Medical & Biological Engineering & Computing

, Volume 46, Issue 3, pp 223–232 | Cite as

Screening of knee-joint vibroarthrographic signals using statistical parameters and radial basis functions

Original Article

Abstract

Externally detected vibroarthrographic (VAG) signals bear diagnostic information related to the roughness, softening, breakdown, or the state of lubrication of the articular cartilage surfaces of the knee joint. Analysis of VAG signals could provide quantitative indices for noninvasive diagnosis of articular cartilage breakdown and staging of osteoarthritis. We propose the use of statistical parameters of VAG signals, including the form factor involving the variance of the signal and its derivatives, skewness, kurtosis, and entropy, to classify VAG signals as normal or abnormal. With a database of 89 VAG signals, screening efficiency of up to 0.82 was achieved, in terms of the area under the receiver operating characteristics curve, using a neural network classifier based on radial basis functions.

Keywords

Entropy Form factor Knee-joint sounds Kurtosis Radial basis functions Skewness Vibroarthrography 

References

  1. 1.
    Barr DA, Long L, Kernohan WG, Mollan RAB (1994) Continuous passive motion in computer assisted auscultation of the knee. Comput Meth Prog Biomed 43:159–169CrossRefGoogle Scholar
  2. 2.
    Beverland DE, Kernohan WG, Mollan RAB (1985) Analysis of physiological patello-femoral crepitus. In: Byford GH (ed) Technology in health care. Biological Engineering Society, London, pp 137–138Google Scholar
  3. 3.
    Beverland DE, Kernohan WG, Mollan RAB (1985) Problems in the analysis of vibration emission from the patello-femoral joint. Med Bio Eng Comput 23(Suppl 2):1253–1254Google Scholar
  4. 4.
    Beverland DE, Kernohan WG, Mollan RAB (1985) What is physiological patello-femoral crepitus? Med Bio Eng Comput 23(Suppl 2):1249–1250Google Scholar
  5. 5.
    Beverland DE, McCoy GF, Kernohan WG, Mollan RAB (1986) What is patellofemoral crepitus? J Bone Joint Surg 68-B:496Google Scholar
  6. 6.
    Binnie CD, Batchelor BG, Bowring PA, Darby CE, Herber L, Lloyd DSL, Smith DM, Smith GF, Smith M (1978) Computer-assisted interpretation of clinical EEGs. Electroencephal Clin Neurophysiol 44:575–585CrossRefGoogle Scholar
  7. 7.
    Binnie CD, Batchelor BG, Gainsborough AJ, Lloyd DSL, Smith DM, Smith GF (1979) Visual and computer-assisted assessment of the EEG in epilepsy of late onset. Electroencephal Clin Neurophysiol 47:102–107CrossRefGoogle Scholar
  8. 8.
    Bircher E (1913) Zur diagnose der meniscusluxation und des meniscusabrisses. Zentralbl f Chir 40:1852–1857Google Scholar
  9. 9.
    Blodgett WE (1902) Auscultation of the knee joint. Boston Med Surg J 146(3):63–66Google Scholar
  10. 10.
    Chen S, Cowan CFN, Grant PM (1991) Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans Neural Net 2(2):302–309CrossRefGoogle Scholar
  11. 11.
    Chu ML, Gradisar IA, Mostardi R (1978) A noninvasive electroacoustical evaluation technique of cartilage damage in pathological knee joints. Med Bio Eng Comput 16:437–442CrossRefGoogle Scholar
  12. 12.
    Chu ML, Gradisar IA, Railey MR, Bowling GF (1976) Detection of knee joint diseases using acoustical pattern recognition technique. J Biomech 9:111–114CrossRefGoogle Scholar
  13. 13.
    Chu ML, Gradisar IA, Railey MR, Bowling GF (1976) An electro-acoustical technique for the detection of knee joint noise. Med Res Eng 12(1):18–20Google Scholar
  14. 14.
    Chu ML, Gradisar IA, Zavodney LD (1978) Possible clinical application of a noninvasive monitoring technique of cartilage damage in pathological knee joints. J Clin Eng 3(1):19–27Google Scholar
  15. 15.
    Cooper R, Osselton JW, Shaw JC (1980) EEG technology, 3rd edn. Butterworths, LondonGoogle Scholar
  16. 16.
    Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley, New YorkMATHGoogle Scholar
  17. 17.
    Erb KH (1933) Über die möglichkeit der registrierung von gelenkgeräuschen. Deutsche Ztschr f Chir 241:237–245Google Scholar
  18. 18.
    Fischer H, Johnson EW (1960) Analysis of sounds from normal and pathologic knee joints. In: Proc 3rd intl congr phys med, pp 50–57Google Scholar
  19. 19.
    Frank CB, Rangayyan RM, Bell GD (1990) Analysis of knee sound signals for non-invasive diagnosis of cartilage pathology. IEEE Eng Med Biol Mag 9(1):65–68CrossRefGoogle Scholar
  20. 20.
    Haykin S (2002) Neural networks: a comprehensive foundation, 2nd edn. Prentice-Hall PTR, Englewood CliffsGoogle Scholar
  21. 21.
    Hjorth B (1970) EEG analysis based on time domain properties. Electroencephal Clin Neurophysiol 29:306–310CrossRefGoogle Scholar
  22. 22.
    Hjorth B (1973) The physical significance of time domain descriptors in EEG analysis. Electroencephal Clin Neurophysiol 34:321–325CrossRefGoogle Scholar
  23. 23.
    Hjorth B (1975) Time domain descriptors and their relation to a particular model for generation of EEG activity. In: Dolce G, Künkel H (eds) CEAN: computerised EEG analysis, Gustav Fischer, Stuttgart, pp 3–8Google Scholar
  24. 24.
    Inoue J, Nagata Y, Suzuki K (1986) Measurement of knee joint sounds by microphone. Sangyo Ika Daigaku Zasshi 8(3):307–316Google Scholar
  25. 25.
    Jackson RW, Abe I (1972) The role of arthroscopy in the management of disorders of the knee: An analysis of 200 consecutive examinations. J Bone Joint Surg 54-B:310–322Google Scholar
  26. 26.
    Jiang CC, Lee JH, Yuan TT (2000) Vibration arthrometry in the patients with failed total knee replacement. IEEE Trans Biomed Eng 47(2):218–227CrossRefGoogle Scholar
  27. 27.
    Jiang CC, Liu YJ, Hang YS (1995) Vibration arthrometry for the diagnosis of meniscal tear of the knee. J Orthop Surg Rep China 12:1–5Google Scholar
  28. 28.
    Jiang CC, Liu YJ, Yip KM, Wu E (1993) Physiological patellofemoral crepitus in knee joint disorders. Bull Hosp Joint Dis 53(4):22–26Google Scholar
  29. 29.
    Kernohan WG, Barr DA, McCoy GF, Mollan RAB (1991) Vibration arthrometry in assessment of knee disorders: the problem of angular velocity. J Biomed Eng 13:35–38CrossRefGoogle Scholar
  30. 30.
    Kernohan WG, Beverland DE, McCoy GF, Hamilton A, Watson P, Mollan RAB (1990) Vibration arthrometry. Acta Orthop Scand 61(1):70–79Google Scholar
  31. 31.
    Kernohan WG, Beverland DE, McCoy GF, Shaw SN, Wallace RGH, McCullagh GC, Mollan RAB (1986) The diagnostic potential of vibration arthrography. Clin Orthop Rel Res 210:106–112Google Scholar
  32. 32.
    Kernohan WG, Mollan RAB (1982) Microcomputer analysis of joint vibration. J Microcomp Appl 5:287–296CrossRefGoogle Scholar
  33. 33.
    Kotani K, Suzuki K (1983) Acoustic analysis of joint-sound through passive motion with special reference to degenerative osteoarthrosis of the knee joints. Nippon Seikeigeta Gakkai Zasshi 57:1869–1880Google Scholar
  34. 34.
    Krishnan S, Rangayyan RM, Bell GD, Frank CB (2000) Adaptive time-frequency analysis of knee joint vibroarthrographic signals for noninvasive screening of articular cartilage pathology. IEEE Trans Biomed Eng 47(6):773–783CrossRefGoogle Scholar
  35. 35.
    Krishnan S, Rangayyan RM, Bell GD, Frank CB (2001) Auditory display of knee-joint vibration signals. J Acoust Soc Am 110(6):3292–3304CrossRefGoogle Scholar
  36. 36.
    Krishnan S, Rangayyan RM, Bell GD, Frank CB, Ladly KO (1997) Adaptive filtering, modelling, and classification of knee joint vibroarthrographic signals for non-invasive diagnosis of articular cartilage pathology. Med Bio Eng Comput 35:677–684CrossRefGoogle Scholar
  37. 37.
    Ladly KO, Frank CB, Bell GD, Zhang YT, Rangayyan RM (1993) The effect of external loads and cyclic loading on normal patellofemoral joint signals. Spl Iss Biomed Eng Def Sci J (India) 43:201–210Google Scholar
  38. 38.
    Lund F, Nilsson BE (1980) Arthroscopy of the patello-femoral joint. Acta Orthop Scand 51:297–302CrossRefGoogle Scholar
  39. 39.
    Mankin HJ (1982) The response of articular cartilage to mechanical injury. J Bone Joint Surg 64-A:462–466Google Scholar
  40. 40.
    Marques de Sá JP (2003) Applied Statistics using SPSS, STATISTICA, and MATLAB. Springer, BerlinGoogle Scholar
  41. 41.
    McCoy GF, McCrea JD, Beverland DE, Kernohan WG, Mollan RAB (1987) Vibration arthrography as a diagnostic aid in diseases of the knee. J Bone Joint Surg 69-B(2):288–293Google Scholar
  42. 42.
    Metz CE (1978) Basic principles of ROC analysis. Sem Nucl Med VIII(4):283–298CrossRefGoogle Scholar
  43. 43.
    Metz CE, Pesce L (2006) Readings in ROC Analysis, with Emphasis on Medical Applications; available at www. radiology. uchicago. http://www.edu /krl/ KRL_ROC/ ROC_analysis_by_topic4.htm. University of Chicago, Chicago
  44. 44.
    Mollan RAB, Kernohan WG, Watters PH (1983) Artefact encountered by the vibration detection system. J Biomech 16(3):193–199CrossRefGoogle Scholar
  45. 45.
    Moussavi ZMK, Rangayyan RM, Bell GD, Frank CB, Ladly KO, Zhang YT (1996) Screening of vibroarthrographic signals via adaptive segmentation and linear prediction modeling. IEEE Trans Biomed Eng 43(1):15–23CrossRefGoogle Scholar
  46. 46.
    Mu T, Nandi AK, Rangayyan RM (2007) Strict 2-surface proximal classification of knee-joint vibroarthrographic signals. In: Proc. 29th ann intl conf IEEE eng med bio soc. IEEE, Lyon, pp 4911–4914Google Scholar
  47. 47.
    Nagata Y (1988) Joint-sounds in gonoarthrosis—clinical application of phonoarthrography for the knees. J Univ Occup Environ Health Japan 10(1):47–58Google Scholar
  48. 48.
    Nagata Y, Suzuki K, Kobayashi Y, Sasaki M, Inoue J, Takyu H (1986) Joint-sounds clinical experience of the knee joint. Sangyo Ika Daigaku Zasshi 8:425–428Google Scholar
  49. 49.
    Peylan A (1953) Direct auscultation of the joints (preliminary clinical observations). Rheumatolgy 9:77–81Google Scholar
  50. 50.
    Rabin EL, Ehrlich MG, Cherrack R, Abermathy P, Paul IL, Rose RM (1978) Effect of repetitive impulsive loading on the knee joints of rabbits. Clin Orthop 131:288Google Scholar
  51. 51.
    Rangayyan RM (2002) Biomedical signal analysis—a case-study approach. IEEE/Wiley, New YorkGoogle Scholar
  52. 52.
    Rangayyan RM (2005) Biomedical image analysis. CRC, Boca RatonGoogle Scholar
  53. 53.
    Rangayyan RM, Krishnan S (2001) Feature identification in the time-frequency plane by using the Hough–Radon transform. Patt Recog 34:1147–1158MATHCrossRefGoogle Scholar
  54. 54.
    Rangayyan RM, Krishnan S, Bell GD, Frank CB, Ladly KO (1997) Parametric representation and screening of knee joint vibroarthrographic signals. IEEE Trans Biomed Eng 44(11):1068–1074CrossRefGoogle Scholar
  55. 55.
    Rangayyan RM, Wu YF (2007) Analysis of knee-joint vibroarthrographic signals using statistical measures. In:Proc. 20th IEEE intl symp computer-based med sys. IEEE, Maribor, pp 377–382Google Scholar
  56. 56.
    Reddy NP, Rothschild BM, Mandal M, Gupta V, Suryanarayanan S (1995) Noninvasive acceleration measurements to characterize knee arthritis and chondromalacia. Ann Biomed Eng 23:78–84CrossRefGoogle Scholar
  57. 57.
    Reddy NP, Rothschild BM, Verrall E, Joshi A (2001) Noninvasive measurement of acceleration at the knee joint in patients with rheumatoid arthritis and spondyloarthropathy of the knee. Ann Biomed Eng 29(12):1106–1111CrossRefGoogle Scholar
  58. 58.
    Sasaki M, Suzuki K, Inoue J (1991) Analysis and application of joint sounds to osteoarthritis of the knee. Trans Comb Meet Orthop Res Soc, USA, Japan and Canada, p 164Google Scholar
  59. 59.
    Shen YP, Rangayyan RM, Bell GD, Frank CB, Zhang YT, Ladly KO (1995) Localization of knee joint cartilage pathology by multichannel vibroarthrography. Med Eng Phys 17(8):583–594CrossRefGoogle Scholar
  60. 60.
    Steindler A (1937) Auscultation of joints. J Bone Joint Surg 19(1):121–136Google Scholar
  61. 61.
    Szabo E, Danis L, Torok Z (1972) Examination of the acoustic phenomena observed in the knee. Traumatologia 15(2):118–127Google Scholar
  62. 62.
    Tavathia S, Rangayyan RM, Frank CB, Bell GD, Ladly KO, Zhang YT (1992) Analysis of knee vibration signals using linear prediction. IEEE Trans Biomed Eng 39(9):959–970CrossRefGoogle Scholar
  63. 63.
    Umapathy K, Krishnan S (2006) Modified local discriminant bases algorithm and its application in analysis of human knee joint vibration signals. IEEE Trans Biomed Eng 53(3):517–523CrossRefGoogle Scholar
  64. 64.
    Zhang YT, Frank CB, Rangayyan RM, Bell GD (1992) Mathematical modeling and spectrum analysis of the physiological patello-femoral pulse train produced by slow knee movement. IEEE Trans Biomed Eng 39(9):971–979CrossRefGoogle Scholar
  65. 65.
    Zhang YT, Rangayyan RM, Frank CB, Bell GD (1994) Adaptive cancellation of muscle contraction interference from knee joint vibration signals. IEEE Trans Biomed Eng 41(2):181–191CrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2007

Authors and Affiliations

  1. 1.Department of Electrical and Computer Engineering Schulich School of Engineering2500 University Dr. NW University of CalgaryCalgaryCanada
  2. 2.School of Information EngineeringBeijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations