Localisation of Vertebrae on DXA Images Using Constrained Local Models with Random Forest Regression Voting

  • P. A. BromileyEmail author
  • J. E. Adams
  • T. F. Cootes
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 20)


Fractures associated with osteoporosis are a significant public health risk, and one that is likely to increase with an ageing population. However, many osteoporotic vertebral fractures present on images do not come to clinical attention or lead to preventative treatment. Furthermore, vertebral fracture assessment (VFA) typically depends on subjective judgement by a radiologist. The potential utility of computer-aided VFA systems is therefore considerable. Previous work has shown that Active Appearance Models (AAMs) give accurate results when locating landmarks on vertebra in DXA images, but can give poor fits in a substantial subset of examples, particularly the more severe fractures. Here we evaluate Random Forest Regression Voting Constrained Local Models (RFRV-CLMs) for this task and show that, while they lead to slightly poorer median errors than AAMs, they are much more robust, reducing the proportion of fit failures by 68 %. They are thus more suitable for use in computer-aided VFA systems.


Vertebral Fracture Manual Annotation Vertebral Height Vertebral Fracture Assessment Active Appearance 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.



This publication presents independent research supported by the Health Innovation Challenge Fund (grant no. HICF-R7-414/WT100936), a parallel funding partnership between the Department of Health and Wellcome Trust. The views expressed in this publication are those of the authors and not necessarily those of the Department of Health or Wellcome Trust.


  1. 1.
    Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)CrossRefzbMATHGoogle Scholar
  2. 2.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. 23, 681–685 (2001)CrossRefGoogle Scholar
  3. 3.
    Cootes, T.F., Ionita, M.C., Lindner, C., Sauer, P.: Robust and Accurate Shape Model Fitting Using Random Forest Regression Voting. In: Proc. ECCV, pp. 278–291. Springer, Berlin (2012)Google Scholar
  4. 4.
    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
  5. 5.
    Cristinacce, D., Cootes, T.: Automatic feature localisation with constrained local models. J. Pattern Recognit. 41(10), 3054–3067 (2008)CrossRefzbMATHGoogle Scholar
  6. 6.
    Cummings, S.R., Melton, J.: Epidemiology and outcomes of osteoporotic fractures. Lancet 359(9319), 1761–1767 (2002)CrossRefGoogle Scholar
  7. 7.
    Dantone, M., Gall, J., Fanelli, G., Van Gool, L.: Real-time facial feature detection using conditional regression forests. In: Proc. CVPR, pp. 2578–2585 (2012)Google Scholar
  8. 8.
    Delmas, P.D., van de Langerijt, L., Watts, N.B., Eastell, R., Genant, H.K., Grauer, A., Cahall, D.L.: Underdiagnosis of vertebral fractures is a worldwide problem: the IMPACT study. J. Bone Miner. Res. 20(4), 557–563 (2005)CrossRefGoogle Scholar
  9. 9.
    Donner, R., Menze, B., Bischof, H., Langs, G.: Fast anatomical structure localization using top-down image patch regression. In: Medical Computer Vision, Recognition Techniques and Applications in Medical Imaging, Lecture Notes in Computer Science, vol. 7766, pp. 133–141 (2013)Google Scholar
  10. 10.
    Genant, H.K., Wu, C.Y., Kuijk, C.V., Nevitt, M.C.: Vertebral fracture assessment using a semi-quantitative technique. J. Bone Miner. Res. 8(9), 1137–1148 (1993)CrossRefGoogle Scholar
  11. 11.
    Leech, J.A., Dulberg, C., Kellie, S., Pattee, L., Gay, J.: Relationship of lung function to severity of osteoporosis in women. Am. Rev. Respir. Dis. 141(1), 68–71 (1990)CrossRefGoogle Scholar
  12. 12.
    Leidig-Bruckner, G., Minne, H.W.: The spine deformity index (SDI); a new approach to quantifying vertebral crush fractures in patients with osteoporosis. Vertebral Fracture in Osteoporosis, pp. 235–252. Osteoporosis Research Group, University of California, California (1995)Google Scholar
  13. 13.
    Lindner, C., Thiagarajah, S., Wilkinson, J.M., arcOGEN Consortium, T., Wallis, G.A., Cootes, T.F.: Fully automatic segmentation of the proximal femur using random forest regression voting. IEEE Trans. Med. Imaging 32(8), 1462–1472 (2013)CrossRefGoogle Scholar
  14. 14.
    McCloskey, E., Selby, P., de Takats, D., Bernard, J., Davies, M., Robinson, J., Francis, R., Adams, J., Pande, K., Beneton, M., Jalava, T., Loyttyniemi, E., Kanis, J.A.: Effects of clodronate on vertebral fracture risk in osteoporosis: a 1-year interim analysis. Bone 28(3), 310–315 (2001)CrossRefGoogle Scholar
  15. 15.
    Rachner, T.D., Khosla, S., Hofbauer, L.C.: Osteoporosis: now and the future. Lancet 377(9773), 1276–1287 (2011)CrossRefGoogle Scholar
  16. 16.
    Roberts, M.G., Cootes, T.F., Adams, J.E.: Vertebral morphometry: semi-automatic determination of detailed shape from DXA images using active appearance models. Investig. Radiol. 41(12), 849–859 (2006)CrossRefGoogle Scholar
  17. 17.
    Roberts, M.G., Cootes, T.F., Adams, J.E.: Automatic Location of Vertebrae on DXA Images Using Random Forest Regression. In: Proc. MICCAI 2012, LNCS, vol. 7512, pp. 361–368. Springer-Verlag, Berlin (2012)Google Scholar
  18. 18.
    Sauer, P., Cootes, T., Taylor, C.: Accurate Regression Procedures for Active Appearance Models. In: J. Hoey, S. McKenna, E. Trucco (eds.) Proc. BMVC, pp. 30.1–30.11 (2011)Google Scholar
  19. 19.
    Valstar, M.F., Martinez, B., Binefa, X., Pantic, M.: Facial point detection using boosted regression and graph models. In: Proc. CVPR, pp. 2729–2736 (2010)Google Scholar
  20. 20.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. CVPR, pp. 511–518. IEEE Computer Society (2001)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Imaging Sciences Research GroupUniversity of ManchesterManchesterUK
  2. 2.Radiology & Manchester Academic Health Science CentreCentral Manchester University Hospitals NHS Foundation TrustManchesterUK

Personalised recommendations