Segmentation of Lumbar Intervertebral Discs from High-Resolution 3D MR Images Using Multi-level Statistical Shape Models

  • Aleš NeubertEmail author
  • Jurgen Fripp
  • Craig Engstrom
  • Stuart Crozier
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 17)


Three-dimensional (3D) high resolution magnetic resonance (MR) scans of the lumbar spine provide relevant diagnostic information for lumbar intervertebral disc related disorders. Automated segmentation algorithms, such as active shape modelling, have the potential to facilitate the processing of the complex 3D MR data. An active shape model employs prior anatomical information about the segmented shapes that is typically described by standard principle component analysis. In this study, performance of this traditional statistical shape model was compared to that of a multi-level statistical shape model, incorporating the hierarchical structure of the spine. The mean Dice score coefficient, mean absolute square distance and Hausdorff distance obtained with the multi-level model were significantly better than those obtained with the traditional shape model. These initial results warrant further investigation of potential benefits that the multi-level statistical shape models can have in spine image analysis.


Lumbar Spine Shape Model Hausdorff Distance Lumbar Intervertebral Disc Active Shape Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The authors would like to thank Dr. Duncan Walker for the radiological assessments. This research was supported under Australian Research Council’s linkage project funding scheme LP100200422.


  1. 1.
    Chevrefils, C., Chériet, F., Aubin, C.E., Grimard, G.: Texture analysis for automatic segmentation of intervertebral disks of scoliotic spines from MR images. IEEE Trans. Inf. Technol. Biomed. 13(4), 608–620 (2009)CrossRefGoogle Scholar
  2. 2.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models-their training and application. Comput. Vis. Image Underst. 61(1), 38–59 (1995)CrossRefGoogle Scholar
  3. 3.
    Cousins, J.P., Haughton, V.M.: Magnetic resonance imaging of the spine. J. Am. Acad. Orthop. Surg. 17(1), 22–30 (2009)Google Scholar
  4. 4.
    Davies, R.H., Twining, C.J., Taylor, C.: Groupwise surface correspondence by optimization: representation and regularization. Med. Image Anal. 12(6), 787–796 (2008)CrossRefGoogle Scholar
  5. 5.
    Emch, T.M., Modic, M.T.: Imaging of lumbar degenerative disk disease: history and current state. Skelet. Radiol. 40(9), 1175–1189 (2011)CrossRefGoogle Scholar
  6. 6.
    Gower, J.C.: Generalized procrustes analysis. Psychometrika 40(1), 33–51 (1975)CrossRefzbMATHMathSciNetGoogle Scholar
  7. 7.
    Lecron, F., Boisvert, J., Benjelloun, M., Labelle, H., Mahmoudi, S.: Multilevel statistical shape models : a new framework for modeling hierarchical structures. In: International Symposium on Biomedical Imaging: From Nano to Macro, pp. 1284–1287 (2012)Google Scholar
  8. 8.
    Lecron, F., Boisvert, J., Mahmoudi, S., Labelle, H., Benjelloun, M.: Fast 3D Spine Reconstruction of Postoperative Patients Using a Multilevel Statistical Model. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 15, 446–453 (2012)Google Scholar
  9. 9.
    Lichy, M.P., Wietek, B.M., Mugler, J.P., Horger, W., Menzel, M.I., Anastasiadis, A., Siegmann, K., Niemeyer, T., Königsrainer, A., Kiefer, B., Schick, F., Claussen, C.D., Schlemmer, H.P.: Magnetic resonance imaging of the body trunk using a single-slab, 3-dimensional, T2-weighted turbo-spin-echo sequence with high sampling efficiency (SPACE) for high spatial resolution imaging: initial clinical experiences. Invest. Radiol. 40(12), 754–760 (2005)CrossRefGoogle Scholar
  10. 10.
    Meindl, T., Wirth, S., Weckbach, S., Dietrich, O., Reiser, M., Schoenberg, S.O.: Magnetic resonance imaging of the cervical spine: comparison of 2D T2-weighted turbo spin echo, 2D T2*weighted gradient-recalled echo and 3D T2-weighted variable flip-angle turbo spin echo sequences. Eur. Radiol. 19(3), 713–721 (2009)CrossRefGoogle Scholar
  11. 11.
    Michopoulou, S.K., Costaridou, L., Panagiotopoulos, E., Speller, R., Panayiotakis, G., Todd-Pokropek, A.: Atlas-based segmentation of degenerated lumbar intervertebral discs from MR images of the spine. IEEE Trans. Biomed. Eng. 56(9), 2225–2231 (2009)Google Scholar
  12. 12.
    Neubert, A., Fripp, J., Engstrom, C., Schwarz, R., Lauer, L., Salvado, O., Crozier, S.: Automated detection, 3D segmentation and analysis of high resolution spine MR images using statistical shape models. Phys. Med. Biol. 57(24), 8357–8376 (2012)CrossRefGoogle Scholar
  13. 13.
    Seifert, S., Wachter, I., Schmelzle, G., Dillmann, R.: A knowledge-based approach to soft tissue reconstruction of the cervical spine. IEEE Trans. Med. Imaging 28(4), 494–507 (2009)CrossRefGoogle Scholar
  14. 14.
    Shi, R., Sun, D., Qiu, Z., Weiss, K.L.: An efficient method for segmentation of MRI spine images. In: IEEE: International Conference on Complex Medical, Engineering, pp. 713–717 (2007)Google Scholar
  15. 15.
    Timmerman, M.E.: Multilevel component analysis. Br. J. Math. Stat. Pychol. 59(Pt 2), 301–320 (2006)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Tustison, N.J., Gee, J.C.: N4ITK: nicks N3 ITK implementation for MRI bias field correction. Insight J. 2009, 1–8 (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Aleš Neubert
    • 1
    • 2
    Email author
  • Jurgen Fripp
    • 1
  • Craig Engstrom
    • 3
  • Stuart Crozier
    • 2
  1. 1.The Australian E-Health Research CentreCSIRO Computational InformaticsBrisbaneAustralia
  2. 2.School of Information Technology and Electrical EngineeringThe University of QueenslandBrisbaneAustralia
  3. 3.School of Human Movement StudiesThe University of QueenslandBrisbaneAustralia

Personalised recommendations