Ali ERFANI SHOLEYAN, Seyed Kamaledin SETAREHDAN, Fereidoun NOWSHIRAVAN RAHATABAD

Sleep staging with deep structured neural net using Gabor layer and data augmentation

Slow wave sleep (SWS) and rapid eye movement (REM) are two of the most important sleep stages that are considered in many studies. Detection of these two sleep stages will help researchers in many applications to detect sleeprelated diseases and disorders and also in many fields of neuroscience studies such as cognitive impairment and memory consolidation. Since manual sleep staging is time-consuming, subjective, and expensive; designing an efficient automatic sleep scoring system will overcome some of these difficulties. Many studies have proposed automatic sleep staging systems with different methods. In recent years, deep learning methods show their potential in different applications. In this study, we propose SWS and REM detection system by using a deep neural network. In the proposed system we use a kernel-based layer to get the system closer to the manual scoring approach. Also, we use a new method for augmenting EEG signals to prevent overfitting the network. The results show the efficiency of the designed system in SWS and REM detection.

PDF

___

[1] Strine TW, Chapman DP. Associations of frequent sleep insufficiency with health-related quality of life and health behaviors. Sleep Medicine 2005; 6: 23-27.
[2] Partinen M. In handbook of clinical neurology 2011; 98: 275-314.
[3] Reuveni H, Tarasiuk A, Wainstock T, Ziv A, Elhayany A et al. Awareness level of obstructive sleep apnea syndrome during routine unstructured interviews of a standardized patient by primary care physicians. Sleep 2004; 27: 1518- 1525.
[4] Dafna E, Tarasiuk A, Zigel Y. Sleep staging using nocturnal sound analysis. Science Report 2018; 8: 13474.
[5] AASM. The AASM manual for the scoring of sleep and associated events-rules. Terminology and Technical Specifications. American Academy of Sleep Medicin. Chicago, 2007.
[6] Rechtschaffen A, Kales A. A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects. UCLA Brain Information Service/Brain Research Institute, Los Angeles, 1968.
[7] Jamieson AO, Becker PM. Management of the 10 most common sleep disorders. American Family Physician 1992; 45: 1262-1268.
[8] Koo BB, Patel SR, Strohl K, Hoffstein V. Rapid eye movement-related sleep-disordered breathing: influence of age and gender. Chest 2008; 134: 1156-1161.
[9] Schenck CH, Hurwitz TD, Mahowald MW. REM sleep behaviour disorder: an update on a series of 96 patients and a review of the world literature. Journal of Sleep Research 1993; 2: 224-231.
[10] Vendette M, Gagnon JF, Decary A, Massicotte-Marquez J, Postuma RB et al. REM sleep behavior disorder predicts cognitive impairment in Parkinson disease without dementia. Neurology 2007; 69: 1843-1849.
[11] Gottesmann C, Gottesman I. The neurobiological characteristics of rapid eye movement (REM) sleep are candidate endophenotypes of depression, schizophrenia, mental retardation and dementia. Progress in Neurobiology 2007; 81: 237-250.
[12] Van Cauter E, Spiegel K, Tasali E, Leproult R. Metabolic consequences of sleep and sleep loss. Sleep Medicine 2008; 9: 23-28.
[13] Van Cauter E, Leproult R, Plat L. Age-related changes in slow wave sleep and REM sleep and relationship with growth hormone and cortisol levels in healthy men. Journal of the American Medical Association 2000; 84: 861-868.
[14] Majde JA, Krueger JM. Links between the innate immune system and sleep. Allergy and Clinical Immunology 2005; 116: 1188-1198.
[15] Tasali E, Leproult R, Ehrmann DA, Van Cauter E. Slow-wave sleep and the risk of type 2 diabetes in humans. Proceedings of the National Academy of Sciences 2008; 105: 1044-1049.
[16] Diekelmann S, Born J. The memory function of sleep. Nature Reviews Neuroscience 2010; 11: 114-126.
[17] Kyung Lee E, Douglass AB. Sleep in psychiatric disorders: where are we now?. The Canadian Journal of Psychiatry 2010; 55: 403-412.
[18] Fung MM, Peters K, Redline S, Ziegler MG, Ancoli-Israel S et al. Decreased slow wave sleep increases risk of developing hypertension in elderly men. Hypertension 2011; 58: 596-603.
[19] Park HJ,Oh JS, Jeong DU, Park KS. Automated sleep stage scoring using hybrid rule-and case-based reasoning. Computers and Biomedical Research 2000; 33: 330-349.
[20] Agarwal R, Gotman J. Computer-assisted sleep staging. IEEE Transactions on Biomedical Engineering 2001; 48: 1412-1423.
[21] Caffarel J, Gibson GJ, Harrison JP, Griffiths CJ, Drinnan MJ. Comparison of manual sleep staging with automated neural network-based analysis in clinical practice. Medical and Biological Engineering and Computing 2006; 44: 105-110.
22] Poree F, Kachenoura A, Gauvrit H, Morvan C, Carrault G et al. Blind source separation for ambulatory sleep recording. IEEE Transactions on Information Technology in Biomedicine 2006; 10: 293-301.
[23] Tagluk ME, Sezgin N, Akin M. Estimation of sleep stages by an artificial neural network employing EEG, EMG and EOG. Journal of Medical Systems 2010; 34: 717-725.
[24] Liang SF, Kuo CE, Hu YH, Cheng YS. A rule-based automatic sleep staging method. Journal of Neuroscience Methods 2012; 205: 169-176.
[25] Pan ST, Kuo CE, Zeng JH, Liang SF. A transition-constrained discrete hidden Markov model for automatic sleep staging. Biomedical Engineering Online 2012; 11: 52.
[26] Yetton BD, Niknazar M, Duggan KA, McDevitt EA, Whitehurst LN, Sattari N, Mednick SC. Automatic detection of rapid eye movements (REMs): A machine learning approach. Journal of Neuroscience Methods 2016; 256: 72-82.
[27] Diekelmann S, Wilhelm I, Born J. The whats and whens of sleep-dependent memory consolidation. Sleep Medicine Reviews 2009; 13: 309-321.
[28] Bellesi M, Riedner BA, Garcia-Molina GN, Cirelli C, Tononi G. Enhancement of sleep slow waves: underlying mechanisms and practical consequences. Frontiers in Systems Neuroscience 2014; 8: 208.
[29] Huber R, Ghilardi MF, Massimini M, Ferrarelli F, Riedner BA et al. Arm immobilization causes cortical plastic changes and locally decreases sleep slow wave activity. Nature Neuroscience 2006; 9: 1169-1176.
[30] Ngo HV, Claussen JC, Born J, Molle M. Induction of slow oscillations by rhythmic acoustic stimulation. Journal of Sleep Research 2013; 22: 22-31.
[31] Tononi G, Riedner BA, Hulse BK, Ferrarelli F, Sarasso S. Enhancing sleep slow waves with natural stimuli. Medicamundi 2010; 54: 82-88.
[32] Ngo HV, Miedema A, Faude I, Martinetz T, Molle M et al. Driving sleep slow oscillations by auditory closed-loop stimulation–a self-limiting process. Journal of Neuroscience 2015; 35: 6630-6638.
[33] Golrou A, Sheikhani A, Nasrabadi AM, Saebipour MR. Enhancement of Sleep Quality and Stability Using Acoustic Stimulation During Slow Wave Sleep. International Clinical Neuroscience Journal 2018.; 5:126-134.
[34] Papalambros NA, Santostasi G, Malkani RG, Braun R, Weintraub S et al. Acoustic enhancement of sleep slow oscillations and concomitant memory improvement in older adults. Frontiers in Human Neuroscience 2017; 11: 1-14.
[35] Ong JL, Lo JC, Chee NI, Santostasi G, Paller KA et al. Effects of phase-locked acoustic stimulation during a nap on EEG spectra and declarative memory consolidation. Sleep Medicine 2016; 20: 88-97.
[36] Leminen MN, Virkkala J, Saure E, Paajanen T, Zee PC et al. Enhanced memory consolidation via automatic sound stimulation during non-REM sleep. Sleep 2017; 40.
[37] Schabus M, Dang-Vu T, Heib D, Boly M, Desseilles M et al. The fate of incoming stimuli during NREM sleep is determined by spindles and the phase of the slow oscillation. Frontiers in Neurology 2012; 3: 1-11.
[38] Lustenberger C, Boyle MR, Alagapan S, Mellin JM, Vaughn BV et al. Feedback-controlled transcranial alternating current stimulation reveals a functional role of sleep spindles in motor memory consolidation. Current biology 2016; 26: 2127-2136.
[39] Hjorth B. EEG analysis based on time domain properties. Electroencephalography and Clinical Neurophysiology 1970; 29: 306-310.
[40] Ahmadlou M, Adeli H, Adeli A. New diagnostic EEG markers of the Alzheimer’s disease using visibility graph. Journal of Neural Transmission 2010; 17: 1099-1109.
[41] Yuan Q, Zhou W, Li S, Cai D. Epileptic EEG classification based on extreme learning machine and nonlinear features. Epilepsy Research 2011; 96: 29-38.
[42] Niknazar H, Nasrabadi AM, Shamsollahi MB. Epileptic Seizure Prediction Using a New Similarity Index for Chaotic Signals. International Journal of Bifurcation and Chaos 2016; 26:1650186.
[43] Ronzhina M, Janousek O, Kolarova J, Novakova M, Honzik P et al. Sleep scoring using artificial neural networks. Sleep Medicine Reviews 2012; 16: 251-263.
[44] Huang CS, Lin CL, Ko LW, Liu SY, Su TP et al. Knowledge-based identification of sleep stages based on two forehead electroencephalogram channels. Frontiers in Neuroscience 2014; 8: 263.
[45] Niknazar H, Nasrabadi AM, Shamsollahi MB. A new similarity index for nonlinear signal analysis based on local extrema patterns. Physics Letters A 2018; 382: 288-299.
[46] Acharya UR, Sudarshan VK, Adeli H. A novel depression diagnosis index using nonlinear features in EEG signals. European Neurology 2016; 74: 79-83.
[47] Shayegh F, Sadri S, Amirfattahi R, Ansari-Asl K. A model-based method for computation of correlation dimension, Lyapunov exponents and synchronization from depth-EEG signals. Computer Methods and Programs in Biomedicine 2014; 113: 323-337.
[48] Ferlazzo E, Mammone N, Cianci V. Permutation entropy of scalp EEG: A tool to investigate epilepsies. Suggestions from absence epilepsies. Clinical Neurophysiology 2014; 125: 12-20.
[49] Niknazar H, Nasrabadi AM, Shamsollahi MB. Volumetric behavior quantification to characterize trajectory in phase space. Chaos, Solitons & Fractals 2017; 103: 294-306.
[50] Xue B, Zhang M, Browne WN, Yao X. A survey on evolutionary computation approaches to feature selection. IEEE Transactions on Evolutionary Computation 2016; 20: 4.
[51] Urbanowicz R, Meeker M, LaCava W, Olson R, Moore J. Relief-based feature selection: introduction and review. Journal of Biomedical Informatics 2017; 85.
[52] Muthukrishnan R, Rohini R. LASSO: A feature selection technique in predictive modeling for machine learning. In: IEEE 2016 International Conference on Advances in Computer Applications (ICACA); 2016. pp. 18-20.
[53] Voulodimos A, Doulamis N, Doulamis A, Protopapadakis E. Deep learning for computer vision: a brief review. Computational Intelligence and Neuroscience 2018; 2018: 706349.
[54] Zheng X, Chen W, You Y, Jiang Y, Li M et al. Ensemble deep learning for automated visual classification using EEG signals. Pattern Recognition 2020; 102: 107147.
[55] Liu M, Zhou M, Zhang T, Xiong N. Semi-supervised learning quantization algorithm with deep features for motor imagery EEG recognition in smart healthcare. application, Applied Soft Computing 2020; 89: 106071.
[56] Chen H, Song Y, Li X. A deep learning framework for identifying children with ADHD using an EEG-based brain network. Neurocomputing 2019; 356: 83-96.
[57] Amin SU, Alsulaiman M, Muhammad G, Mekhtiche M, Hossain MS. Deep learning for EEG motor imagery classification based on multi-layer CNNs feature fusion. Future Generation Computer Systems 2019; 101:542-554.
[58] Tjepkema-Cloostermans MC, de Carvalho RC, van Putten MJ. Deep learning for detection of focal epileptiform discharges from scalp EEG recordings. Clinical Neurophysiology 2018; 129: 2191-2196.
[59] Zeiler M, Fergus R. Visualizing and Understanding Convolutional Neural Networks. ECCV; 2014; Part I, LNCS 8689.
[60] Erhan D, Bengio Y, Courville A, Vin-cent P. Visualizing higher-layer features of a deep network. Technical report. University of Mon-treal, 2009.
[61] Nguyen A, Yosinski J, Clune J. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2015; Boston, MA, USA: pp. 427-436.
[62] Goodfellow IJ, Shlens J, Szegedy C. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572. 2014 Dec 20
[63] Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Object detectors emerge in deep scene cnns. arXiv preprint arXiv:1412.6856. 2014 Dec 22.
[64] Schonwald SV, Gerhardt GJ, Santa-Helena EL, Chaves ML. Characteristics of human EEG sleep spindles assessed by Gabor transform. Physica A 2003; 327: 180-184.
[65] Cudlenco N,Popescu N, Leordeanu M. Reading into the mind’s eye: boosting automatic visual recognition with EEG signals. Neurocomputing 2019; 386: 281-292
[66] Schonwald SV, Carvalho DZ, Dellagustin G, Santa-Helena EL, Gerhardt GJ. Quantifying chirp in sleep spindles. Journal of Neuroscience Methods 2011; 197: 158-164.
[67] Mohsina M, Majumdar A. Gabor based analysis prior formulation for EEG signal reconstruction. Biomedical Signal Processing and Control 2011; 8: 951-955.
[68] Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 2014; 15: 1929:1958.
[69] Kingma DP, Ba J. Adam: a method for stochastic optimization. In: 3rd International Conference for Learning Representations; San Diego; 2015.
[70] Thomasson N, Hoeppner T, Webber C, Zbilut J. Recurrence quantification in epileptic EEGs. Physics Letter A 2001; 279:94-101
[71] Takens F, Crowcroft J, Zhang I. Detecting strange attractors in turbulence, Dynamical Systems and Turbulence. Lecture Notes in Mathematics 1981; 898: 361-381.
[72] Block A, Bloh W, Schellnhuber HJ. Efficient box-counting determination of generalized fractal dimensions. Physical Review A 1990; 42: 1869-1874.
[73] Fraser AM, Swinney HL. Independent coordinates for strange attractors from mutual information. Physical Review A 1953; 33: 1134-1140.
[74] Durka PJ, Malinowska U, Szelenberger W, Wakarow A, Blinowska KJ. High resolution parametric description of slow wave sleep. Journal of Neuroscience Methods 2005; 147: 15-21.
[75] Virkkala J, Hasan J, Varri A, Himanen S, Muller K. Automatic detection of slow wave sleep using two channel electro-oculography. Journal of Neuroscience Methods 2007; 160: 171-177.
[76] Su B, Luo Y, Hong C, Nagurka ML, Yen C. Detecting slow wave sleep using a single EEG signal channel. Journal of Neuroscience Methods 2015; 243: 47-52.
[77] IMTIAZ SA, Rodriguez-Villegas E. A low computational cost algorithm for REM sleep detection using single channel EEG. Annals of Biomedical Engineering 2014; 42: 2344-2359.
[78] Liang S, Kuo C, Hu Y, Pan Y, Wang Y. Automatic stage scoring of single-channel sleep EEG by using multiscale entropy and autoregressive models. IEEE Transactions on Instrumentation and Measurement 2012; 61: 1649-1657.
[79] Berthomier C, Drouot X, Herman-Stoica M, Berthomier P, Prado J et al. Automatic analysis of single-channel sleep EEG: validation in healthy individuals. Sleep 2007; 30: 1587-1595.
[80] Seifpour S, Niknazar H, Mikaeili M, Nasrabadi AM. A new automatic sleep staging system based on statistical behavior of local extrema using single channel EEG signal. Expert Systems with Applications 2018; 104: 277-293.
[81] Golrou A, Sheikhani A, Nasrabadi AM. Detecting slow wave sleep and rapid eye movement stage using cortical effective connectivity. Turkish Journal of Electrical Engineering & Computer Sciences 2018; 26: 2779-2792.