Boosting-based decision tree for improved screening of vibroarthrographic signals

Many diseases affect the knee joint, such as Chondromalica Pattelle (CP), which is the most bearing joint in the body. X-ray, MRI and arthroscopy are currently used for screening knee joint diseases. However, some of these techniques may be costly, dangerous as well as some of them being poor in functional resolution. On the other hand, researchers have shown the existence of variation in Vibroarthrography signal, recorded from the knee joint surface, between the normal and abnormal knee. VAG is the recording of vibrations generated from the knee joint surface, during flexion and extension, which may offer a tool of non-invasive screening for knee joint diseases. The main aim of this paper is to improve the VAG signal classification to diagnose CP. Simple time-domain features were used for the first time alongside boosting-based Decision Tree classifier. The area under the receiver operating characteristic curves was 0.816 which shows the effectiveness of the proposed features and boosting-based classifier compared to other methods.

[1]  Petia Radeva,et al.  On the assessment of texture feature descriptors in intravascular ultrasound images: a boosting approach to a feasible plaque classification. , 2005, Studies in health technology and informatics.

[2]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[3]  Tingting Mu,et al.  Screening of knee-joint vibroarthrographic signals using the strict 2-surface proximal classifier and genetic algorithm , 2008, Comput. Biol. Medicine.

[4]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[5]  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.

[6]  Yoav Freund,et al.  Large Margin Classification Using the Perceptron Algorithm , 1998, COLT.

[7]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[8]  Keo-Sik Kim,et al.  Feature extraction of knee joint sound for non-invasive diagnosis of articular pathology , 2008, 2008 IEEE Biomedical Circuits and Systems Conference.

[9]  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.

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

[11]  R.N. Scott,et al.  A new strategy for multifunction myoelectric control , 1993, IEEE Transactions on Biomedical Engineering.

[12]  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.

[13]  Rangaraj M. Rangayyan,et al.  Screening of knee-joint vibroarthrographic signals using probability density functions estimated with Parzen windows , 2010, Biomed. Signal Process. Control..

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

[15]  Pat Langley,et al.  Estimating Continuous Distributions in Bayesian Classifiers , 1995, UAI.

[16]  Pierre Baldi,et al.  Assessing the accuracy of prediction algorithms for classification: an overview , 2000, Bioinform..

[17]  Kevin B. Englehart,et al.  A robust, real-time control scheme for multifunction myoelectric control , 2003, IEEE Transactions on Biomedical Engineering.

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