Recognizing knee pathologies by classifying instantaneous screws of the six degrees-of-freedom knee motion

Original Article

Abstract

We address the problem of knee pathology assessment by using screw theory to describe the knee motion and by using the screw representation of the motion as an input to a machine learning classifier. The flexions of knees with different pathologies are tracked using an optical tracking system. The instantaneous screw parameters which describe the transformation of the tibia with respect to the femur in each two successive observation is represented as the instantaneous screw axis of the motion given in its Plücker line coordinates along with its corresponding pitch. The set of instantaneous screw parameters associated with a particular knee with a given pathology is then identified and clustered in R6 to form a “signature” of the motion for the given pathology. Sawbones model and two cadaver knees with different pathologies were tracked, and the resulting screws were used to train a classifier system. The system was then tested successfully with new, never-trained-before data. The classifier demonstrated a very high success rate in identifying the knee pathology.

Keywords

Knee kinematics Screw axis Pathology classification Support vector machines 

References

  1. 1.
    Andriacchi T P, Alexander E J., et al. (1998) A point cluster method for in vivo motion analysis: applied to a study of knee kinematics. J Biomech Eng 120(6):743–749Google Scholar
  2. 2.
    Ball RS (1900) A treatise on the theory of screws. Cambridge University Press CambridgeGoogle Scholar
  3. 3.
    Begg R, Kamruzzaman J (2005) A machine learning approach for automated recognition of movement patterns using basic, kinetic and kinematic gait data. J Biomech 38:401–408CrossRefGoogle Scholar
  4. 4.
    Blankevoort L, Huiskes R, et al. (1990) Helical axes of passive knee joint motions. J Biomech 23(12):1219CrossRefGoogle Scholar
  5. 5.
    Bottlang M, Marsh JL, et al. (1998) Factors influencing accuracy of screw displacement axis detection with a D.C.-based electromagnetic tracking system. J Biomech Eng Trans ASME 120(3):431Google Scholar
  6. 6.
    Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Mining Knowl Disc 2(2):121–167CrossRefGoogle Scholar
  7. 7.
    Caruntu DI, Hefzy MS (2004) 3-D anatomically based dynamic modeling of the human knee to include tibio-femoral and patello-femoral joints. J Biomech Eng 126(1):44–53CrossRefGoogle Scholar
  8. 8.
    Davidson JK, Hunt KH (2004) Robots and screw theory: applications of kinematics and statics to robotics. Oxford University Press, New YorkMATHGoogle Scholar
  9. 9.
    DiGioia AB, Jaramaz J, et al. (2000) Surgical navigation for total hip replacement with the use of Hipnav. Oper Techn Orthop 10(1):3–8CrossRefGoogle Scholar
  10. 10.
    Duck TR, Ferreira LM, et al. (2004) Assessment of screw displacement axis accuracy and repeatability for joint kinematic description using an electromagnetic tracking device. J Biomech 37(1):163CrossRefGoogle Scholar
  11. 11.
    Fernandez JW, Hunter P J (2005) An anatomically based patient-specific finite element model of patella articulation: towards a diagnostic tool. Biomech Model Mechanobiol 4(1):20–38CrossRefGoogle Scholar
  12. 12.
    Hart R, Mote C J, et al. (1991) A finite helical axis as a landmark for kinematic reference of the knee. J Biomech Eng 113(2):215–222Google Scholar
  13. 13.
    Hasan SS, Hurwitz DE, et al. (1998) Dynamic evaluation of knee instability during gait in anterior cruciate ligament deficient patients. Trans Orthop Res Soc 44:805Google Scholar
  14. 14.
    Hefzy MS, Ebraheim N, Mekhail A, Caruntu D, Lin H, Yeasting R, (2003) Kinematics of the human pelvis following open book injury. Med Eng Phys 25(4):259–274CrossRefGoogle Scholar
  15. 15.
    Hunt KH (1978) Kinematic geometry of mechanisms. Clarendon, OxfordMATHGoogle Scholar
  16. 16.
    Jonsson H, Karrholm J (1994) Three-dimensional knee joint movements during a step-up: evaluation after anterior cruciate ligament rupture. J Orthop Res 12(6):769–779CrossRefGoogle Scholar
  17. 17.
    Maki B (1997) Gait changes in older adults: predictors of falls or indicators of fear? J Am Geriatr Soc 45:313–320Google Scholar
  18. 18.
    Pottmann H, Wallner J (2001) Computational line geometry. Springer, BerlinMATHGoogle Scholar
  19. 19.
    Roth B (1984) Screws, motors, and wrenches that cannot be bought in a hardware store. MIT Press, CambridgeGoogle Scholar
  20. 20.
    Scholten R J, Opstelten W, et al. (2003) Accuracy of physical diagnostic tests for assessing ruptures of the anterior cruciate ligament: a meta-analysis. J Fam PractGoogle Scholar
  21. 21.
    Shiavi R, Limbird T, et al. (1987) Helical motion analysis of the knee—I. Methodology for studying kinematics during locomotion. J Biomech 20:459–469CrossRefGoogle Scholar
  22. 22.
    Soudan K, Van Audekercke R, Martens M (1979) Methods, difficulties and inaccuracies in the study of human joint kinematics and pathokinematics by the instant axis concept. Example: the knee joint. J Biomech 12:27–33CrossRefGoogle Scholar
  23. 23.
    Vapnik VN (1995) The nature of statistical learning theory. Springer, New YorkMATHGoogle Scholar
  24. 24.
    Vapnik VN (1998) Statistical learning theory. Wiley, New YorkMATHGoogle Scholar
  25. 25.
    Woltring HJ, Huiskes R, et al. (1985) Finite centroid and helical axis estimation from noisy landmark measurements in the study of human joint kinematics. J Biomech 185:379–389CrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2007

Authors and Affiliations

  1. 1.Faculty of Mechanical EngineeringTechnion, Israel Institute of TechnologyHaifaIsrael
  2. 2.The Robotics InstituteCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations