Volume 2, Issue 3, September 2017, Page: 95-102
Diagnosing Knee Osteoarthritis Using Artificial Neural Networks and Deep Learning
Jean de Dieu Uwisengeyimana, Department of Electrical and Electronics Engineering, Cukurova University, Adana, Turkey; Department of Electrical and Electronics Engineering, University of Rwanda, Kigali, Rwanda
Turgay Ibrikci, Department of Electrical and Electronics Engineering, Cukurova University, Adana, Turkey
Received: Jan. 24, 2017;       Accepted: Feb. 18, 2017;       Published: Mar. 29, 2017
DOI: 10.11648/j.bsi.20170203.11      View  2477      Downloads  208
Among various medical diagnostic tests performed to identify osteoarthritis in the knee, most of them are invasive and expensive. Therefore, in this study, another methodology for diagnosing osteoarthritis in the knee in a more qwick, non-invasive and cheap manner was proposed. For that purpose, surface electromyography signals recorded from the four muscles surrounding the knee, the recording of the flexion degree in the knee and pattern recognition algorithms were used. The datasets of this experiment comprised 22 subjects among whom 11 subjects had normal knee and other 11 Subjects had an osteoarthritis-affected knee. The total sample size was 1, 048, 576 samples and were processed using segments of overlapping-windows of 5000 samples. Time-series features were then extracted from each segment and were used to train, test and validate 7 different learning classifiers and 7 variants of deep learning networks. In this study, the best performance measure of 99.5% was achieved by multilayer perceptron. Quadratic support vector machine and complex tree performed as well with accuracy of 99.4% and 98.3% respectively. In contrast, the use of deep learning networks which were investigated over a wide range of hidden size of the sparse autoencoders, showed accuracy of 86.6% with final softmax layer and accuracy of 91.3% by replacing the final softmax layer with k-nearest neighbour. By comparison, artificial neural networks outperformed deep learning networks and it is therefore concluded that the knee pathology can be diagnosed more effeciently and automatically using surface electromyography signals and artificial neural network algorithms.
Diagnosis, Electromyography, Deep Learning, Feature Extraction, Artificial Neural Network
To cite this article
Jean de Dieu Uwisengeyimana, Turgay Ibrikci, Diagnosing Knee Osteoarthritis Using Artificial Neural Networks and Deep Learning, Biomedical Statistics and Informatics. Vol. 2, No. 3, 2017, pp. 95-102. doi: 10.11648/j.bsi.20170203.11
Copyright © 2017 Authors retain the copyright of this article.
This article is an open access article distributed under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
McAlindon, T. E., Bannuru, R. R., Sullivan, M. C., Arden, N. K., Berenbaum, F., Zeinstra, S. M. B., Hawker, G. A., Henrotin, Y., Hunter, D. J., Kawaguchi, H., Kwoh, K., Lohmander, S., Rannou, F., Roos, E. M., Underwood, M. (2014). OARSI Guidelines for the non-surgical management of knee osteoarthritis. Osteoarthritis and Cartilage. Volume, 22: Pages, 363-388. DOI: http://dx. doi. org/ 10.1016/j. joca.2014.01.003.
Teitel, A. D. and Zieve, D. (2010). Osteoarthritis. MedlinePlud Medical Encycolpedia. National Institutes of Health. Last updated: Sept 26, 2011.
Centeno, C. J., Pitts, J., Sayegh, H. A., Freeman, M. D. (2015). Anterior cruciate ligament tears treated with percutaneous injection of autologous bone marrow nucleated cells: a case series. Journal of Pain Research. Volume, 8: Pages, 437–447. Doi: 10.2147/JPR. S86244.
Robert, E. M., Stephen, J. M., Marsha, E. M., Angelo, J. C., Matthew, D. (2008). Management of the Patient with an ACL/MCL Injured Knee. N Am J Sports Phys Ther. Volume, 3 (4): Pages, 204–211.
Shamir, L., Ling, S. M., Scott, W. W., Bos, A., Orlov, N., MacUra, T. J., Eckley, D. M., Ferrucci, L., Goldberg, I. G. (2009). Knee X-ray image analysis method for automated detection of Osteoarthritis. IEEE transactions on bio-medical engineering. 2009; 56 (2): 407-415. doi: 10.1109/TBME.2008.2006025.
Bedson, J., Jordan, K., Croft, P. (2003). How do GPs use x-rays to manage chronic knee pain in the elderly? A case study. Ann Rheum Dis. Volume, 62: Page, 450–454. Available at www.annrheumdis.com.
Eckstein, F., Burstein, D., Link, T. M. (2006). Quantitative MRI of cartilage and bone: degenerative changes in osteoarthritis. NMR Biomed. Volume, 19 (7): 822-54. DOI: 10.1002/nbm.1063
Peterfy, C. and Kothari, M. (2006). Imaging osteoarthritis: magnetic resonance imaging versus x-ray. Curr Rheumatol Rep. Volume 8. (1): Pages, 16-21.
Ferris, D. P., Gordon, K. E., Sawicki, G. S., Peethambaran, A. (2006). An improved powered ankle–foot orthosis using proportional myoelectric control. Gait & Posture, Volume 23, Issue 4, 2006, Pages 425–428. http://dx. doi. org/10.1016/ j. gaitpost.
Gazzoni, M. (2010), Multichannel surface electromyography in ergonomics: Potentialities and limits. Hum. Factors Man. Volume, 20: Pages, 255–271. Doi: 10.1002/hfm.20219.
Jefferson, F. L., Debora, C., Fabia, M., Marcelo, L. T., Claudia, T. C. (2012). Evaluating the Electromyographical Signal During Symmetrical Load Lifting. Applications of EMG in Clinical and Sports Medicine. DOI: 10.5772/25732.
Goen, A. (2014). Classification of EMG Signals for Assessment of Neuromuscular Disorders. International Journal of Electronics and Electrical Engineering Vol. 2, No. 3.
Reaz, B. I., Hussain, M. S., Yasin, M. F. (2006) Techniques of EMG signal analysis: Detection, processing, classification and applications, Biol. Proced. Volume, 8 (1): Pages, 11-35.
Gonzalez, M. H., Hernandez, G. M., Sotelo, J. R., Sanchez, O. A. (2015). Knee functional state classification using surface electromyographic and goniometric signals by means artificial neural networks. Ing. Univ. Volume, 19 (1): Pages, 51-66 http://dx. doi. org/ 10.11144/Javeriana. iyu19-1. kfsc.
Sanchez, O. F. A., Sotelo, J. L. R., Gonzales, M. H., Hernandez, G. A. M. (2014). EMG dataset in Lower Limb. UCI Machine Learning repository, avaiable: 2014-02-05.
Phinyomark, A., Phukpattaranont, P., Limsakul, C., Phothisonothai, M. (2011). Electromyography (Emg) Signal Classification Based On Detrended Fluctuation Analysis. Fluctuation and Noise Letters. Volume, 10 (3): Pages, 281-301. DOI: 10.1142/S0219477511000570.
Krishnan, N. C., Juillard, C., Colbry, D., Panchanathan, S. (2009). Recognition of hand movements using wearable accelerometers. JAISE, Volume, 1 (2): Pages, 143-155.
Tkach, D., Huang, H., Kuiken, T. A. (2010). Study of stability of time-domain features for electromyographic pattern recognition. Journal of NeuroEngineering and Rehabilitation. Volume, 7 (21). doi: 10.1186/1743-0003-7-21.
Hamedi, M., Salleh, S. H., Noor, A. M., Swee, T. T., Afizam, I. K. (2012). comparison of Different Time-domain Feature Extraction Methods on Facial Gestures' EMGs. Progress In Electromagnetics Research Symposium Proceedings, KL, MALAYSIA, 1897-1900.
Li, G. (2011). Electromyography Pattern-Recognition-Based Control of Powered Multifunctional Upper-Limb Prostheses, Advances in Applied Electromyography, Prof. Joseph Mizrahi (Ed.), InTech, DOI: 10.5772/22876.
MATLAB, Statistics and Machine Learning Toolbox Release 2015b, The MathWorks, Inc., Natick, Massachusetts, United States.
Gales, M. (2015). Statistical Pattern Processing. University of Cambridge Engineering Part IIB. http://mi. eng. cam. ac. uk/~mjfg/local/4F10/lect6. pdf
Koo, J. Y., Lee, Y., Kim, Y., Park, C. (2008). Representation of the Linear Support Vector Machine. Journal of Machine Learning Research. Volume, 9 (2008): Pages, 1343-1368.
Yeh, C. (2015). Support Vector Machines for classification. Methods and Theory. Available at http://efavdb.com/svm-classification/
Chamasemani, F. F. and Singh, Y. P. (2011). Multi-class Support Vector Machine (SVM) Classifiers- An Application in Hypothyroid Detection and Classification. Bio-Inspired Computing: Theories and Applications (BIC-TA).
Jurafsky, D. and Martin, J. H. (2016). Logistic Regression. Speech and Language Processing. Draft of November 7, 2016.
Korkmaz, M., Güney, S., Yiğîter, Ş. Y. (2011). The Importance Of Logistic Regressıon Implementations In The Turkish Livestock Sector and Logistic Regression Implementations/Fields. J. Agric. Fac. Hr. U. Volume 16 (2): Pages, 25-36.
Mandelkow, H., Zwart, J. A. D., Duyn, J. H. (2016). Linear Discriminant Analysis Achieves High Classification Accuracy for the bold fMRI Response to Naturalistic Movie Stimuli. Front Hum Neurosci. Volume: 10: Page 128. doi: 10.3389/fnhum.2016.00128.
Sewaiwar, P. and Verma, K. K. (2015). Comparative Study of Various Decision Tree Classification Algorithm Using WEKA. International Journal of Emerging Research in Management &Technology. ISSN: 2278-9359, Volume-4, Issue-10.
Patel, N. and Singh, D. (2015). An Algorithm to Construct Decision Tree for Machine Learning based on Similarity Factor. International Journal of Computer Applications, Volume 111 – No 10.
Imandoust, S. B. and Bolandraftar, M. (2013). Application of k-Nearest Neighbor (k-NN) Approach for Predicting Economic Events: Theoretical Background. Int. Journal of Engineering Research and Applications. Volume, 3 (5): Pages, 605-610.
Baldi, P. (2012). Autoencoders, Unsupervised Learning, and Deep Architectures. JMLR: Workshop and Conference Proceedings. Volume, 27: Pages, 37–50.
Deng, L. and Yu, D. (2014). Deep Learning: Methods and Applications. Foundations and Trends in Signal Processing. Volume, 7 (3-4): Pages, 1–199. doi: 10.1561/2000000039.
Schmidhuber, J. (2015). Deep Learning in Neural Networks: An Overview. Neural Networks. Volume, 61: Pages, 85–117. Available at doi: 10.1016/j.neunet.2014.09.003.
Hinton, G. E., Osindero, S., Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural computation. Volume, 18 (7): Pages, 1527-1554.
Bengio, Y. (2009). Learning Deep Architectures for AI. Foundations and Trends in Machine Learning. Volume, 2 (1): Pages, 1-127. http://dx. doi. org/ 10.1561/2200000006.
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H. (2007). Greedy layer-wise training of deep networks. In Advances in Neural Information Processing Systems.
Rumelhart, D. E., Hinton, G. E., Williams, R. J. (1986). Learning Representations By Back-Propagating Errors. Nature. Volume 323: Pages, 533 – 536. Doi: 10.1038/323533a0.
Erhan, D., Bengio, Y., Courville, A., Manzagol, P. A., Vincent, P. (2010). Why Does Unsupervised Pre-training Help Deep Learning?. Journal of Machine Learning Research. Volume, 11 (2010): Pages, 625-660.
De Luca, C. J., Gilmore, L. D, Kuznetsov, M., Roy, S. H. (2010). Filtering the surface EMG signal: Movement artifact and baseline noise contamination. Journal of Biomechanics. Volume, 43 (2010): Pages, 1573–1579. Doi: 10.1016/j.jbiomech.2010.01.027.
Matthias, K. (2012). Performance Measures in Binary Classification. International Journal of Statistics in Medical Research. Volume, 1: Pages, 79-81.
Rotello, C. M. and Chen, T. (2016). ROC curve analyses of eyewitness identification decisions: An analysis of the recent debate. Cognitive Research: Principles and Implications 2016 1: 10. DOI: 10.1186/s41235-016-0006-7.
Majnik, M. and Bosnic´, Z. (2013). ROC analysis of classifiers in machine learning: A survey. Intelligent Data Analysis 17, 531–558. DOI 10.3233/IDA-130592.
Wright, S. (2009). Optimization Algorithms in Support Vector Machines. computational Learning Workshop, University of Wisconsin-Madison, Chicago, June 2009.
LeCun, Y., Bengio, Y., Hinton, G. (2015). Review on deep learning. Nature, Volume, 521: Pages, 436-444. doi: 10.1038/nature14539.
Browse journals by subject