Classification of Vibroarthrographic SignalsBased on PCNN-LSTM Neural Network
Yang Jia1, Qiu Tianshuang1#*, Liu Yupeng2
1(Faculty of Electronic Information and Electrical Engineering,Dalian University of Technology,Dalian 116024,Liaoning, China) 2(Zhongshan Hospital,Dalian University,Dalian 116001,Liaoning, China)
Abstract：The vibroarthrographic (VAG) signal is a sound of the knee joint during flexion and extension. VAG signal can be used to describe the health status of knee joint sensitively and objectively. Hence, it is often used in the detection of knee joint diseases. However, at present, classification accuracy of the normal and abnormal classification method of VAG signal is still low and not automated. The performance needs to be further improved. To solve this problem, in this paper, a classification algorithm of VAG signal based on improved convolutional neural network (PCNN-LSTM) was proposed. First, empirical mode decomposition (EMD) and wavelet transform are used to transform one-dimensional VAG signal into two-dimensional time-frequency characteristic spectrum, which was used as data set. Second, on the basis of CNN, the parallel CNN network structure was combined with LSTM neural network to form the PCNN-LSTM model, which could classify normal or abnormal VAG signals and realizd the automatic detection of knee joint health status. In this paper, the performances of the proposed algorithm were verified by the data set that composed of the real VAG signals collected by the acceleration sensor (181A02) and USB acquisition instrument (FSC812). The data set consisted of 654 samples, including 222 health data and 432 data of patients with knee diseases. Results showed that the classification accuracy of the proposed algorithm was 96.93%, the sensitivity was 100%, and the specificity was 95.56%. Compared with other algorithms, the proposed algorithm achieved better results, and realized the classification and recognition of VAG signals, which was of great significance for non-invasive detection and auxiliary diagnosis of knee joint diseases.
杨佳, 邱天爽, 刘宇鹏. 基于PCNN-LSTM神经网络的膝关节摆动信号分类识别[J]. 中国生物医学工程学报, 2021, 40(2): 129-136.
Yang Jia, Qiu Tianshuang, Liu Yupeng. Classification of Vibroarthrographic SignalsBased on PCNN-LSTM Neural Network. Chinese Journal of Biomedical Engineering, 2021, 40(2): 129-136.
[1] Chandrasekaran S, Ma D, Scarvell JM, et al. A review of the anatomical,biomechanical and kinematic findings of posterior cmciate ligament injury with respect to non-operative management [J].The Knee, 2012, 19(6): 738-745. [2] McCoy GF, McCrea JD, Beverland DE, et al. Vibration arthrography as a diagnostic aid in diseases of the knee- A Preliminary Report. [J] The Journal of Bone and Joint Surgery, 1987, 69(2): 288-293. [3] Wu Yunfeng, Knee Joint Vibroarthmgraphic Signal Processing and Analysis [M]. Heidelberg: Springer, 2014. [4] 徐一平, 邱天爽, 刘宇鹏. 基于VAG信号分析的无创膝关节损伤病变检测与辅助诊断[J].生物医学工程研究, 2018, 37(2): 233-237. [5] Rangayyan RM, Oloumi F, Wu YunFeng, et al. Fractal analysis of kneejoint vibroarthrographic signals via power spectral analysis[J]. Biomed Signal Proces, 2013,8(1):23-29. [6] Wu YunFeng, Chen Pinnan, Luo Xin, et al. Quantification of knee vibroarthrographic signal irregularity associated with patellofemoral joint cartilage pathology based on entropy and envelope amplitude measures[J]. Comput Methods Programs Biomed,2016,130:1-12. [7] Befrui N, Elsner J, Flesser A, et al. Detection and grading of knee joint cartilage defect using multi-class classification in vibroarthrography [J]. EPiC Series in Health Sciences, 2018,2: 6-10. [8] Tuan ChiuChing, Lu ChiHeng, Wu YiChao et al. Developmental screening system for patient vibration signals with knee disorder[J]. Applied Sciences, 2019, 9(5): 908. [9] Mollan RAB, Mccullagh GC, Wilson RI. A critical appraisal of auscultation of human joints [J]. Clinical Orthopaedics and Related Research, 1982,170:231-235. [10] Huang NE, Shen Z, Long SR, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proceedings of the Royal Society A: Mathematical Physical and Engineering Sciences, 1998, 454 (1971):903-995. [11] 程正兴.小波分析与应用实例[M]. 西安:西安交通大学出版社, 2006. [12] Nalband S, Valliappan CA. Time-frequency based feature extraction for the analysis of vibroarthographic signals [J]. Computers and Electrical Engineering. 2018, 69: 720-731. [13] Lecun Y, Botlou L, Bengio Y, et al.Gradient·based leaming applied to document recognition[J]. Proceedings of the IEEE, 1998.86(11): 2278-2324. [14] Gao X, Cai Y, Qiu C, et al.Retinal blood vessel segmentation based on the Gaussian matched filter and U-net[C]//2017 10th, International Congress on Image and Signal Processing, BioMedical Engineering and Informatics(CISP-BMEI). Shanghai:IEEE, 2017: 1-5. [15] Theodoridis S. Neuml networks and deep leaming [M]∥Machine Learning.Berlin:Springer,2015:875-936. [16] Shieh CS, Tseng CD, et al. Synthesis of vibroarthrographic signals in knee osteoarthritis diagnosis training[J]. BMC Research Notes,2016, 9:352-362. [17] Agastinose R, Jac F, Thomas RAJ, et al.Classification of normal and knee joint disorder vibroarthrographic signals using multifractals and support vector machines[J]. Biomedical Engineering: Applications, Basis and Communications, 2017, 29(3):1750016-1750025. [18] Poornapushpakala S, Subramoniam M. Assessment of cartilage disorder in knee with VAG signals using wavelet transform and neural network[C]∥2017 International Conference on Intelligent Computing and Control Systems (ICICCS). Madural:IEEE, 2017: 998-1001. [19] Befrui N, Elsner J, Flesser A, et al. Vibroarthrography for early detection of knee osteoarthritis using normalized frequency features[J]. Medical & Biological Engineering & Computing, 2018,56(8):1499-1514. [20] Krecisz K, Baczkowicz D, Analysis and multiclass classifification of pathological knee joints using vibroarthrographic signals[J]. Computer Methods and Programs in Biomedicine, 2018,154:37-44. [21] Liu Kaizhi,Luo Xin,Yang Shanshan, et al. Classification of knee joint vibroarthrographic signals using k-nearest neighbor algorithm [C]∥2014 IEEE 27th Conference on Electrical and Computer Engineering(CCECE). Toronto: IEEE, 2014:1-4. [22] 徐一平,邱天爽,刘宇鹏. 基于多重分形的膝关节摆动信号特征提取与分类[J].信号处理, 2017, 33(3): 383-388.
