Skip to main content
SpringerLink
Log in

Evaluation of the usefulness of deep neural networks in classifying X-ray images according to radiation exposure level for automatic exposure control of digital radiography

  • Original Paper
  • Published:
Journal of the Korean Physical Society Aims and scope Submit manuscript

Abstract

In medicine, X-ray imaging has to have stable image quality while minimizing radiation exposure. In recent digital radiography (DR), the radiation exposure and image quality are controlled by employing automatic exposure control (AEC) technology. In such an environment, the technology needs the capability of accurately classifying the level of radiation exposure despite statistical X-ray fluctuations. Therefore, the purpose of this study was to implement a radiation exposure classifier that could objectively determine the level using the deep neural network (DNN) method. Datasets containing 2000 images were used for training and validation of the DNN. This was done by changing the sensitivity of the AEC of the DR system to S200, S400, S800, and S1000. The changes in sensitivity generated four groups of 500 X-ray images each: overexposure, normal exposure (2), normal exposure (1), and underexposure. The results showed a classification accuracy of 93.83% and a loss 38.9%. In conclusion, through deep learning with X-ray images, an objective radiation exposure classifier was implemented and is expected to be used for the AEC of DR systems and to improve diagnostic accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. N.W. Marshall, C.V. Ongeval, H. Bosmans, Phys. Med. Eur. J. Med. Phys. 32, 312 (2016)

    Google Scholar 

  2. C. Chimhundu, S. Sivarasu, S. Steiner, J. Smit, T.S. Douglas, Med. Eng. Phys. 38, 187 (2016)

    Article  Google Scholar 

  3. H. Matsumoto, K. Komiya, M. Yamasue, H. Shuto, A. Goto, T. Kan, K. Honjo, S. Uchida, S. Takikawa, T. Yoshimatsu, K. Hiramatsu, T. Johkoh, J.I. Kadota, Infect. Dis. 52, 520 (2020)

    Article  Google Scholar 

  4. R.K. Grewal, N. Young, L. Colins, N. Karunnaratne, N. Sabharwal, Aust. Phys. Eng. Sci. Med. 35, 71 (2012)

    Article  Google Scholar 

  5. M.W.M. Jones, P.M. Kopittke, L. Casey, J. Reinhardt, F.P.C. Blamey, A.V.D. Ent, Ann. Bot. 125, 599 (2020)

    Article  Google Scholar 

  6. G. Li, T.C. Greene, T.K. Nishino, C.E. Willis, J. Appl. Clin. Med. Phys. 17, 391 (2016)

    Article  Google Scholar 

  7. J.H. Hwang, K.B. Lee, J.A. Choi, T.S. Lee, J. Med. Sys. 44, 183 (2020)

    Article  Google Scholar 

  8. S.J. Shepard, J. Wang, M. Flynn, E. Gingold, L. Goldman, K. Krugh, D.L. Leong, E. Mah, K. Ogden, D. Peck, E. Samei, C.E. Willis, Med. Phys. 36, 2898 (2009)

    Article  Google Scholar 

  9. J. K. Dave, A. K. Jones, R. Fisher, K. Hulme, L. Rill, D. Zamora, A. Woodward, S. Brady, R. D. MacDougall, L. Goldman, S. Lang, D. Peck, B. Apgar, S. J. Shepard, R. Uzenoff and C. Willis, Med. Phys. 45, e1146 (2018).

  10. S. Dinggang, W. Guorong, H.I. Suk, Annu. Rev. Biomed. Eng. 19, 221 (2017)

    Article  Google Scholar 

  11. Y. LeCun, Y. Bengio, G. Hinton, Nature 521, 436 (2015)

    Article  ADS  Google Scholar 

  12. C. M. Hyun, H. P. Kim, S. M. Lee, S. C. Lee and J. K. Seo, Phys. Med. Biol. 63, 135007 (2018).

  13. S. Zhou, H. Zou, C. Liu, M. Zang, Z. Zhang, J. Yue, Optik 127, 9008 (2016)

    Article  ADS  Google Scholar 

  14. H. Goh, N. Thome, M. Cord, J.H. Lim, IEEE Trans. Neural. Netw. Learn. Syst. 25, 2212 (2014)

    Article  Google Scholar 

  15. N. Kriegeskorte, T. Golan, Curr. Biol. 29, R231 (2019)

    Article  Google Scholar 

  16. ICRP, Diagnostic Reference Levels in Medical Imaging, ICRP Publication 135, Ann. ICRP 46, 1 (2017).

  17. ICRP, Managing patient dose in digital radiology, ICRP Publication 93, Ann. ICRP 34, 1 (2004).

  18. ICRP, Radiological protection in medicine, ICRP Publication 105, Ann. ICRP 37, 6 (2007).

  19. IEC, Medical diagnostic X-ray equipment—radiation conditions for use in the determination of characteristics, IEC 61267 (2005).

  20. IEC, Medical electrical equipment—characteristics of digital X-ray imaging devices–part 1, determinations detective quantum efficiency, IEC 62220–1 (2003).

  21. IEC, Medical electrical equipment—exposure index of digital X-ray imaging systems–part 1: definitions and requirements for general radiography, IEC 62494–1 (2008).

  22. ISO, Photography - Sensitometry of Screen/film Systems for Medical Radiography — Part 1: Determination of Sensitometric Curve Shape, Speed and Average Gradient, ISO 9236–1 (2004).

  23. S.B. Yoo, M. Han, Sensors 19, 1 (2019)

    Article  Google Scholar 

  24. K. Zhang, W. Zuo, Y. Chen, D. Meng, L. Zhang, IEEE Trans. Image. Process. 26, 3142 (2017)

    Article  ADS  MathSciNet  Google Scholar 

  25. J.P.F. D’Haeyer, D. Haeyer, Signal Process. 18, 169 (1989)

    Article  Google Scholar 

  26. S.B. Yoo, M. Han, Electron. Lett. 55, 529 (2019)

    Article  ADS  Google Scholar 

  27. H. Pratt, F. Coenen, D.M. Broadbent, S.P. Harding, Y. Zheng, Procedia. Comput. Sci. 90, 200 (2016)

    Article  Google Scholar 

  28. N.V. Hieu, N.L.H. Hien, IJEET 68, 25 (2020)

    Google Scholar 

  29. M.A. Uddin, Y.K. Lee, Sensors 19, 1 (2019)

    Article  Google Scholar 

  30. Z. Wang, J. Yang, ArXiv 1703, 1 (2018)

    Google Scholar 

  31. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, J. Mach. Learn. Res. 15, 1929 (2015)

    Google Scholar 

  32. S.W. Kim, J.S. Kim, J. Korean Phys. Soc. 77, 1274 (2020)

    Article  ADS  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Neurosurgery, Kyung Hee University Hospital Gamma Knife Center, Seoul, 02447, Korea

    Jun-Ho Hwang & Chang-Kyu Park

  2. Department of Neurosurgery, Kyung Hee University College of Medicine, Seoul, 02447, Korea

    Chang-Kyu Park

  3. Department of Radiology, Kyung Hee University Hospital, Seoul, 02447, Korea

    Kyung-Bae Lee

  4. Department of Biomedical Engineering Graduate School, Chungbuk National University, Cheongju-si, 28644, Korea

    Jun-Ho Hwang & Tae-Soo Lee

Authors
  1. Jun-Ho Hwang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chang-Kyu Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kyung-Bae Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tae-Soo Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tae-Soo Lee.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hwang, JH., Park, CK., Lee, KB. et al. Evaluation of the usefulness of deep neural networks in classifying X-ray images according to radiation exposure level for automatic exposure control of digital radiography. J. Korean Phys. Soc. 79, 208–215 (2021). https://doi.org/10.1007/s40042-021-00189-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40042-021-00189-w

Keyword

Search

Navigation