Automatic 3D Reconstruction Detection System for Knee Osteoarthritis Based on K-Means Algorithm

  • Kadry Ali EzzatEmail author
  • Lamia Nabil Mahdy
  • Aboul Ella Hassanien
  • Ashraf Darwish
  • Snasel Vaclav
  • Deepak Gupta
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1087)


This paper exhibits an automatic determination framework for knee osteoarthritis. The pre-handling stage incorporates three primary steps. The initial step is visualizing DICOM in three perspectives then distinguishes the three main knee parts, trailed by applying the second step which is an adaptive threshold and the third step is applying adjusted region growing methods to isolate the knee from the encompassing bones and tissues. At that point, the second stage is applied to divide each part in the knee utilizing a K-means clustering algorithm. At long last, the third stage happened by three dimensions (3D) recreation for fragmented parts of the knee to help orthopedics in the diagnosis procedure. The 3D reconstruction detection framework was tried on seven datasets obtained from the Cancer Imaging Archive (TCIA). The test results emphatically exhibit that the expected framework is useful in the detection of knee osteoarthritis.


Knee osteoarthritis Automatic detection Cartilage Magnetic resonance imaging (MRI) 


  1. 1.
    S. Liu, J. Yang, C. Huang, M.H. Yang, Multi-objective convolutional learning for face labeling, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 100, pp. 3451–3459 (2015)Google Scholar
  2. 2.
    O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, et al., ImageNet large-scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  3. 3.
    N. Kowsalya et al., Skin-melanoma evaluation with Tsallis’s thresholding and Chan-Vese approach, in 2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA), pp. 1–5 (2018)Google Scholar
  4. 4.
    E.B. Dam, M. Lillholm, J. Marques, M. Nielsen, Automatic segmentation of high-end low-field knee MRIs using knee image quantification with data from the osteoarthritis initiative. J. Med. Imaging 2(2), 24001–24011 (2015)CrossRefGoogle Scholar
  5. 5.
    F. Liu, Z. Zhou, H. Jang, A. Samsonov, G. Zhao, R. Kijowski, Deep convolutional neural network and 3d deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging. Magn. Reson. Med. 79(4), 2379–2391 (2017)CrossRefGoogle Scholar
  6. 6.
    L. Shamir, S.M. Ling, W. Scott, M. Hochberg, L. Ferrucci, I.G. Goldberg, Early detection of radiographic knee osteoarthritis using computer-aided analysis. Osteoarthr. Cartil. 17(10), 1307–1312 (2009)CrossRefGoogle Scholar
  7. 7.
    T.K. Yo, D.W. Kim, S.B. Choi, J.S. Park, Simple scoring system and artificial neural network for knee osteoarthritis risk prediction: A cross-sectional study. PLOS One 11(2), 520–528 (2016)Google Scholar
  8. 8.
    L. Shamer, S.M. Ling, W.W. Scott Jr., A. Bos, N. Orlov, T.J. Macura, D.M. Eckley, L. Ferrucci, I.G. Goldberg, Knee X-ray image analysis method for automated detection of osteoarthritis. IEEE Trans. Biomed. Eng. 56(2), 407–415 (2009)CrossRefGoogle Scholar
  9. 9.
    N. Orlov, L. Shamer, T. Macura, J. Johnston, D.M. Eckley, I.G. Goldberg, WND-CHARM: Multi-purpose image classification using compound image transforms. Pattern Recognit. Lett. 29(11), 1684–1693 (2008)Google Scholar
  10. 10.
    N.D. Salih, D. Saleh Marwan, C. Eswaran, J. Abdullah, Fast optic disc segmentation using FFT-based template-matching and region-growing techniques. Comput. Meth. Biomech. Biomed. Eng. Imag. Vis. 6(1), 101–112 (2017)Google Scholar
  11. 11.
    J. Qi, Y. Yu, L. Wang, et al., K-means: An effective and efficient K-means clustering algorithm, in Proceedings of the IEEE International Conferences on Big Data and Cloud Computing, vol. 13 (IEEE, Atlanta, GA), pp. 242–249 (2016)Google Scholar
  12. 12.
    J. Canilho, M. Véstias, H. Neto, Multi-core for K-means clustering on FPGA, in 2016 26th International Conference on Field Programmable Logic and Applications (FPL), pp. 1–4 (2016)Google Scholar
  13. 13.
    R.J. Crawford, J. Cornwall, R. Abbott, J.M. Elliott, Manually defining regions of interest when quantifying paravertebral muscles fatty infiltration from axial magnetic resonance imaging: A intended method for the lumbar spine with an anatomical cross-reference. BMC Muscoskel. Disord. 30–38 (2017)Google Scholar
  14. 14.
    L.N. Omran, K.A. Ezzat, A.E. Hassanien, Decision support system for determination of forces applied in orthodontic based on fuzzy logic, in the International Conference on Advanced Machine Learning Technologies and Applications (AMLTA2018), (Springer), pp. 158–168 (2018)Google Scholar
  15. 15.
    L.N. Omran, K.A. Ezzat, A.E. Hassanien, Automatic detection system for degenerative disk and simulation for artificial disc replacement surgery in the spine. ISA Trans. 81, 244–258. (2018). Scholar
  16. 16.
    L.N. Omran, K.A. Ezzat, A.E. Hassanien, Biomechanics of artificial intervertebral disc with different materials using finite element method. Soft. Comput. (2018). Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Kadry Ali Ezzat
    • 1
    Email author
  • Lamia Nabil Mahdy
    • 1
  • Aboul Ella Hassanien
    • 2
  • Ashraf Darwish
    • 3
  • Snasel Vaclav
    • 4
  • Deepak Gupta
    • 5
  1. 1.Biomedical Engineering DepartmentHigher Technological Institute10th of RamadanEgypt
  2. 2.Faculty of Computers and InformationCairo UniversityCairoEgypt
  3. 3.Faculty of ScienceHelwan UniversityHelwanEgypt
  4. 4.Faculty of Electrical Engineering and Computer ScienceVSB-Technical University of OstravaOstravaCzech Republic
  5. 5.Maharaja Agrasen Institute of TechnologyDelhiIndia

Personalised recommendations