Automated Shape and Texture Analysis for Detection of Osteoarthritis from Radiographs of the Knee

  • Jessie Thomson
  • Terence O’Neill
  • David Felson
  • Tim Cootes
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9350)


Osteoarthritis (OA) is considered to be one of the leading causes of disability, however clinical detection relies heavily on subjective experience to condense the continuous features into discrete grades. We present a fully automated method to standardise the measurement of OA features in the knee used to diagnose disease grade. Our approach combines features derived from both bone shape (obtained from an automated bone segmentation system) and image texture in the tibia. A simple weighted sum of the outputs of two Random Forest classifiers (one trained on shape features, the other on texture features) is sufficient to improve performance over either method on its own. We also demonstrate that Random Forests trained on simple pixel ratio features are as effective as the best previously reported texture measures on this task. We demonstrate the performance of the system on 500 knee radiographs from the OAI study.


Computer-aided diagnosis Quantitative Image Analysis X-ray Imaging Imaging Biomarkers Computer Vision 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chen, A., Gupte, C., Akhtar, K., Smith, P., Cobb, J.: The global economic cost of Osteoarthritis: How the UK compares. Arthritis, vol. 2012 (2012)Google Scholar
  2. 2.
    Shamir, L., Ling, S.M., Scott, W.W., Bos, A., Orlov, N.: Knee X-ray image analysis method for automated detection of Osteoarthritis. IEEE Trans. Biomed. Eng. 56(2), 407–415 (2009)CrossRefGoogle Scholar
  3. 3.
    Woloszynski, T., Podsiadlo, P., Stachowiak, G.W., Kurzynski, M.: A signature dissimilarity measure for trabecular bone texture in knee radiographs. Med. Phys. 37(5), 2030–2042 (2010)CrossRefGoogle Scholar
  4. 4.
    Anifah, L., Purnama, I.K.E., Hariadi, M., Purnomo, M.H.: Osteoarthritis classification using self organizing map based on gabor kernel and contrast-limited adaptive histogram equalization. Open Biomed. Eng. J. 7, 18–28 (2013)CrossRefGoogle Scholar
  5. 5.
    Lester, G.: Clinical research in OA. The NIH Osteoarthritis Initiative. J. Musculoskelet. Neuronal. Interact. 8(4), 313–314 (2008)Google Scholar
  6. 6.
    Cootes, T.F., Taylor, C.J.: Statistical Models of Appearance for Computer Vision. Technical report, University of Manchester (2004)Google Scholar
  7. 7.
    Kellgren, J.H., Lawrence, J.S.: Radiological assessment of Osteo-Arthrosis. Annals of the Rheumatic Diseases 16(4), 494–502 (1957)CrossRefGoogle Scholar
  8. 8.
    Cootes, T.F., Ionita, M.C., Lindner, C., Sauer, P.: Robust and accurate shape model fitting using random forest regression voting. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 278–291. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  9. 9.
    Lindner, C., Wilkinson, J.M., Consortium, T.A., Wallis, G.A., Cootes, T.F.: Fully automatic segmentation of the proximal femur using random forest regression voting. IEEE Trans. on Med. Imaging 32(8), 1462–1472 (2013)CrossRefGoogle Scholar
  10. 10.
    Breiman, L.: Random Forests. Machine Learning 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  11. 11.
    Podsiadlo, P., Stachowiak, G.W.: Analysis of shape wear particles found in synovial joints. J. Orthop. Rheumatol. 8, 155–160 (1995)Google Scholar
  12. 12.
    Lee, H., Lee, J., Lin, M. C., Wu, C., Sun, Y.: Automatic assessment of knee Osteoarthritis parameters from two-dimensional X-ray images. In: First International Conference on ICICIC 2006, vol. 2, pp. 673–676 (2006)Google Scholar
  13. 13.
    Wolski, M., Podsiadlo, P., Stachowiak, G. W.: Directional fractal signature analysis of trabecular bone: Evaluation of different methods to detect early Osteoarthritis in knee radiographs. In: Proc. IMechE, vol. 223(2), Part H: J. Eng. Med. pp. 211–236 (2009)Google Scholar
  14. 14.
    Lindner, C., Thiagarajah, S., Wilkinson, J.M., arcOGEN Consortium, Wallis, G.A., Cootes, T.F.: Accurate bone segmentation in 2D radiographs using fully automatic shape model matching based on regression-voting. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part II. LNCS, vol. 8150, pp. 181–189. Springer, Heidelberg (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Jessie Thomson
    • 1
    • 2
  • Terence O’Neill
    • 2
    • 3
  • David Felson
    • 2
    • 3
    • 4
  • Tim Cootes
    • 1
  1. 1.Centre for Imaging SciencesUniversity of ManchesterManchesterUK
  2. 2.NIHR Manchester Musculoskeletal BRU, Central Manchester NHS Foundation TrustMAHSCManchesterUK
  3. 3.Arthritis Research UK Centre for EpidemiologyUniversity of ManchesterManchesterUK
  4. 4.Boston UniversityBostonUSA

Personalised recommendations