Accurate Fully Automatic Femur Segmentation in Pelvic Radiographs Using Regression Voting

  • C. Lindner
  • S. Thiagarajah
  • J. M. Wilkinson
  • arcOGEN Consortium
  • G. A. Wallis
  • Timothy F. Cootes
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7512)


Extraction of bone contours from radiographs plays an important role in disease diagnosis, pre-operative planning, and treatment analysis. We present a fully automatic method to accurately segment the proximal femur in anteroposterior pelvic radiographs. A number of candidate positions are produced by a global search with a detector. Each is then refined using a statistical shape model together with local detectors for each model point. Both global and local models use Random Forest regression to vote for the optimal positions, leading to robust and accurate results. The performance of the system is evaluated using a set of 519 images. We show that the fully automated system is able to achieve a mean point-to-curve error of less than 1mm for 98% of all 519 images. To the best of our knowledge, this is the most accurate automatic method for segmenting the proximal femur in radiographs yet reported.


automatic femur segmentation femur detection Random Forests Hough Transform Constrained Local Models radiographs 


  1. 1.
    Behiels, G., Maes, F., Vandermeulen, D., Suetens, P.: Evaluation of image features and search strategies for segmentation of bone structures in radiographs using Active Shape Models. Medical Image Analysis 6(1), 47–62 (2002)CrossRefGoogle Scholar
  2. 2.
    Breiman, L.: Random forests. Machine Learning 45, 5–32 (2001)zbMATHCrossRefGoogle Scholar
  3. 3.
    Cootes, T., Ionita, M., Lindner, C., Sauer, P.: Robust and accurate shape model fitting using random forest regression. Tech. Rep. 2012-01, Uni. Manchester (2012)Google Scholar
  4. 4.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active Appearance Models. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 484–498. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  5. 5.
    Cootes, T., Taylor, C., Cooper, D., Graham, J.: Active shape models - their training and application. Computer Vision and Image Understanding 61(1), 38–59 (1995)CrossRefGoogle Scholar
  6. 6.
    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
  7. 7.
    Cristinacce, D., Cootes, T.: Automatic feature localisation with Constrained Local Models. Journal of Pattern Recognition 41(10), 3054–3067 (2008)zbMATHCrossRefGoogle Scholar
  8. 8.
    Ding, F., Leow, W.-K., Howe, T.S.: Automatic Segmentation of Femur Bones in Anterior-Posterior Pelvis X-Ray Images. In: Kropatsch, W.G., Kampel, M., Hanbury, A. (eds.) CAIP 2007. LNCS, vol. 4673, pp. 205–212. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Gall, J., Lempitsky, V.: Class-specific Hough forests for object detection. In: CVPR, pp. 1022–1029. IEEE Press (2009)Google Scholar
  10. 10.
    Girshick, R., Shotton, J., Kohli, P., Criminisi, A., Fitzgibbon, A.: Efficient regression of general-activity human poses from depth images. In: ICCV, pp. 415–422. IEEE Press (2011)Google Scholar
  11. 11.
    Pilgram, R., et al.: Knowledge-based femur detection in conventional radiographs of the pelvis. Computers in Biology and Medicine 38, 535–544 (2008)CrossRefGoogle Scholar
  12. 12.
    Smith, R., Najarian, K., Ward, K.: A hierarchical method based on active shape models and directed Hough transform for segmentation of noisy biomedical images. BMC Medical Informatics and Decision Making 9(suppl. 1), 2–12 (2009)CrossRefGoogle Scholar
  13. 13.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR, pp. 511–518. IEEE Press (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • C. Lindner
    • 1
  • S. Thiagarajah
    • 2
  • J. M. Wilkinson
    • 2
  • arcOGEN Consortium
  • G. A. Wallis
    • 3
  • Timothy F. Cootes
    • 1
  1. 1.Imaging SciencesUniversity of ManchesterUK
  2. 2.Department of Human MetabolismUniversity of SheffieldUK
  3. 3.Wellcome Trust Centre for Cell Matrix ResearchUniversity of ManchesterUK

Personalised recommendations