Automated Grading of Modic Changes Using CNNs – Improving the Performance with Mixup

  • Dimitrios DamopoulosEmail author
  • Daniel Haschtmann
  • Tamás F. Fekete
  • Guoyan Zheng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11397)


We propose a method for automated grading of the vertebral endplate regions according to the Modic changes scale based on the VGG16 network architecture. We evaluate four variations of the method in a standard 9-fold cross-validation study setup on a heterogeneous dataset of 92 cases. Due to the very weak representation of the Modic Type III in the dataset, we focus on the grading of Modic Type I and Modic Type II. Despite the relatively small size of our dataset, the pipeline demonstrated a performanc1e that is similar to or better than those achieved by the state-of-the-art methods. In particular, the most performant variant achieved an accuracy of 88.0% with an average-per-class accuracy of 77.3%. When the method is used as a binary detector for the presence or not of Modic changes, the achieved average-per-class accuracy is 92.3%. Our evaluation also suggests that the so-called mixup strategy is particularly useful for this type of classification task.


Modic changes Automated grading Mixup VGG 


  1. 1.
    De Roos, A., et al.: MR imaging of marrow changes adjacent to end plates in degenerative lumbar disk disease. Am. J. Roentgenol. 149(3), 531–534 (1987)CrossRefGoogle Scholar
  2. 2.
    Modic, M.T., et al.: Degenerative disk disease: assessment of changes in vertebral body marrow with MR imaging. Radiology 166(1), 193–199 (1988)CrossRefGoogle Scholar
  3. 3.
    Modic, M.T., et al.: Imaging of degenerative disk disease. Radiology 168(1), 177–186 (1988)CrossRefGoogle Scholar
  4. 4.
    Wang, Y., Videman, T., Battié, M.C.: Modic changes: prevalence, distribution patterns, and association with age in white men. Spine J. 12(5), 411–416 (2012)CrossRefGoogle Scholar
  5. 5.
    Zhang, Y.-H., et al.: Modic changes: a systematic review of the literature. Eur. Spine J. 17(10), 1289–1299 (2008)CrossRefGoogle Scholar
  6. 6.
    Albert, H.B., et al.: Modic changes, possible causes and relation to low back pain. Med. Hypotheses 70(2), 361–368 (2008)CrossRefGoogle Scholar
  7. 7.
    Järvinen, J., et al.: Association between changes in lumbar Modic changes and low back symptoms over a two-year period. BMC Musculoskelet. Disord. 16(1), 98 (2015)CrossRefGoogle Scholar
  8. 8.
    Fayad, F., et al.: Reliability of a modified Modic classification of bone marrow changes in lumbar spine MRI. Jt. Bone Spine 76(3), 286–289 (2009)CrossRefGoogle Scholar
  9. 9.
    Crockett, M.T., et al.: Modic type 1 vertebral endplate changes: injury, inflammation, or infection? Am. J. Roentgenol. 209(1), 167–170 (2017)CrossRefGoogle Scholar
  10. 10.
    Wang, Y., et al.: Quantitative measures of Modic changes in lumbar spine magnetic resonance imaging: intra-and inter-rater reliability. Spine 36(15), 1236–1243 (2011)CrossRefGoogle Scholar
  11. 11.
    Vivas, E.L.A., et al.: Application of a semiautomatic classifier for Modic and disk hernia changes in magnetic resonance. Coluna/Columna 14(1), 18–22 (2015)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Jamaludin, A., Kadir, T., Zisserman, A.: Automatic Modic changes classification in spinal MRI. In: Vrtovec, T., Yao, J., Glocker, B., Klinder, T., Frangi, A., Zheng, G., Li, S. (eds.) CSI 2015. LNCS, vol. 9402, pp. 14–26. Springer, Cham (2016). Scholar
  13. 13.
    Jensen, T.S., Sorensen, J.S., Kjaer, P.: Intra-and interobserver reproducibility of vertebral endplate signal (Modic) changes in the lumbar spine: the Nordic Modic consensus group classification. Acta Radiol. 48(7), 748–754 (2007)CrossRefGoogle Scholar
  14. 14.
    Jamaludin, A., Kadir, T., Zisserman, A.: SpineNet: automatically pinpointing classification evidence in spinal MRIs. In: Ourselin, S., Joskowicz, L., Sabuncu, Mert R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 166–175. Springer, Cham (2016). Scholar
  15. 15.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  16. 16.
    Zhang, H., et al.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)
  17. 17.
    Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. IEEE (2009)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Dimitrios Damopoulos
    • 1
    Email author
  • Daniel Haschtmann
    • 2
  • Tamás F. Fekete
    • 2
  • Guoyan Zheng
    • 1
  1. 1.Institute for Surgical Technology and BiomechanicsUniversity of BernBernSwitzerland
  2. 2.Schulthess ClinicZürichSwitzerland

Personalised recommendations