Advertisement

Automated Radiological Grading of Spinal MRI

  • Meelis LootusEmail author
  • Timor Kadir
  • Andrew Zisserman
Chapter
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 20)

Abstract

This paper describes a fully automatic system for obtaining the standard Pfirrmann degeneration grading of individual intervertebral spinal discs in T2 MRI scans. It involves detecting and labeling all the vertebrae in the scan and then learning a regression from the disc region to the grading. In developing the regression function we investigate a spectrum of support regions which involve differing degrees of segmentation of the scan: our intention is to ascertain to what extent segmentation is necessary or detrimental in obtaining robust and accurate measurements. The methods are assessed on a heterogeneous clinical dataset containing 1,710 Pfirrmann-graded discs, from 285 symptomatic back pain patients. We are able to predict the grade to \(\pm 1\) precision at 85.8 % accuracy. Our novel method proposes new image features that outperform previous features and utilizes techniques to improve robustness to MR imaging variations.

Keywords

Spine Radiological measurement MRI Grading Discs Regression 

References

  1. 1.
    Alomari, R.S., Corso, J.J., Chaudhary, V.: Desiccation diagnosis in lumbar discs from clinical MRI with a probabilistic model. In: ISBI (2009)Google Scholar
  2. 2.
    Battie, M.C., Viderman, T., Gibbons, L.E., Fisher, L.D., Manninen, H., Gill, K.: 1995 volvo award in clinical sciences—determinants of lumbar disc degeneration. Spine 20(24), 2601–2612 (1995)Google Scholar
  3. 3.
    Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: Proceedings ICCV (2001)Google Scholar
  4. 4.
    Chang, C.-C., Lin, C.-J., LIBSVM: A library for support vector machines. ACM TIST, 2:27:1–27:27 (2011)Google Scholar
  5. 5.
    Cheng, F., You, J., Rampersaud, Y.R.: Relationship between spinal magnetic resonance imaging findings and candidacy for spinal surgery. Can. Fam. Physician, 56, 323–330 (2010)Google Scholar
  6. 6.
    Gamio, J.C., Belongie, S.J., Majumdar, S.: Normalized cuts in 3D for spinal MRI segmentation. TMI 23, 36–44 (2004)Google Scholar
  7. 7.
    Hao, S., Jiang, J., Guo, Y., Li, H.: Active learning based intervertebral disk classification combining shape and texture similarities. Neurocomputing 101, 252–257 (2013)CrossRefGoogle Scholar
  8. 8.
    Huang, S.-H., Chu, Y.-H., Lai, S.-H., Novak, C.L.: Learning-based vertebra detection and iterative normalized-cut segmentation for spinal MRI. TMI 28(10), 1595–1605 (2009)Google Scholar
  9. 9.
    Lam, K., Anbar, A., O’Brien, A.: The correlation of the severity of lumbar disc degeneration with discogenic low back pain—a study utilizing a validated classification with awake provocative discography. J Bone Joint Surg. 92-B (2010)Google Scholar
  10. 10.
    Law, M.W.K., Tay, K., Leung, A., Garvin, G., Shuo, L.I.: Intervertebrald disc segmentation in MR images using anisotropic oriented flux, In: Proceedings of MIA (2012)Google Scholar
  11. 11.
    Lootus, M., Kadir, T., Zisserman, A.: Vertebrae detection and labelling in lumbar MR images. In: MICCAI CSI Workshop (2013)Google Scholar
  12. 12.
    Lurie, J.D., Moses, R.A., Tosteson, A.N.A., Tosteson, T.D., Carragee, E.J., Carrino, J.A., Kaiser, J.A., Herzog, R.J.: Magnetic resonance imaging predictors of surgical outcome in patients with lumbar intervertebral disc herniation. Spine 38, 1216–1225 (2013)CrossRefGoogle Scholar
  13. 13.
    Michopoulou, S., Costaridou, L., Vlychou, M., Speller, R., Todd-Pokropek, A.: Texture-based quantification of lumbar intervertebral disc degeneration from conventional T2-weighted MRI. Acta Radiol. 52, 91–98 (2011)CrossRefGoogle Scholar
  14. 14.
    Neubert, A., Fripp, J., Engstrom, C., Walker, D., Weber, M.-A., Schwarz, R., Crozier, S.: Three-dimensional morphological and signal intensity features for detection of intervertebral disc degeneration from magnetic resonance images. J. Am. Med. Inform. Assoc. 4, 1082–1090 (2013)Google Scholar
  15. 15.
    Pfirrmann, C.W.A., Metzdorf, A., Zanetti, M., Hodler, J., Boos, N.: Magnetic resonance classification of lumbar intervertebral disc degeneration. Spine 26, 1873–1878 (2001)Google Scholar
  16. 16.
    Shen, J., Parent, S., Kadoury, S.: Classification of spinal deformities using a parametric torsion estimator. In: MICCAI CSI Workshop (2013)Google Scholar
  17. 17.
    Smola, A.J., Schölkopf, B.: A tutorial on support vector regression. Stat. Comput. 14, 199–222 (2004)CrossRefMathSciNetGoogle Scholar
  18. 18.
    Štern, D., Likar, B., Pernus, F., Vrtovec, T.: Parametric modelling and segmentation of vertebral bodies in 3D CT and MR images. Phys. Med. Biol. 56, 7505 (2011)CrossRefGoogle Scholar
  19. 19.
    Unal, Y., Kocer, H.E., Akkurt. H.E.: A comparison of feature extraction techniques for diagnosis of lumbar intervertebral degenerative disc disease. INISTA (2011)Google Scholar
  20. 20.
    Xu, Y., Gao, X., Lin, S., Wong, D.W.K., Liu, J., Xu, D. Cheng, C.-Y. Cheung, C.Y., Wong, T.Y.: Automatic grading of nuclear cataracts from slit-lamp lens images using group sparsity regression. In: MICCAI (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Oxford UniversityOxfordUK
  2. 2.Mirada MedicalOxfordUK

Personalised recommendations