An enhanced algorithm for knee joint sound classification using feature extraction based on time-frequency analysis

Vibroarthrographic (VAG) signals, generated by human knee movement, are non-stationary and multi-component in nature and their time-frequency distribution (TFD) provides a powerful means to analyze such signals. The objective of this paper is to improve the classification accuracy of the features, obtained from the TFD of normal and abnormal VAG signals, using segmentation by the dynamic time warping (DTW) and denoising algorithm by the singular value decomposition (SVD). VAG and knee angle signals, recorded simultaneously during one flexion and one extension of the knee, were segmented and normalized at 0.5 Hz by the DTW method. Also, the noise within the TFD of the segmented VAG signals was reduced by the SVD algorithm, and a back-propagation neural network (BPNN) was used to classify the normal and abnormal VAG signals. The characteristic parameters of VAG signals consist of the energy, energy spread, frequency and frequency spread parameter extracted by the TFD. A total of 1408 segments (normal 1031, abnormal 377) were used for training and evaluating the BPNN. As a result, the average classification accuracy was 91.4 (standard deviation +/-1.7) %. The proposed method showed good potential for the non-invasive diagnosis and monitoring of joint disorders such as osteoarthritis.

[1]  G. Wittum,et al.  Adaptive filtering , 1997 .

[2]  H. Genant,et al.  Whole-Organ Magnetic Resonance Imaging Score (WORMS) of the knee in osteoarthritis. , 2004, Osteoarthritis and cartilage.

[3]  Rangaraj M. Rangayyan,et al.  Adaptive time-frequency analysis of knee joint vibroarthrographic signals for noninvasive screening of articular cartilage pathology , 2000, IEEE Transactions on Biomedical Engineering.

[4]  Ju-Hong Lee,et al.  Vibration arthrometry in the patients with failed total knee replacement , 2000, IEEE Trans. Biomed. Eng..

[5]  Ju-Hong Lee,et al.  Vibration arthrometry in patients with knee joint disorders , 2000, IEEE Trans. Biomed. Eng..

[6]  Rangaraj M. Rangayyan,et al.  Time-frequency signal feature extraction and screening of knee joint vibroarthrographic signals using the matching pursuit method , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[7]  Rangaraj M. Rangayyan,et al.  Screening of knee-joint vibroarthrographic signals using statistical parameters and radial basis functions , 2008, Medical & Biological Engineering & Computing.

[8]  Zahra M. K. Maussavi,et al.  Screening of vibroarthrographic signals via adaptive segmentation and linear prediction modeling , 1996, IEEE Transactions on Biomedical Engineering.

[9]  Andrew H. Jazwinski,et al.  Adaptive filtering , 1969, Autom..

[10]  R.M. Rangayyan,et al.  Analysis of knee vibration signals using linear prediction , 1992, IEEE Transactions on Biomedical Engineering.

[11]  R. M. Rangayyan,et al.  Automatic de-noising of knee-joint vibration signals using adaptive time-frequency representations , 2006, Medical and Biological Engineering and Computing.

[12]  H. Yoshioka,et al.  Articular cartilage of knee: normal patterns at MR imaging that mimic disease in healthy subjects and patients with osteoarthritis. , 2004, Radiology.

[13]  R.M. Rangayyan,et al.  Parametric representation and screening of knee joint vibroarthrographic signals , 1997, IEEE Transactions on Biomedical Engineering.

[14]  R. Mollan,et al.  Vibration arthrography as a diagnostic aid in diseases of the knee. A preliminary report. , 1987, The Journal of bone and joint surgery. British volume.

[15]  Jianwen Luo,et al.  Savitzky-Golay smoothing and differentiation filter for even number data , 2005, Signal Process..

[16]  R. M. Rangayyan,et al.  Adaptive filtering, modelling and classification of knee joint vibroarthrographic signals for non-invasive diagnosis of articular cartilage pathology , 1997, Medical and Biological Engineering and Computing.

[17]  J F Prinz,et al.  Characterization of sounds emanating from the human temporomandibular joints. , 1996, Archives of oral biology.

[18]  Karthikeyan Umapathy,et al.  Modified local discriminant bases algorithm and its application in analysis of human knee joint vibration signals , 2006, IEEE Transactions on Biomedical Engineering.

[19]  R.M. Rangayyan,et al.  Adaptive cancellation of muscle contraction interference in vibroarthrographic signals , 1994, IEEE Transactions on Biomedical Engineering.

[20]  G.D. Bell,et al.  Mathematical modeling and spectrum analysis of the physiological patello-femoral pulse train produced by slow knee movement , 1992, IEEE Transactions on Biomedical Engineering.

[21]  I Van Breuseghem.  Ultrastructural MR imaging techniques of the knee articular cartilage: problems for routine clinical application. , 2004, European radiology.

[22]  Derrick J. Fluhme,et al.  Knee arthroscopy in the older patient , 2002 .

[23]  R M Rangayyan,et al.  Localization of knee joint cartilage pathology by multichannel vibroarthrography. , 1995, Medical engineering & physics.

[24]  Rangaraj M. Rangayyan,et al.  Analysis of knee joint sound signals , 1988, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[25]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[26]  Boualem Boashash,et al.  Time-Frequency Signal Analysis and Processing , 2002 .

[27]  Hamid Hassanpour.  A time-frequency approach for noise reduction , 2008, Digit. Signal Process..

[28]  Hamid Hassanpour,et al.  Improved SVD-Based Technique for Enhancing the Time-Frequency Representation of Signals , 2007, 2007 IEEE International Symposium on Circuits and Systems.