Screening of knee-joint vibroarthrographic signals using time and spectral domain features. (July 2021)

• Record Type: Journal Article
• Authors: Shidore, Mrunal M.; Athreya, Shreeram S.; Deshpande, Shantanu; Jalnekar, Rajesh
• Is Part Of: Biomedical signal processing and control. Volume 68(2021)
• Publication Date: 2021-07
• Subjects: Articular cartilage pathology -- Baseline wander removal -- Impulse factor -- Knee-joint -- Margin factor -- Mutual information -- Random forest classifier -- Shape factor -- Short-time Fourier transform -- Spectral flux -- Spectral slope -- Spectral mean -- Spectral peak -- Vibroarthrography; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102808
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: This work classifies knee-joint vibroarthrographic signals based on time and spectral domain features. Significant performance obtained without the use of complex time-frequency transformations. The proposed system also includes a feature selection mechanism to ensure accurate feature-space modelling of VAG data. This method works with lesser computational complexity and has the potential to be effectively deployed for early stage diagnosis of knee-joint conditions. Abstract: It has been determined that variations in vibroarthrographic (VAG) signal characteristics have a direct association with various diseases of the knee joints including degenerative and traumatic etiology. Several studies have proposed temporal and time-frequency parameters for the analysis and classification of VAG signals; however, very few statistical modelling methods have been explored to analyze distinctions in the spectral domain characteristics of VAG signals. The aim of our work is to classify VAG signals into normal and abnormal thus portraying knee health condition by proposing a novel set of features. Spectral domain transformations of VAG signals were derived using the short-time Fourier transform (STFT) approach to extract statistical characteristic features from VAG signals. Several time-domain statistical features; the mean and variance values of spectral domain features namely – spectral mean, peak, skewness, kurtosis, flux, and slope were utilized to express VAG signal fluctuations. Further, mutual information test, ANOVA F -test, and Chi-square test were used to select significant features and assess their effectiveness. Random forest, Gaussian Naive Bayes, and support vector machine (SVM) algorithms were used to perform signal pattern classification. The results showed that subjects with knee joint abnormalities possess higher values of spectral flux, spectral slope, and shape factor than healthy subjects. An overall classification accuracy of 89.23%, sensitivity of 87.09% and specificity of 91.18% were obtained using the random forest classifier trained with features selected by the mutual information test. The proposed system could effectively screen almost 94% of subjects accurately based on area under the ROC curve.