Netw 2015; 61: 85-117. https://doi.org/10.1016/j.neunet.2014.09.003
  5. Yamashita R, Nishio M, Do RK, Togashi K. Convolutional neural networks: an overview and application in radiology. Insights Imaging 2018; 9: 611-29.
  6. Zhang Z, Sejdic E. Radiological images and machine learning: trends, perspectives, and prospects. Comput Biol Med 2019; 108: 354-70. https://doi.org/10.1016/j.compbiomed.2019.02.017
  7. Rodrigues JA, Krois J, Schwendicke F. Demystifying artificial intelligence and deep learning in dentistry. Braz Oral Res 2021; 35: e094.
  8. Brown JS, Khan A, Wareing S, Schache AG. A new classification of mandibular fractures. Int J Oral Maxillofac Surg 2022; 51: 78-90. https://doi.org/10.1016/j.ijom.2021.02.012
  9. Boffano P, Roccia F, Zavattero E, Dediol E, Uglesic V, Kovacic Z, et al. European Maxillofacial Trauma (EURMAT) project: a multicentre and prospective study. J Craniomaxillofac Surg 2015; 43: 62-70. https://doi.org/10.1016/j.jcms.2014.10.011
  10. Vinayahalingam S, van Nistelrooij N, van Ginneken B, Bressem K, Troltzsch D, Heiland M, et al. Detection of mandibular fractures on panoramic radiographs using deep learning. Sci Rep 2022; 12: 19596.
  11. Son DM, Yoon YA, Kwon HJ, Lee SH. Combined deep learning techniques for mandibular fracture diagnosis assistance. Life (Basel) 2022; 12: 1711.
  12. Nishiyama M, Ishibashi K, Ariji Y, Fukuda M, Nishiyama W, Umemura M, et al. Performance of deep learning models constructed using panoramic radiographs from two hospitals to diagnose fractures of the mandibular condyle. Dentomaxillofac Radiol 2021; 50: 20200611.
  13. Shahnavazi M, Mohamadrahimi H. The application of artificial neural networks in the detection of mandibular fractures using panoramic radiography. Dent Res J(Isfahan) 2023; 20: 27.
  14. Moher D, Liberati A, Tetzlaff J, Altman DG, PRISMA Group. Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. Ann Intern Med 2009; 151: 264-9. https://doi.org/10.7326/0003-4819-151-4-200908180-00135
  15. Whiting PF, Rutjes AW, Westwood ME, Mallett S, Deeks JJ, Reitsma JB, et al. QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Ann Intern Med 2011; 155: 529-36. https://doi.org/10.7326/0003-4819-155-8-201110180-00009
  16. Son DM, Yoon YA, Kwon HJ, An CH, Lee SH. Automatic detection of mandibular fractures in panoramic radiographs using deep learning. Diagnostics(Basel) 2021; 11: 933.
  17. Simundic AM. Measures of diagnostic accuracy: basic definitions. EJIFCC 2009; 19: 203-11.
  18. Khanagar SB, Alfouzan K, Awawdeh M, Alkadi L, Albalawi F, Alfadley A. Application and performance of artificial intelligence technology in detection, diagnosis and prediction of dental caries(DC) - a systematic review. Diagnostics(Basel) 2022; 12: 1083.
  19. Londono J, Ghasemi S, Hussain Shah A, Fahimipour A, Ghadimi N, Hashemi S, et al. Evaluation of deep learning and convolutional neural network algorithms accuracy for detecting and predicting anatomical landmarks on 2D lateral cephalometric images: a systematic review and meta-analysis. Saudi Dent J 2023; 35: 487-97.
  20. Dashti M, Londono J, Ghasemi S, Tabatabaei S, Hashemi S, Baghaei K, et al. Evaluation of accuracy of deep learning and conventional neural network algorithms in detection of dental implant type using intraoral radiographic images: a systematic review and meta-analysis. J Prosthet Dent(in press).
  21. Chen L, Li S, Bai Q, Yang J, Jiang S, Miao Y. Review of image classification algorithms based on convolutional neural networks. Remote Sens 2021; 13: 4712.