Robust Proximal Femur Segmentation in Conventional X-Ray Images via Random Forest Regression on Multi-resolution Gradient Features

  • Cheng Chen
  • Guoyan Zheng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7950)


In this paper, we propose a fully automatic, robust approach for segmenting proximal femur in conventional X-ray images. Our method is based on hierarchical landmark detection by random forest regression, where the detection results of 22 global landmarks are used to do the spatial normalization, and the detection results of the 59 local landmarks serve as the image cue for instantiation of a statistical shape model of the proximal femur. To detect landmarks in both levels, we use multi-resolution HoG (Histogram of Oriented Gradients) as features which can achieve better accuracy and robustness. The efficacy of the present method is demonstrated by experiments conducted on 150 clinical x-ray images. It was found that the present method could achieve an average point-to-curve error of 2.0 mm and that the present method was robust to low image contrast, noise and occlusions caused by implants.


X-ray segmentation femur landmark detection random forest statistical shape model 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chen, Y., Ee, X., Leow, W.K., Howe, T.S.: Automatic extraction of femur contours from hip X-ray images. In: Liu, Y., Jiang, T., Zhang, C. (eds.) CVBIA 2005. LNCS, vol. 3765, pp. 200–209. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  2. 2.
    Lindner, C., Thiagarajah, S., Wilkinson, J.M., Wallis, G.A., Cootes, T.F.: Accurate fully automatic femur segmentation in pelvic radiographs using regression voting. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part III. LNCS, vol. 7512, pp. 353–360. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  3. 3.
    Gottschling, H., Roth, M., Schweikard, A., Burgkart, R.: Intraoperative, fluoroscopy-based planning for complex osteotomies of the proximal femur. IJMRCAS 1(3), 33–38 (2005)CrossRefGoogle Scholar
  4. 4.
    Baka, N., Kaptein, B.L., de Bruijne, M., et al.: 2D-3D shape reconstruction of the distal femur from stereo x-ray imaging using statistical shape model. Med. Image Anal. 15(6), 840–850 (2011)CrossRefGoogle Scholar
  5. 5.
    Dong, X., Zheng, G.: Automatic extraction of proximal femur contours from calibrated x-ray images using 3D statistical models: an in vitro study. IJMRCAS 5(2), 213–222 (2009)CrossRefGoogle Scholar
  6. 6.
    Cristinacce, D., Cootes, T.: Automatic feature localization with constrained local models. Pattern Recognition 41(19), 3054–3067 (2008)zbMATHCrossRefGoogle Scholar
  7. 7.
    Gall, J., Lempitsky, V.: Class-specific Hough forests for object detection. In: CVPR 2009, pp. 1022–1029 (2009)Google Scholar
  8. 8.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR 2005, vol. I, pp. 886–893 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Cheng Chen
    • 1
  • Guoyan Zheng
    • 1
  1. 1.Institute for Surgical Technology and BiomechanicsUniversity of BernSwitzerland

Personalised recommendations