X-ray image segmentation for vertebral mobility analysis

Original article

Abstract

Objective

The goal of this work is to extract the parameters determining vertebral motion and its variation during flexion–extension movements using a computer vision tool for estimating and analyzing vertebral mobility.

Materials and Methods

To compute vertebral body motion parameters we propose a comparative study between two segmentation methods proposed and applied to lateral X-ray images of the cervical spine. The two vertebra contour detection methods include (1) a discrete dynamic contour model (DDCM) and (2) a template matching process associated with a polar signature system. These two methods not only enable vertebra segmentation but also extract parameters that can be used to evaluate vertebral mobility. Lateral cervical spine views including 100 views in flexion, extension and neutral orientations were available for evaluation. Vertebral body motion was evaluated by human observers and using automatic methods.

Results

The results provided by the automated approaches were consistent with manual measures obtained by 15 human observers.

Conclusion

The automated techniques provide acceptable results for the assessment of vertebral body mobility in flexion and extension on lateral views of the cervical spine.

Keywords

Vertebral mobility analysis X-ray images segmentation Contour detection Template matching Discrete dynamic contour model (DDCM) 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

References

  1. 1.
    Benjelloun M, Mahmoudi S (2007) Spine localization and vertebral mobility analysis using faces contours detection. 29th IEEE annual international conference on engineering in Medicine and Biology society, EMBS07, 23–26 August, 2007, pp 6557–6560, Cité Internationale, LyonGoogle Scholar
  2. 2.
    Benjelloun M, Téllez H, Mahmoudi S (2006) Template matching method for vertebra region selection. 2nd IEEE international conference on information and communication technologies: from theory to applications. (ICTTA’06), Damascus, April 2006, pp 393–398Google Scholar
  3. 3.
    Blane MM, Lei Z, Civi H, Cooper DB (2000) The 3L algorithm for fitting implicit polynomial curves and surfaces to data. IEE Transactions on Pattern Analysis and Machine Intelligence 22(3): 298–313CrossRefGoogle Scholar
  4. 4.
    Brejl M, Sonka M (2000) Object localization and border detection criteria design in edge-based image segmentation: automated learning from examples. IEEE Trans Med Imaging 19(10): 973–985PubMedCrossRefGoogle Scholar
  5. 5.
    Canny J (1986) A computational approach to edge detection, 1986. IEEE Trans Pattern Anal Machine Intell 8: 6Google Scholar
  6. 6.
    Cootes T, Edwards G, Taylor C (2001) Active appearance models. IEEE TPAMI 23(6): 681–684Google Scholar
  7. 7.
    Cootes T, Taylor C (1999) Statistical models of appearance for computer vision. Internal reportGoogle Scholar
  8. 8.
    Cootes TF, Hill A, Taylor CJ, Haslam J (1994) The use of active shape models for locating structures in medical images. Image Vision Comput 12: 355–366CrossRefGoogle Scholar
  9. 9.
    de Bruijne M, van Ginneken B, Viergever M, Niessen W (2003) Adapting active shape models for 3d segmentation of tubular structures in medical images. In IPMI, vol 2732 of LNCS, pp 136–147. Springer, Heidelberg, 2003Google Scholar
  10. 10.
    Deriche R, Faugeras O (1998) 2d curve matching using high curvature points: application to stereo vision. Proc. International Conf on Pattern Recognition, vol 1, pp 240–242Google Scholar
  11. 11.
    Pham DL, Xu C, Prince JL (2000) Current methods in medical image segmentation. Annu Rev Biomed Eng 2: 315–337PubMedCrossRefGoogle Scholar
  12. 12.
    Howe B, Gururajan A, Sari-Sarraf H, Long R (2004) Hierarchical segmentation of cervical and lumbar vertebrae using a customized generalized hough transform. Proc IEEE 6th SSIAI, pp 182–186, Lake TahoeGoogle Scholar
  13. 13.
    Kass M, Witkin A, Terzopoulos D (1987) Snakes: active contour models. Int J Computer Vision 1: 321–331CrossRefGoogle Scholar
  14. 14.
    Kauffman C, Guise JA (1997) Digital radiography segmentation of scoliotic vertebral body using deformable models. SPIE Med Imaging 3034: 243–251Google Scholar
  15. 15.
    Keren D (2004) Topologically faithful fitting of simple closed curves. IEEE Trans PAMI 26(1)Google Scholar
  16. 16.
    Keren D, Gotsman C (1999) Fitting curves and surfaces with constrained implicit polynomials. IEEE Trans PAMI 21(1)Google Scholar
  17. 17.
    Lie WN, Chen YC (1986) Shape representation and matching using polar signature. Proc Intl Comput Symp, pp 710–718Google Scholar
  18. 18.
    Lobregt S, Viergever MA (1995) A discrete dynamic contour model, 1995. IEEE Trans Med Imaging 14(1)Google Scholar
  19. 19.
    Long LR, Thoma GR (1999) Segmentation and feature extraction of cervical spine X-ray images, Proc SPIE medical imaging image processing, vol 3661, San Diego 20–26 February, pp 1037–1046Google Scholar
  20. 20.
    Long LR, Thoma GR (2000) Use of shape models to search digitized spine X-rays. Proc. IEEE computer-based medical systems, pp 255–260, HoustonGoogle Scholar
  21. 21.
    Long LR, Thoma GR (2001) Identification and classification of spine vertebrae by automated methods. Proc SPIE medical imaging 2001: image processing, vol 4322Google Scholar
  22. 22.
    Rico G, Benjelloun M, Libert G (2001) Detection, localization and representation of cervical vertebrae. Computer vision winter workshop, Bled, pp 114–124Google Scholar
  23. 23.
    Stanley RJ, Long LR, Antani S, Thoma GR, Downey E (2004) Image analysis techniques for the automated evaluation of subaxial subluxation in cervical spine X-ray images. Proceeding of the 17th IEEE symposium on computer-based medical systems CMBS04Google Scholar
  24. 24.
    Sethian JA (1996) Level set methods. Cambridge University Press, CambridgeGoogle Scholar
  25. 25.
    Smyth P, Taylor C, Adams J (1999) Vertebral shape: automatic measurement with active shape models. Radiology 211(2): 571–578PubMedGoogle Scholar
  26. 26.
    Tezmol A, Sari-Sarraf H, Mitra S, Long R, Gururajan A (2002) A customized hough transform for robust segmentation of cervical vertebrae from X-ray images. Proc. 5th IEEE southwest symposium on image analysis and interpretation, Santa FeGoogle Scholar
  27. 27.
    Verdonck B, Nijlunsing R, Gerritsenand FA, Cheung J, Wever DJ, Veldhuizen A, Devillers S, Makram-Ebeid S (1998) Computer assisted quantitative analysis of deformities of the human spine. Proceeding of international conference of computing and computer assisted interventions, LNCS, pp 822–831. Springer, HeidelbergGoogle Scholar
  28. 28.
    Vosselman G, Haralick R (1996) Performance analysis of line and circle fitting in digital images. Proceedings of the workshop on performance characteristics of vision algorithms, CambridgeGoogle Scholar
  29. 29.
    Zamora G, Sari-Sarrafa H, Long R (2003) Hierarchical segmentation of vertebrae from X-ray images. Med imaging: image process, vol 5032 of Proc of SPIE, pp 631–642. SPIE PressGoogle Scholar
  30. 30.
    Zheng Y, Nixon MS, Allen R (2004) Automate segmentation of lumbar vertebrae in digital videofluoroscopic images, 2004. IEEE Trans Medical Imaging 23(1): 45–52CrossRefGoogle Scholar

Copyright information

© CARS 2008

Authors and Affiliations

  1. 1.Computer Science Department, Faculty of Engineering of MonsMonsBelgium

Personalised recommendations