Osteoporosis International

, Volume 23, Issue 2, pp 655–664 | Cite as

Semi-automatic determination of detailed vertebral shape from lumbar radiographs using active appearance models

  • M. G. RobertsEmail author
  • T. Oh
  • E. M. B. Pacheco
  • R. Mohankumar
  • T. F. Cootes
  • J. E. Adams
Original Article



The vertebral endplates in lumbar radiographs were located by a semi-automatic annotation method using statistical shape models.


Vertebral fractures are common osteoporotic fractures, but current quantitative detection methods (morphometry) lack specificity. We have previously developed more specific quantitative classifiers of vertebral fracture using shape and appearance models. This method has only been applied to DXA vertebral fracture assessment (VFA) images and not to spinal radiographs. The classifiers require a detailed annotation of the outline of the vertebral endplate, so we investigated the application of similar semi-automated annotation methods to lumbar radiographs as the initial step in the generalisation of the statistical classifiers used in VFA images.


The vertebral body outlines in a training set of 670 lumbar radiographs were manually annotated by expert radiologists. This training set was used to build statistical models of vertebral shape and appearance using triplets of vertebrae. In order to segment vertebrae, the models were refitted using a sequence of active appearance models of vertebral triplets, using a miss-40-out train/test cross-validation experiment. The accuracy was evaluated against the manual annotation and analysed by fracture grade.


Good accuracy was obtained for normal vertebrae (0.82 mm) and fracture grades 1 and 2 (1.19 mm), but the localisation accuracy deteriorated for grade 3 fractures to 2.12 mm.


Vertebral body shape annotation can be substantially automated on lumbar radiographs. However, an occasional manual correction may be required, typically with either severe fractures, or when there is a high degree of projectional tilting or scoliosis. The located detailed shapes may enable the development of more powerful quantitative classifiers of osteoporotic vertebral fracture.


Active appearance model Annotation Computer-assisted diagnosis Osteoporosis Vertebral fracture 



The authors acknowledge the kind provision of digitised training images by the team at the University of Sheffield (Professor R. Eastell and Dr. L. Ferrar). We thank Professor Cyrus Cooper (Universities of Southampton and Oxford) and Professor David Reid (University of Aberdeen) for permission to use radiographs from earlier studies. The authors wish to thank Mr Stephen Capener (SC) who performed the manual annotation of the vertebrae in the first dataset. The work was funded through a grant from Arthritis Research UK, with earlier foundation work having been funded by grants from the Central Manchester University Hospitals NHS Foundation Trust (CMFT) Research Endowment Fund.

Conflicts of interest



  1. 1.
    Ensrud K, Thompson D, Cauley J, Nevitt M, Kado D, Hochberg M, An S, Black D (2000) Prevalent vertebral deformities predict mortality and hospitalization in older women with low bone mass. Fracture Intervention Trial Research Group. J Am Geriatr Soc 48:241–249PubMedGoogle Scholar
  2. 2.
    Melton LJ III, Atkinson EJ, Cooper C et al (1999) Vertebral fractures predict subsequent fractures. Osteoporos Int 10(3):214–221PubMedCrossRefGoogle Scholar
  3. 3.
    Lindsay R, Silverman SL, Cooper C, Hanley DA, Barton I, Broy SB, Licata A, Benhamou L, Geusens P, Flowers K, Stracke H, Seeman E (2001) Risk of new vertebral fracture in the year following a fracture. JAMA 285(3):320–323PubMedCrossRefGoogle Scholar
  4. 4.
    Ensrud KE, Nevitt MC, Palermo L et al (1999) What proportion of incident morphometric vertebral fractures are clinically diagnosed and vice versa? J Bone Miner Res 14(S1):S138Google Scholar
  5. 5.
    Gehlbach SH, Bigelow C, Heimisdottir M et al (2000) Recognition of vertebral fractures in a clinical setting. Osteoporos Int 11(7):577–582PubMedCrossRefGoogle Scholar
  6. 6.
    Delmas PD, van de Langerijt L, Watts NB et al (2005) Underdiagnosis of vertebral fractures is a worldwide problem: the IMPACT study. J Bone Miner Res 20(4):557–563PubMedCrossRefGoogle Scholar
  7. 7.
    Ferrar L, Jiang G, Adams J, Eastell R (2005) Identification of vertebral fractures: an update. Osteoporos Int 16(7):717–728PubMedCrossRefGoogle Scholar
  8. 8.
    Guermazi A, Mohr A, Grigorian M et al (2002) Identification of vertebral fractures in osteoporosis. Semin Musculoskelet Radiol 6(3):241–252PubMedCrossRefGoogle Scholar
  9. 9.
    Genant HK, Wu CY, van Kuijk C et al (1993) Vertebral fracture assessment using a semi-quantitative technique. J Bone Miner Res 8(9):1137–1148PubMedCrossRefGoogle Scholar
  10. 10.
    Black DM, Cummings SR, Stone K et al (1991) A new approach to defining normal vertebral dimensions. J Bone Miner Res 6(8):883–892PubMedCrossRefGoogle Scholar
  11. 11.
    Eastell R, Cedel SL, Wahner HW et al (1991) Classification of vertebral fractures. J Bone Miner Res 6(3):207–215PubMedCrossRefGoogle Scholar
  12. 12.
    McCloskey E, Spector T, Eyres K et al (1993) The assessment of vertebral deformity: a method for use in population studies and clinical trials. Osteoporos Int 3(3):138–147PubMedCrossRefGoogle Scholar
  13. 13.
    Guglielmi G, Diacinti D, van Kuijk C et al (2008) Vertebral morphometry: current methods and recent advances. Eur Radiol 18(7):1484–1496PubMedCrossRefGoogle Scholar
  14. 14.
    Wu CY, Li J, Jergas M et al (1995) Comparison of semiquantitative and quantitative techniques for the assessment of prevalent and incident vertebral fractures. Osteoporos Int 5(5):354–370PubMedCrossRefGoogle Scholar
  15. 15.
    Black D, Palermo L, Nevitt MC et al (1995) Comparison of methods for defining prevalent vertebral deformities: the study of osteoporotic fractures. J Bone Miner Res 10(6):890–902PubMedCrossRefGoogle Scholar
  16. 16.
    Jiang G, Eastell R, Barrington NA, Ferrar L (2004) Comparison of methods for the visual identification of prevalent vertebral fracture in osteoporosis. Osteoporos Int 15(11):887–896PubMedCrossRefGoogle Scholar
  17. 17.
    Roberts MG, Pacheco EM, Mohamkumar R, Cootes TF, Adams JE (2010) Detection of vertebral fractures in DXA VFA images using statistical models of appearance and a semi-automatic segmentation. Osteoporos Int 21:2037–2046PubMedCrossRefGoogle Scholar
  18. 18.
    de Bruijne M, Lund M, Tanko L et al (2007) Quantitative vertebral morphometry using neighbour-conditional shape models. Med Image Anal 11(5):503–512PubMedCrossRefGoogle Scholar
  19. 19.
    Cootes TF, Edwards GJ, Taylor CJ (1998) Active appearance models. In: Burkhardt H, Neumann B (eds) Proc. 5th European conference on computer vision. Springer, Berlin, pp 484–498Google Scholar
  20. 20.
    Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Pattern Match Mach Intell 23(6):681–885CrossRefGoogle Scholar
  21. 21.
    Roberts MG, Cootes TF, Adams JE (2006) Vertebral morphometry: semiautomatic determination of detailed shape from dual-energy x-ray absorptiometry images using active appearance models. Invest Radiol 41(12):849–859PubMedCrossRefGoogle Scholar
  22. 22.
    Cooper C, Shah S, Hand DJ et al (1991) Screening for vertebral osteoporosis using individual risk factors. Osteoporos Int 2:48–53PubMedCrossRefGoogle Scholar
  23. 23.
    Gluer C, Eastell R, Reid DM et al (2004) Association of five quantitative ultrasound devices and bone densitometry with osteoporotic vertebral fractures in a population-based sample: the OPUS study. J Bone Miner Res 19:782–793PubMedCrossRefGoogle Scholar
  24. 24.
    Ferrar L, Jiang G, Barrington NA, Eastell R (2000) Identification of vertebral deformities in women: comparison of radiological assessment and quantitative morphometry using morphometric radiography and morphometric x-ray absorptiometry. J Bone Miner Res 15(3):575–585PubMedCrossRefGoogle Scholar
  25. 25.
    Scott IM, Cootes TF, Taylor CJ (2003) Improving active appearance model matching using local image structure. In: Proceedings of the 18th conference on information processing in medical imaging, Ambleside, UK, July 20–25, 2003, pp 258–269Google Scholar
  26. 26.
    Roberts MG (2008) Automatic detection and classification of vertebral fracture using statistical models of appearance. PhD thesis, University of ManchesterGoogle Scholar
  27. 27.
    Howe B, Gururajan A, Sari-Sarraf H et al. (2004) Hierarchical segmentation of cervical and lumbar vertebrae using a customized generalized hough transform and extensions to active appearance models. In: Proceedings IEEE 6th SSIAI, Lake Tahoe, NV, March 2004, 182–186Google Scholar
  28. 28.
    de Bruijne M, Nielsen M. (2004) Image segmentation by shape particle filtering. In: Proc. International Conference on Pattern Recognition 2004, 722–725Google Scholar
  29. 29.
    Ettinger B, Black DM (1999) Reduction of vertebral fracture risk in postmenopausal women with osteoporosis treated with raloxifene: results from a 3 year randomized clinical trial. Multiple Outcomes of Raloxifene Evaluation (MORE) investigators. JAMA 282(7):637–645PubMedCrossRefGoogle Scholar
  30. 30.
    Siris E, Genant HK, Laster AJ et al (2007) Enhanced prediction of fracture risk combining vertebral fracture and BMD. Osteoporos Int 18(6):761–770PubMedCrossRefGoogle Scholar
  31. 31.
    Neer RM, Arnaud CD, Zanetta JR et al (2001) Effect of parathyroid hormone (1–34) on bone mineral density in postmenopausal women with osteoporosis. N Engl J Med 344(19):1434–1441PubMedCrossRefGoogle Scholar
  32. 32.
    Genant HK, Delmas PD, Chen P et al (2007) Severity of vertebral fracture reflects deterioration of bone microarchitecture. Osteoporos Int 18(1):69–76PubMedCrossRefGoogle Scholar
  33. 33.
    Parfitt AM, Mathews CH (1983) Relations between surface, volume and thickness of iliac trabecular bone in aging and in osteoporosis. Implications for the microanatomic and cellular mechanisms of bone loss. J Clin Invest 72:1396–1409PubMedCrossRefGoogle Scholar
  34. 34.
    Roberts MG, Cootes TF, Pacheco E, Adams JE (2007) Quantitative vertebral fracture detection on DXA images using shape and appearance models. Acad Radiol 14(10):1166–1178PubMedCrossRefGoogle Scholar

Copyright information

© International Osteoporosis Foundation and National Osteoporosis Foundation 2011

Authors and Affiliations

  • M. G. Roberts
    • 1
    Email author
  • T. Oh
    • 1
  • E. M. B. Pacheco
    • 1
    • 2
  • R. Mohankumar
    • 1
  • T. F. Cootes
    • 1
  • J. E. Adams
    • 3
  1. 1.Imaging Science and Biomedical EngineeringUniversity of ManchesterManchesterUK
  2. 2.Department of Radiology, Faculty of Medical SciencesState University of Campinas (Unicamp)CampinasBrazil
  3. 3.Clinical RadiologyManchester Royal InfirmaryManchesterUK

Personalised recommendations