Skip to main content
SpringerLink
Log in

A unifying framework for automatic and semi-automatic segmentation of vertebrae from radiographs using sample-driven active shape models

  • Special Issue Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Segmentation of vertebral contours is an essential task in the design of imaging biomarkers for osteoporosis based on vertebra shape or texture. In this paper, we propose a novel automatic segmentation technique which can optionally be constrained by the user. The proposed technique solves the segmentation problem in a hierarchical manner. In the first phase, a coarse estimate of the overall spine alignment and the vertebra locations is computed using a sampling scheme. These samples are used to initialize a second phase of active shape model search, under a nonlinear model of vertebra appearance. The search is constrained by a conditional shape model, based on the variability of the coarse spine location estimates. In supplement, we describe an approach for manual initialization of the segmentation procedure as a simple set of constraints on the fully automatic technique. The technique is evaluated on a data base of 157 manually annotated lumbar radiographs, resulting in a final mean point-to-contour error of \(0.81~\pm ~0.98\) mm for automatic segmentation. The results outperform the previous work in automatic vertebra segmentation in terms of both segmentation accuracy and failure rate, offering a both automatic and semi-automatic approach in one unifying framework.

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.

Institutional subscriptions

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

Similar content being viewed by others

References

  1. Bagger, Y.Z., Tankó, L.B., Alexandersen, P., Hansen, H.B., Qin, G., Christiansen, C.: The long-term predictive value of bone mineral density measurements for fracture risk is independent of the site of measurement and the age at diagnosis: results from the Prospective Epidemiological Risk Factors study. Osteoporos. Int. 17(3), 471–477 (2006)

    Article  Google Scholar 

  2. Bauer, J.S., Müller, D., Ambekar, A., Dobritz, M., Matsuura, M., Eckstein, F., Rummeny, E.J., Link, T.M.: Detection of osteoporotic vertebral fractures using multidetector CT. Osteoporos. Int. 17(4), 608–615 (2006)

    Article  Google Scholar 

  3. Behiels, G., Vandermeulen, D., Maes, F., Suetens, P., Dewaele, P.: Active shape model-based segmentation of digital x-ray images.In: Medical Image Computing and Computer-Assisted Intervention (MICCAI) (1999)

  4. Benameur, S., Mignotte, M., Parent, S., Labelle, H., Skalli, W., de Guise, J.: 3D/2D registration and segmentation of scoliotic vertebrae using statistical models. Comput. Med. Imaging. Graph. 27(5), 321–337 (2003)

    Google Scholar 

  5. Benameur, S., Mignotte, M., Labelle, H., de Guise, J.A.: A hierarchical statistical modeling approach for the unsupervised 3-D biplanar reconstruction of the scoliotic spine. IEEE Trans. Biomed. Eng. 52(12), 2041–2057 (2005)

    Article  Google Scholar 

  6. Black, D.M., Cummings, S.R., Stone, K., Hudes, E., Palermo, L., Steiger, P.: A new approach to defining normal vertebral dimensions. J. Bone Miner. Res. 6(8), 883–892 (1991)

    Article  Google Scholar 

  7. Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)

    Article  MATH  Google Scholar 

  8. Brett, A.D., Taylor, C.J.: A method of automated landmark generation for automated 3D PDM construction. Image Vis. Comput. 18(9), 739–748 (2000)

    Article  Google Scholar 

  9. de Bruijne, M., Lund, M.T., Tankó, L.B., Pettersen, P.C., Nielsen, M.: Quantitative vertebral morphometry using neighbor-conditional shape models. Med. Image Anal. 11(5), 503–512 (2007)

    Article  Google Scholar 

  10. de Bruijne, M., Nielsen, M.: Image segmentation by shape particle filtering. In: International Conference on Pattern Recognition (ICPR) (2004)

  11. Carballido-Gamio, J., Belongie, S.J., Majumdar, S.: Normalized cuts in 3-D for spinal MRI segmentation. IEEE Trans. Med. Imaging 23(1), 36–44 (2004)

    Article  Google Scholar 

  12. Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. 23(6), 681–685 (2001)

    Article  Google Scholar 

  13. 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)

    Article  Google Scholar 

  14. Davies, R., Twining, C., Cootes, T., Waterton, J., Taylor, C.: 3D statistical shape models using direct optimisation of description length. In: European Conference on Computer Vision (ECCV) (2002)

  15. Eastell, R., Cedel, S.L., Wahner, H.W., Riggs, B.L.: Classification of vertebral fractures. J. Bone Miner. Res. 6(3), 207–215 (1991)

    Article  Google Scholar 

  16. Florack, L., Ter Haar Romeny, B., Viergever, M., Koenderink, J.: The Gaussian scale-space paradigm and the multiscale local jet. Int. J. Comput. Vis. 18(1), 61–75 (1996)

    Article  Google Scholar 

  17. Fukunaga, K., Hostetler, L.: The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Inf. Theory 21(1), 32–40 (1975)

    Article  MathSciNet  MATH  Google Scholar 

  18. Genant, H.K., Wu, C.Y., van Kuijk, C., Nevitt, M.C.: Vertebral fracture assessment using a semiquantitative technique. J. Bone Miner. Res. 8(9), 1137–1148 (1993)

    Article  Google Scholar 

  19. Gower, J.C.: Generalized procrustes analysis. Psychometrika 40(1), 33–51 (1975)

    Article  MathSciNet  MATH  Google Scholar 

  20. Hoerl, A.E., Kennard, R.W.: Ridge regression: biased estimation for nonorthogonal problems. Technometrics 42(1), 80–86 (2000)

    Article  MathSciNet  Google Scholar 

  21. Howe, B., Gururajan, A., Sari-Sarraf, H., Long, L.R.: Hierarchical segmentation of cervical and lumbar vertebrae using a customized generalized hough transform and extensions to active appearance models. In: 6th IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) (2004)

  22. Iglesias, J.E., de Bruijne, M.: Semiautomatic segmentation of vertebrae in lateral x-rays using a conditional shape model. Acad. Radiol. 14(10), 1156–1165 (2007)

    Article  Google Scholar 

  23. Isard, M., Blake, A.: Condensation–conditional density propagation for visual tracking. Int. J. Comput. Vis. 29(1), 5–28 (1998)

    Article  Google Scholar 

  24. Ismail, A.A., Cooper, C., Felsenberg, D., Varlow, J., Kanis, J.A., Silman, A.J., ONeill, T.W.: Number and type of vertebral deformities: epidemiological characteristics and relation to back pain and height loss. Osteoporos. Int. 9(3), 206–213 (1999)

    Article  Google Scholar 

  25. Klinder, T., Ostermann, J., Ehm, M., Franz, A., Kneser, R., Lorenz, C.: Automated model-based vertebra detection, identification, and segmentation in CT images. Med. Image Anal. 13(3), 471–482 (2009)

    Article  Google Scholar 

  26. Mastmeyer, A., Engelke, K., Fuchs, C., Kalender, W.A.: A hierarchical 3D segmentation method and the definition of vertebral body coordinate systems for QCT of the lumbar spine. Med. Image Anal. 10(4), 560–577 (2006)

    Google Scholar 

  27. McCloskey, E.V., Spector, T.D., Eyres, K.S., Fern, E.D., O’rourke, N., Vasikaran, S., Kanis, J.A.: The assessment of vertebral deformity: a method for use in population studies and clinical trials. Osteoporos. Int. 3(3), 138–147 (1993)

    Article  Google Scholar 

  28. Melton III, L.J., Atkinson, E.J., Cooper, C., OFallon, W.M., Riggs, B.L.: Vertebral fractures predict subsequent fractures. Osteoporos. Int. 10(3), 214–221 (1999)

  29. Mitton, D., Landry, C., Veron, S., Skalli, W., Lavaste, F., de Guise, J.A.: 3D reconstruction method from biplanar radiography using non-stereocorresponding points and elastic deformable meshes. Med. Biol. Eng. Comput. 38(2), 133–139 (2000)

    Article  Google Scholar 

  30. del Moral, P., Doucet, A., Jasra, A.: Sequential monte carlo samplers. J. R. Stat. Soc. 68(3), 411–436 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  31. Neal, R.M.: Annealed importance sampling. Stat. Comput. 11(2), 125–139 (2001)

    Article  MathSciNet  Google Scholar 

  32. Peng, Z., Zhong, J., Wee, W., Lee, J.: Automated vertebra detection and segmentation from the whole spine MR images. In: Conference of the Engineering in Medicine and Biology Society (2005)

  33. Petersen, K., Nielsen, M., Brandt, S.: A static SMC Sampler on shapes for the automated segmentation of aortic Calcifications. In: European Conference on Computer Vision (ECCV) (2010)

  34. Petersen, K., Nielsen, M., Brandt, S.: Conditional point distribution models. In: Workshop on Medical Computer Vision 2010 (2010). doi:10.1007/978-3-642-18421-5_1

  35. Roberts, M.G., Oh, T., Pacheco, E.M.B., Mohankumar, R., Cootes, T.F., Adams, J.E.: Semi-automatic determination of detailed vertebral shape from lumbar radiographs using active appearance models. Osteoporos. Int. (2011). doi:10.1007/s00198-011-1604-3

  36. Roberts, M., Cootes, T.F., Adams, J.E.: Vertebral morphometry: semiautomatic determination of detailed shape from dual-energy x-ray absorptiometry images using active appearance models. Invest. Radiol. 41(12), 849–859 (2006)

    Article  Google Scholar 

  37. Roberts, M., Cootes, T., Pacheco, E., Adams, J.: Quantitative vertebral fracture detection on DXA images using shape and appearance models. Acad. Radiol. 14(10), 1166–1178 (2007)

    Article  Google Scholar 

  38. Roberts, M., Cootes, T., Pacheco, E., Oh, T., Adams, J.: Segmentation of lumbar vertebrae using part-based graphs and active appearance models. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI) (2009)

  39. Rodan, G.A., Martin, T.J.: Therapeutic approaches to bone diseases. Science 289(5484), 1508–1514 (2000)

    Article  Google Scholar 

  40. Smyth, P.P., Taylor, C.J., Adams, J.E.: Vertebral shape: automatic measurement with active shape models. Radiology 211(2), 575–581 (1999)

    Article  Google Scholar 

  41. Zamora, G., Sari-sarraf, L.R., Long, L.R.: Hierarchical segmentation of vertebrae from x-ray images. In: SPIE Medical Imaging (2003)

  42. Zheng, Y., Nixon, M.S., Allen, R.: Automated segmentation of lumbar vertebrae in digital videofluoroscopic images. IEEE Trans. Med. Imaging 23(1), 45–52 (2004)

    Article  Google Scholar 

Download references

Acknowledgments

The authors would like to thank the Center for Clinical and Basic Research for providing scans and radiographic readings. We gratefully acknowledge the funding from the Danish Research Foundation (Den Danske Forskningsfond) supporting this work.

Author information

Authors and Affiliations

  1. eScience Center, University of Copenhagen, Universitetsparken 5, 2100 , Copenhagen Ø, Denmark

    Peter Mysling, Kersten Petersen, Mads Nielsen & Martin Lillholm

  2. Biomediq A/S, Fruebjergvej 3, 2100 , Copenhagen Ø, Denmark

    Mads Nielsen & Martin Lillholm

Authors
  1. Peter Mysling
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kersten Petersen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mads Nielsen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Martin Lillholm
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Peter Mysling.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mysling, P., Petersen, K., Nielsen, M. et al. A unifying framework for automatic and semi-automatic segmentation of vertebrae from radiographs using sample-driven active shape models. Machine Vision and Applications 24, 1421–1434 (2013). https://doi.org/10.1007/s00138-012-0460-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-012-0460-2

Keywords

Search

Navigation