Advertisement

A Novel Method for Automatic Localization of Joint Area on Knee Plain Radiographs

  • Aleksei Tiulpin
  • Jerome Thevenot
  • Esa Rahtu
  • Simo Saarakkala
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10270)

Abstract

Osteoarthritis (OA) is a common musculoskeletal condition typically diagnosed from radiographic assessment after clinical examination. However, a visual evaluation made by a practitioner suffers from subjectivity and is highly dependent on the experience. Computer-aided diagnostics (CAD) could improve the objectivity of knee radiographic examination. The first essential step of knee OA CAD is to automatically localize the joint area. However, according to the literature this task itself remains challenging. The aim of this study was to develop novel and computationally efficient method to tackle the issue. Here, three different datasets of knee radiographs were used (n = 473/93/77) to validate the overall performance of the method. Our pipeline consists of two parts: anatomically-based joint area proposal and their evaluation using Histogram of Oriented Gradients and the pre-trained Support Vector Machine classifier scores. The obtained results for the used datasets show the mean intersection over the union equals to: 0.84, 0.79 and 0.78. Using a high-end computer, the method allows to automatically annotate conventional knee radiographs within 14–16 ms and high resolution ones within 170 ms. Our results demonstrate that the developed method is suitable for large-scale analyses.

Keywords

Knee radiographs Medical image analysis Object localization Proposal generation 

Notes

Acknowledgements

MOST is comprised of four cooperative grants (Felson – AG18820; Torner – AG18832, Lewis – AG18947, and Nevitt – AG19069) funded by the National Institutes of Health, a branch of the Department of Health and Human Services, and conducted by MOST study investigators. This manuscript was prepared using MOST data and does not necessarily reflect the opinions or views of MOST investigators.

The authors would also like to acknowledge the strategic funding of University of Oulu.

References

  1. 1.
    Antony, J., McGuinness, K., O’Connor, N.E., Moran, K.: Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks. In: Proceedings of 23rd International Conference on Pattern Recognition, ICPR (2016)Google Scholar
  2. 2.
    Berlin, L.: Malpractice issues in radiology. Perceptual errors. AJR Am. J. Roentgenol. 167(3), 587–590 (1996)CrossRefGoogle Scholar
  3. 3.
    Cibere, J.: Do we need radiographs to diagnose osteoarthritis? Best Pract. Res. Clin. Rheumatol. 20(1), 27–38 (2006)CrossRefGoogle Scholar
  4. 4.
    Cross, M., Smith, E., Hoy, D., Nolte, S., Ackerman, I., Fransen, M., Bridgett, L., Williams, S., Guillemin, F., Hill, C.L., et al.: The global burden of hip and knee osteoarthritis: estimates from the global burden of disease 2010 study. Ann. Rheum. Dis. 73, 1323–1330 (2014). doi: 10.1136/annrheumdis-2013-204763 CrossRefGoogle Scholar
  5. 5.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 886–893. IEEE (2005)Google Scholar
  6. 6.
    Demehri, S., Hafezi-Nejad, N., Carrino, J.A.: Conventional and novel imaging modalities in osteoarthritis: current state of the evidence. Curr. Opin. Rheumatol. 27(3), 295–303 (2015)CrossRefGoogle Scholar
  7. 7.
    Duda, R.O., Hart, P.E., Stork, D.G., et al.: Pattern Classification, vol. 2. Wiley, New York (1973)zbMATHGoogle Scholar
  8. 8.
    Duryea, J., Li, J., Peterfy, C., Gordon, C., Genant, H.: Trainable rule-based algorithm for the measurement of joint space width in digital radiographic images of the knee. Med. Phys. 27(3), 580–591 (2000)CrossRefGoogle Scholar
  9. 9.
    Eckstein, F., Hudelmaier, M., Wirth, W., Kiefer, B., Jackson, R., Yu, J., Eaton, C., Schneider, E.: Double echo steady state magnetic resonance imaging of knee articular cartilage at 3 tesla: a pilot study for the osteoarthritis initiative. Ann. Rheum. Dis. 65(4), 433–441 (2006)CrossRefGoogle Scholar
  10. 10.
    Englund, M., Guermazi, A., Roemer, F.W., Aliabadi, P., Yang, M., Lewis, C.E., Torner, J., Nevitt, M.C., Sack, B., Felson, D.T.: Meniscal tear in knees without surgery and the development of radiographic osteoarthritis among middle-aged and elderly persons: The multicenter osteoarthritis study. Arthritis Rheum. 60(3), 831–839 (2009)CrossRefGoogle Scholar
  11. 11.
    Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9, 1871–1874 (2008)zbMATHGoogle Scholar
  12. 12.
    Hirvasniemi, J., Thevenot, J., Immonen, V., Liikavainio, T., Pulkkinen, P., Jämsä, T., Arokoski, J., Saarakkala, S.: Quantification of differences in bone texture from plain radiographs in knees with and without osteoarthritis. Osteoarthritis Cartilage 22(10), 1724–1731 (2014)CrossRefGoogle Scholar
  13. 13.
    Huo, Y., Vincken, K.L., Viergever, M.A., Lafeber, F.P.: Automatic joint detection in rheumatoid arthritis hand radiographs. In: 2013 IEEE 10th International Symposium on Biomedical Imaging, pp. 125–128. IEEE (2013)Google Scholar
  14. 14.
    Itseez: Open source computer vision library (2016). https://github.com/itseez/opencv
  15. 15.
    Lindner, C., Thiagarajah, S., Wilkinson, J., Wallis, G., Cootes, T., The arcOGEN Consortium, et al.: Development of a fully automatic shape model matching (FASMM) system to derive statistical shape models from radiographs: application to the accurate capture and global representation of proximal femur shape. Osteoarthritis Cartilage 21(10), 1537–1544 (2013)Google Scholar
  16. 16.
    Multanen, J., Heinonen, A., Häkkinen, A., Kautiainen, H., Kujala, U., Lammentausta, E., Jämsä, T., Kiviranta, I., Nieminen, M.: Bone and cartilage characteristics in postmenopausal women with mild knee radiographic osteoarthritis and those without radiographic osteoarthritis. J. Musculoskelet. Neuronal Interact. 15(1), 69–77 (2015)Google Scholar
  17. 17.
    Pitman, A.: Perceptual error and the culture of open disclosure in Australian radiology. Australas. Radiol. 50(3), 206–211 (2006)CrossRefGoogle Scholar
  18. 18.
    Podlipská, J., Guermazi, A., Lehenkari, P., Niinimäki, J., Roemer, F.W., Arokoski, J.P., Kaukinen, P., Liukkonen, E., Lammentausta, E., Nieminen, M.T., et al.: Comparison of diagnostic performance of semi-quantitative knee ultrasound and knee radiography with MRI: Oulu knee osteoarthritis study. Sci. Rep. 6 (2016)Google Scholar
  19. 19.
    Podsiadlo, P., Wolski, M., Stachowiak, G.: Automated selection of trabecular bone regions in knee radiographs. Med. Phys. 35(5), 1870–1883 (2008)CrossRefGoogle Scholar
  20. 20.
    Podsiadlo, P., Cicuttini, F., Wolski, M., Stachowiak, G., Wluka, A.: Trabecular bone texture detected by plain radiography is associated with an increased risk of knee replacement in patients with osteoarthritis: a 6 year prospective follow up study. Osteoarthritis Cartilage 22(1), 71–75 (2014)CrossRefGoogle Scholar
  21. 21.
    Seise, M., McKenna, S.J., Ricketts, I.W., Wigderowitz, C.A.: Double contour active shape models. In: BMVC. Citeseer (2005)Google Scholar
  22. 22.
    Shamir, L., Ling, S.M., Scott, W., Hochberg, M., Ferrucci, L., Goldberg, I.G.: Early detection of radiographic knee osteoarthritis using computer-aided analysis. Osteoarthritis Cartilage 17(10), 1307–1312 (2009)CrossRefGoogle Scholar
  23. 23.
    Stachowiak, G.W., Wolski, M., Woloszynski, T., Podsiadlo, P.: Detection and prediction of osteoarthritis in knee and hand joints based on the x-ray image analysis. Biosurface Biotribology 2, 162–172 (2016)CrossRefGoogle Scholar
  24. 24.
    Thomson, J., O’Neill, T., Felson, D., Cootes, T.: Automated shape and texture analysis for detection of osteoarthritis from radiographs of the knee. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9350, pp. 127–134. Springer, Cham (2015). doi: 10.1007/978-3-319-24571-3_16 CrossRefGoogle Scholar
  25. 25.
    Uijlings, J.R., van de Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154–171 (2013)CrossRefGoogle Scholar
  26. 26.
    Woloszynski, T., Podsiadlo, P., Stachowiak, G., Kurzynski, M.: A signature dissimilarity measure for trabecular bone texture in knee radiographs. Med. Phys. 37(5), 2030–2042 (2010)CrossRefGoogle Scholar
  27. 27.
    Zitnick, C.L., Dollár, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391–405. Springer, Cham (2014). doi: 10.1007/978-3-319-10602-1_26 Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Aleksei Tiulpin
    • 1
  • Jerome Thevenot
    • 1
  • Esa Rahtu
    • 2
  • Simo Saarakkala
    • 1
    • 3
  1. 1.Research Unit of Medical Imaging, Physics and TechnologyUniversity of OuluOuluFinland
  2. 2.Center for Machine Vision and Signal AnalysisUniversity of OuluOuluFinland
  3. 3.Department of Diagnostic RadiologyOulu University HospitalOuluFinland

Personalised recommendations