CLASSIFICATION OF AMYOTROPHIC LATERAL SCLEROSIS AND HEALTHY ELECTROMYOGRAPHY SIGNALS BASED ON TRANSFER LEARNING

Year 2018, Volume: 8 Issue: 2, 179 - 185, 29.12.2018

Abdulkadir Şengür , Ümit Budak , Yaman Akbulut

https://doi.org/10.36222/ejt.498095

Cited By: 2

Abstract

This paper investigates the usage of
transfer learning in amyotrophic lateral sclerosis (ALS) disease detection. ALS
is a dangerous disease which affects the nerve cells in brain and spinal cord.
Electromyogram (EMG) is an important measure for analysing of the electrical
level of the muscles. EMG based early ALS disease detection system helps the
physicians and patients. The proposed work uses EMG signals in discrimination
of the ALS and healthy persons. The EMG signals are initially segmented with a
overlapped window and each segment is converted to the spectrogram images. The
obtained spectrogram images are resized and fed into the pre-trained
convolutional neural networks model. The pre-trained model is fine-tuned with
the problem at hand. The R002 dataset which is obtained from www.emglab.net is
used during the experimental works. Accuracy, sensitivity and specificity
measures are used to evaluate the obtained achievement. According to these
measures, 97.70% accuracy, 97.97% sensitivity, and 97.29% specificity values
are recorded. We further compare the obtained results with some of the existing
results that were obtained on the same dataset. The comparisons show that
proposed method is outperformed.

Keywords

EMG signals, ALS disease, Transfer learning, Convolutional neural networks, Pre-trained models

References

• Fuglsang‐Frederiksen, A., The utility of interference pattern analysis, Muscle & Nerve: Official Journal of the American Association of Electrodiagnostic Medicine, 23(1), 2000, pp. 18-36.
• Fukuda, T. Y. et al., Root mean square value of the electromyographic signal in the isometric torque of the quadriceps, hamstrings and brachial biceps muscles in female subjects, Journal of Applied Research, 10(1), 2010, pp. 32-39.
• Fattah, S. A. et al., Evaluation of different time and frequency domain features of motor neuron and musculoskeletal diseases, Int. J. Comput. Appl., 43(23), 2012, pp. 34–40.
• Doulah, A. B. M. S. U., Fattah, S. A., Neuromuscular disease classification based on mel frequency cepstrum of motor unit action potential, In Electrical Engineering and Information & Communication Technology (ICEEICT), 2014 International Conference on IEEE, pp. 1-4.
• Mishra, V. K. et al., Analysis of ALS and normal EMG signals based on empirical mode decomposition, IET Science, Measurement & Technology, 10(8), 2016, pp. 963-971.
• Sengur, A. et al., DeepEMGNet: an application for efficient discrimination of ALS and normal EMG signals, T. Bvrezina, R. Jabłoński (Eds.), Mechatronics 2017 Recent Technol. Sci. Adv., Springer International Publishing, Cham (2018), pp. 619-625, 10.1007/978-3-319-65960-2_77.
• Fattah, S. A. et al., Identification of motor neuron disease using wavelet domain features extracted from EMG signal, In Circuits and Systems (ISCAS), International Symposium on IEEE, 2013, pp. 1308-1311.
• Pal, P. et al., Feature extraction for evaluation of Muscular Atrophy, In Computational Intelligence and Computing Research (ICCIC), International Conference on IEEE, December 2010, pp. 1-4.
• Merlo, A. et al., A fast and reliable technique for muscle activity detection from surface EMG signals, IEEE Transactions on Biomedical Engineering, 50(3), 20113, pp. 316-323.
• Sengur, A. et al., Classification of amyotrophic lateral sclerosis disease based on convolutional neural network and reinforcement sample learning algorithm, Health information science and systems, 5(1), 2017, 9. Doi: 10.1007/s13755-017-0029-6
• Orenstein, E. C., Beijbom, O., Transfer Learning and Deep Feature Extraction for Planktonic Image Data Sets, In Applications of Computer Vision (WACV), Winter Conference on IEEE, March 2017, pp. 1082-1088.
• Krizhevsky, A. et al., Imagenet classification with deep convolutional neural networks, In Advances in neural information processing systems, 2012, pp. 1097-1105.
• Nikolic, M., Detailed analysis of clinical electromyography signals: EMG decomposition, findings and firing pattern analysis in controls and patients with myopathy and amyotrophic lateral sclerosis, 2001, Doctoral dissertation.
• Simonyan, K., Zisserman, A., Very deep convolutional networks for large-scale image recognition, 2014, arXiv preprint arXiv:1409.1556.
• Deniz, E., et al., Transfer learning based histopathologic image classification for breast cancer detection, Health information science and systems, 2018, 6(1), 18.
• Detailed analysis of clinical electromyography signals EMG decomposi-tion, findings and firing pattern analysis in controls and patients with myopathy and amy-trophic lateral sclerosis. Ph.D. Thesis, Faculty of Health Science, University of Copenhagen.