Abstract
Interpretation of vibrations or sound signals emitted from the patellofemoral joint during movement of the knee, also known as vibroarthrography (VAG), could lead to a safe, objective, and non-invasive clinical tool for early detection, localisation, and quantification of articular cartilage disorders. In this study with a reasonably large database of VAG signals of 90 human knee joints (51 normal and 39 abnormal), a new technique for adaptive segmentation based on the recursive least squares lattice (RLSL) algorithm was developed to segment the non-stationary VAG signals into locally-stationary components; the stationary components were then modelled autoregressively, using the Burg-Lattice method. Logistic classification of the primary VAG signals into normal and abnormal signals (with no restriction on the type of cartilage pathology) using only the AR coefficients as discriminant features provided an accuracy of 68.9% with the leave-one-out method. When the abnormal signals were restricted to chondromalacia patella only, the classification accuracy rate increased to 84.5%. The effects of muscle contraction interference (MCI) on VAG signals were analysed using signals from 53 subjects (32 normal and 21 abnormal), and it was found that adaptive filtering of the MCI from the primary VAG signals did not improve the classification accuracy rate. The results indicate that VAG is a potential diagnostic tool for screening for chondromalacia patella.
Similar content being viewed by others
References
Akay, M. (1994): ‘Biomedical Signal Processing’, (Academic Press, Inc., San Diego, CA)
Blodgett, W. E. (1902): ‘Auscultation of the knee joint’,Boston Med. Surg. J.,146(3), pp. 63–66
Chu, M. L., Gradisar, I. A., andZavodney, L. D. (1978): ‘Possible clinical application of a noninvasive monitoring technique of cartilage damage in pathological knee joints’,J. Clin. Eng.,3(1) pp. 19–27
Fischer, H. andJohnson, E. W. (1960): ‘Analysis of sounds from normal and pathologic knee joints’,in 3rd Int. Congr. Phys. Med, pp. 50–57
Frank, C. B., Rangayyan, R. M., andBell, G. D. (1990): ‘Analysis of knee sound signals for non-invasive diagnosis of cartilage pathology’,IEEE Eng. Med. Biol. Mag. pp. 65–68
Fukunaga, K. (1990), ‘Introduction to Statistical Pattern Recognition’, (Academic Press, Inc., San Diego, CA., 2nd edn)
Haykin, S. (1990): ‘Adaptive filter theory’ (Prentice-Hall, Englewood Cliffs, N.J., 2nd edn.)
Kang, W. J., Shiu, J. R., Cheng, C. K., Lai, J. S., Tsao, H. W., andKuo, T. S. (1995): ‘The application of cepstral coefficients and maximum likelihood method in EMG pattern recognition’,IEEE Trans. Biomed. Eng.,42(8) pp. 777–785
Kernohan, W. G., Barr, D. A., McCoy, G. F., andMollan, R. A. B. (1991): ‘Vibration arthrometry in assessment of knee disorders: the problem of angular velocity’,J. Biomed. Eng.,13, pp. 35–38
Krishnan, S. (1996): ‘Adaptive filtering, modeling, and classification of knee joint vibroarthrographic signals’, Master’s thesis, Dept. of Electrical and Computer Engineering, The University of Calgary, Calgary, Alberta, Canada
Kulund, D. N. (1988): ‘The Injured Athlete’, (J. B. Lippincott Company, Philadelphia, PA, 2nd edn.)
Ladly, K. O. (1992): ‘Analysis of patellofemoral joint vibration signals’ Master’s thesis, Dept. of Medical Science, The University of Calgary, Calgary, Alberta, Canada
Ladly, K. O., Frank, C. B., Bell, G. D., Zhang, Y. T., andRangayyan, R. M. (1993): ‘The effect of external loads and cyclic loading on normal patellofemoral joint signals’,Def. Sci. J. (India),43 pp. 201–210
McCoy, G. F., McCrea, J. D., Beverland, D. E., Kernohan, W. G., andMollan, R. A. B. (1987). ‘Vibration arthrography as a diagnostic aid in diseases of the knee’,J. Bone Joint Surg.,69-B(2) pp. 288–293
Mollan, R. A. B., McCullagh, G. C., andWilson, R. I. (1982): ‘A critical appraisal of auscultation of human joints’,Clin. Orthopaedics Related Res.,170 pp. 231–237
Moussavi, Z. M. K., Rangayyan, R. M., Bell, G. D., Frank, C. B., Ladly, K. O., andZhang, Y. T. (1996): ‘Screening of vibroarthrographic signals via adaptive segmentation and linear prediction modeling’,IEEE Trans. Biomed. Eng.,43, pp. 15–23.
Nagata, Y. (1988): ‘Joint-sounds in gonoarthrosis—clinical application of phonoarthrography for the knee’,J. UOEH,10(1) pp. 47–58
Shen, Y., Rangayyan, R. M., Bell, G. D., Frank, C. B., Zhang, Y. T., andLadly, K. O. (1995): ‘Localization of knee joint cartilage pathology by multichannel vibroarthrography’,Med. Eng. Phys.,17(8), 583–594
SPSS (1990a): ‘SPSS Advanced Statistics User’s Guide’, (SPSS Inc., Chicago, IL)
SPSS (1990b): ‘SPSS Base System User’s Guide’, (SPSS Inc., Chicago, IL)
Tavathia, S., Rangayyan, R. M., Frank, C. B., Bell, G. D., Ladly, K. O., andZhang, Y. T. (1992): ‘Analysis of knee vibration signals using linear prediction’,IEEE Trans. Biomed. Eng.,39(9) pp. 959–970
Zhang, Y. T., Frank, C. B., Rangayyan, R. M., andBell, G. D. (1992): ‘Mathematical modeling and spectrum analysis of the physiological patello-femoral pulse train produced by slow knee movement’,IEEE Trans. Biomed. Eng.,39 (9) pp. 971–979
Zhang, Y. T., Rangayyan, R. M., Frank, C. B., Bell, G. D., andLadly, K. O. (1994a): ‘Vibroarthrographic (VAG) signal analysis for non-invasive diagnosis of knee joint disorders’,Med. Life Sci. Eng. (India),13 pp. 146–160
Zhang, Y. T., Rangayyan, R. M., Frank, C. B., andBell, G. D. (1994b): ‘Adaptive cancellation of muscle contraction interference from knee joint vibration signals’,IEEE Trans. Biomed. Eng.,41(2) pp. 181–191
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Krishnan, S., Rangayyan, R.M., Bell, G.D. et al. Adaptive filtering, modelling and classification of knee joint vibroarthrographic signals for non-invasive diagnosis of articular cartilage pathology. Med. Biol. Eng. Comput. 35, 677–684 (1997). https://doi.org/10.1007/BF02510977
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02510977