Automatic Location of Vertebrae on DXA Images Using Random Forest Regression

  • M. G. Roberts
  • Timothy F. Cootes
  • J. E. Adams
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7512)

Abstract

We provide a fully automatic method of segmenting vertebrae in DXA images. This is of clinical relevance to the diagnosis of osteoporosis by vertebral fracture, and to grading fractures in clinical trials. In order to locate the vertebrae we train detectors for the upper and lower vertebral endplates. Each detector uses random forest regressor voting applied to Haar-like input features. The regressors are applied at a grid of points across the image, and each tree votes for an endplate centre position. Modes in the smoothed vote image are endplate candidates, some of which are the neighbouring vertebrae of the one sought. The ambiguity is resolved by applying geometric constraints to the connections between vertebrae, although there can be some ambiguity about where the sequence starts (e.g. is the lowest vertebra L4 or L5, Fig 2a). The endplate centres are used to initialise a final phase of Active Appearance Model search for a detailed solution. The method is applied to a dataset of 320 DXA images. Accuracy is comparable to manually initialised AAM segmentation in 91% of images, but multiple grade 3 fractures can cause some edge confusion in severely osteoporotic cases.

Keywords

Vertebral Fracture Random Forest Vertebral Fracture Assessment Active Appearance Model Lower Endplate 
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.
Download to read the full conference paper text

References

  1. 1.
    Roberts, M.G., Cootes, T.F., Pacheco, E.M., Adams, J.E.: Quantitative vertebral fracture detection on DXA images using shape and appearance models. Academic Radiology 14, 1166–1178 (2007)CrossRefGoogle Scholar
  2. 2.
    de Bruijne, M., Lund, M., Tanko, L., Pettersen, P., Nielsen, M.: Quantitative vertebral morphometry using neighbour-conditional shape models. Med. Image Anal. 11, 503–512 (2007)CrossRefGoogle Scholar
  3. 3.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 681–685 (2001)CrossRefGoogle Scholar
  4. 4.
    Roberts, M.G., Cootes, T.F., Adams, J.E.: Vertebral morphometry: semi-automatic determination of detailed shape from DXA images using active appearance models. Investigative Radiology 41(12), 849–859 (2006)CrossRefGoogle Scholar
  5. 5.
    McCloskey, E.V., et al.: Effects of clodronate on vertebral fracture risk in osteoporosis: a 1-year interim analysis. Bone 28(3), 310–315 (2001)CrossRefGoogle Scholar
  6. 6.
    Breiman, L.: Random forests. Machine Learning 45, 5–32 (2001)MATHCrossRefGoogle Scholar
  7. 7.
    Criminisi, A., Shotton, J., Robertson, D., Konukoglu, E.: Regression Forests for Efficient Anatomy Detection and Localization in CT Studies. In: Menze, B., Langs, G., Tu, Z., Criminisi, A. (eds.) MICCAI 2010 Workshop MCV. LNCS, vol. 6533, pp. 106–117. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  8. 8.
    Gall, J., Lempitsky, V.: Class-specific hough forests for object detection. In: Proc of CVPR 2009, pp. 1022–1029. IEEE Computer Society (2009)Google Scholar
  9. 9.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc of CVPR 2001, pp. 511–518. IEEE Computer Society (2001)Google Scholar
  10. 10.
    Donner, R., Micusik, B., Langs, G., Bischof, H.: Sparse MRF appearance models for fast anatomical structure localisation. In: Rajpoot, N., Bhalerao, A. (eds.) Proc. of BMVC 2007, pp. 1080–1089. BMVA (2007)Google Scholar
  11. 11.
    Weiss, Y., Freeman, W.: On the optimality of solutions of the max-product belief propagation algorithm in arbitrary graphs. IEEE Trans. Inf. Theory 47, 736–744 (2001)MathSciNetMATHCrossRefGoogle Scholar
  12. 12.
    de Bruijne, M., Nielsen, M.: Image segmentation by shape particle filtering. In: Proc. of ICPR 2004, pp. 722–725. IEEE Computer Society (2004)Google Scholar
  13. 13.
    Petersen, K., Ganz, M., Mysling, P., Nielsen, M., Lillemark, L., Crimi, A., Brandt, S.: A bayesian framework for automated cardiovascular risk scoring on standard lumbar radiographs. IEEE Trans. Med. Imag. 31(3), 663–676 (2012)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • M. G. Roberts
    • 1
  • Timothy F. Cootes
    • 1
  • J. E. Adams
    • 1
  1. 1.Imaging Science Research GroupUniversity of ManchesterU.K.

Personalised recommendations