Noninvasive Detection And Auxiliary Diagnosis Of Knee Injury Lesions Based On VAG Signal Analysis

In daily activities of the human body,the knee is the most complex joint.The knee joint is fragile,easy to hurt or causing arthritis.Early diagnosis of knee joint disease can help doctors take some measures to prevent disease deterioration.The vibroarthrographic(VAG)signal is the vibration and contact friction generated by the knee joint during flexion and extension.It reflects the characteristics and status of chondromalacia,meniscal tears,osteoarthritis and other diseases,and it is gradually getting the attention of clinical medicine.In the present,the abnormal VAG signal screening of knee joint injury is studied.But the accuracy of classifying normal and abnormal signal is not high.It is not effective in distinguishing the degree of knee disease.More feature extraction methods are needed to improve the detection ability and classification of knee joint injuries.In this paper,the problems of VAG signal are studied.Firstly,in this paper,an improved denoising method combination ensemble empirical mode decomposition with wavelet threshold is proposed.According to traditional wavelet threshold function existing the shortcomings of bad continuity and constant deviation,improve wavelet threshold function,enhancing the denoising effect of wavelet threshold.This method is applied to the preprocessing of VAG signal,obtaining better signal to noise ratio and smaller mean square error.It makes the quality of VAG signal improved.Secondly,in this paper,the characteristics of normal and abnormal VAG signals are quantitatively analyzed according to the multifractal detrended fluctuation method.The features of the VAG signals are extracted,including the fractal scale exponent,the multifractal spectrum and extremum values,the generalized fractal dimension and the time-frequency information entropy.SVM is used to classify the normal and abnormal VAG signals,getting a high classification accuracy.Lastly,osteoarthritis of different degree has different characteristics in different frequencies.Frequency slice wavelet transform is applied to VAG signal suffering from osteoarthritis,reconstructing the signal in different frequency bands.Based on multifractal detrended fluctuation method,two new features are extracted,including the multifractal spectrum extremum values ratio and fractal scale exponent ratio.According to the range of values based on these feature parameters,differentiate the osteoarthritis of different degree.In the paper,normal and abnormal VAG signal is indentified and classified,obtaining higher classification accuracy.Osteoarthritis of Different grades can be distinguished effectively,which is very important for noninvasive detection and assistant diagnosis of knee joint injury.