A novel deep LSTM network for artifacts detection in microelectrode recordings

• Autorzy: Hosny Mohamed , Zhu Minwei , Gao Wenpeng , Fu Yili

Identyfikatory

DOI

10.1016/j.bbe.2020.04.004

• Języki publikacji: EN

Abstrakty

EN

Microelectrode recording (MER) signals are world-widely used for validating the planned trajectories in the procedure of deep brain stimulation (DBS) surgery to obtain accurate position of electrodes inside the brain structure. Besides, MER signals are important source for studying extracellular neuronal activity and DBS biomarkers, such as, spike clustering and sorting. However, MER signals are prone to several artifacts derived from electrical equipment in the operating room, electrode movement and patient activities, etc., which reduce the signal-to-noise ratio of the MER signals. Therefore, in this paper, we propose a novel deep learning architecture based on long short-term memory (LSTM) network for automatic artifact detection in MER signals. Frequency and time-domain features were extracted from the raw MER signals and fed to the deep LSTM network. A manually annotated MER database obtained from 17 Parkinson's disease (PD) patients were used to validate the proposed architecture. The proposed architecture achieved promising results of 97.49% accuracy, 98.21% sensitivity and 96.87% specificity on an unseen test set. To our best knowledge, this is the first study to use LSTM network for artifacts detection in MER signals. The MER data will be available at http://homepage.hit.edu.cn/wpgao.

Słowa kluczowe

EN

recurrent neural network; long short-term memory; Parkinson's disease; microelectrode recording; artifacts detection; wavelet packet decomposition

PL

rekurencyjna sieć neuronowa; choroba Parkinsona; wykrywanie artefaktów; dekompozycja pakietów falkowych

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 3
• Strony: 1052--1063
• Opis fizyczny: Bibliogr. 56 poz., rys., tab., wykr.

Twórcy

autor

Hosny Mohamed

• School of Life Science and Technology, Harbin Institute of Technology, Harbin, China

autor

Zhu Minwei

• Department of Neurosurgery, First Affiliated Hospital of Harbin Medical University, Harbin, China

autor

Gao Wenpeng

• Building 2E, Science Park of Harbin Institute of Technology, Yikuang Str. 2, Nangang District, Harbin 150080, China

autor

Fu Yili

• School of Life Science and Technology, Harbin Institute of Technology, Harbin, China

Bibliografia

• [1] Silver J, Schwab ME, Popovich PG. Central nervous system regenerative failure: role of oligodendrocytes, astrocytes, and microglia. Cold Spring Harb Perspect Biol 2015;7(3): a020602.
• [2] Umay E, Ozturk E, Gurcay E, Delibas O, Celikel F. Swallowing in Parkinson's disease: how is it affected? Clin Neurol Neurosurg 2019;177:37–41.
• [3] Pereira CR, Pereira DR, Weber SA, Hook C, de Albuquerque VHC, Papa JP. A survey on computer-assisted Parkinson's disease diagnosis. Artif Intell Med 2019;95:48–63.
• [4] Schapira AH, Jenner P. Etiology and pathogenesis of Parkinson's disease. Mov Disord 2011;26(6):1049–55.
• [5] Kühn AA, Volkmann J. Innovations in deep brain stimulation methodology. Mov Disord 2017;32(1):11–9.
• [6] Holt AB, Netoff TI. Computational modeling to advance deep brain stimulation for the treatment of Parkinson's disease. Drug Discov Today: Dis Models 2016;19:31–6.
• [7] Bot M, Schuurman PR, Odekerken VJJ, Verhagen R, Contarino FM, De Bie RMA, et al. Deep brain stimulation for Parkinson's disease: defining the optimal location within the subthalamic nucleus. J Neurol Neurosurg Psychiatry 2018;89(5):493–8.
• [8] Horn A, Neumann WJ, Degen K, Schneider GH, Kühn AA. Toward an electrophysiological ‘‘sweet spot’’ for deep brain stimulation in the subthalamic nucleus. Hum Brain Mapp 2017;38(7):3377–90.
• [9] Pozzi NG, Arnulfo G, Canessa A, Steigerwald F, Nickl R, Homola GA, et al. Distinctive neuronal firing patterns in subterritories of the subthalamic nucleus. Clin Neurophysiol 2016;127(11):3387–93.
• [10] Valsky D, Marmor-Levin O, Deffains M, Eitan R, Blackwell KT, Bergman H, et al. Stop! border ahead: automatic detection of subthalamic exit during deep brain stimulation surgery. Mov Disord 2017;32(1):70–9.
• [11] van Wijk BC, Pogosyan A, Hariz MI, Akram H, Foltynie T, Limousin P, et al. Localization of beta and high-frequency oscillations within the subthalamic nucleus region. NeuroImage: Clinical 2017;16:175–83.
• [12] Kim J, Duchin Y, Shamir RR, Patriat R, Vitek J, Harel N, et al. Automatic localization of the subthalamic nucleus on patient-specific clinical MRI by incorporating 7 T MRI and machine learning: application in deep brain stimulation. Hum Brain Mapp 2019;40(2):679–98.
• [13] Lima C. Analysis and classification of microelectrode recordings in deep brain stimulation surgery [Master's thesis]. Universidade de Lisboa; 2015.
• [14] Chaovalitwongse W, Jeong Y, Jeong MK, Danish S, Wong S. Pattern recognition approaches for identifying subcortical targets during deep brain stimulation surgery. IEEE Intell Syst 2011;26(5):54–63.
• [15] D'Haese PF, Pallavaram S, Li R, Remple MS, Kao C, Neimat JS, et al. CranialVault and its CRAVE tools: a clinical computer assistance system for deep brain stimulation (DBS) therapy. Med Image Anal 2012;16(3):744–53.
• [16] Cagnan H, Dolan K, He X, Contarino MF, Schuurman R, Van Den Munckhof P, et al. Automatic subthalamic nucleus detection from microelectrode recordings based on noise level and neuronal activity. J Neural Eng 2011;8(4):046006.
• [17] Bakštein E, Schneider J, Sieger T, Novák D, Wild J, Jech R. Supervised segmentation of microelectrode recording artifacts using power spectral density. 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2015. pp. 1524–7.
• [18] Wild J, Prekopcsak Z, Sieger T, Novak D, Jech R. Performance comparison of extracellular spike sorting algorithms for single-channel recordings. J Neurosci Methods 2012;203 (2):369–76.
• [19] Lourens MA, Meijer HG, Contarino MF, van den Munckhof P, Schuurman PR, van Gils SA, et al. Functional neuronal activity and connectivity within the subthalamic nucleus in Parkinsons disease. Clin Neurophysiol 2013;124(5):967–81.
• [20] Ciecierski K, Mandat T, Rola R, Ras ZW, Przybyszewski AW. Computer aided subthalamic nucleus (STN) localization during deep brain stimulation (DBS) surgery in Parkinson's patients. Ann Acad Med Silesiensis 2014;5(68):275–83.
• [21] Nowacki A, Debove I, Fiechter M, Rossi F, Oertel MF, Wiest R, et al. Targeting accuracy of the subthalamic nucleus in deep brain stimulation surgery: comparison between 3 T T2-weighted magnetic resonance imaging and microelectrode recording results. Oper Neurosurg 2018;15 (1):66–71.
• [22] Abosch A, Timmermann L, Bartley S, Rietkerk HG, Whiting D, Connolly PJ, et al. An international survey of deep brain stimulation procedural steps. Stereotact Funct Neurosurg 2013;91(1):1–11.
• [23] Zaidel A, Spivak A, Grieb B, Bergman H, Israel Z. Subthalamic span of beta oscillations predicts deep brain stimulation efficacy for patients with Parkinson's disease. Brain 2010;133(7):2007–21.
• [24] Bakštein E, Sieger T, Wild J, Novák D, Schneider J, Vostatek P, et al. Methods for automatic detection of artifacts in microelectrode recordings. J Neurosci Methods 2017;290:39–51.
• [25] Zaidel A, Spivak A, Shpigelman L, Bergman H, Israel Z. Delimiting subterritories of the human subthalamic nucleus by means of microelectrode recordings and a hidden Markov model. Mov Disord 2009;24(12):1785–93.
• [26] Verhagen R, Zwartjes DG, Heida T, Wiegers EC, Contarino MF, de Bie RM, et al. Advanced target identification in STN-DBS with beta power of combined local field potentials and spiking activity. J Neurosci Methods 2015;253:116–25.
• [27] Dolan K, Martens HC, Schuurman PR, Bour LJ. Automatic noise-level detection for extra-cellular micro-electrode recordings. Med Biol Eng Comput 2009;47(7):791–800.
• [28] Aboy M, Falkenberg JH. An automatic algorithm for stationary segmentation of extracellular microelectrode recordings. Med Biol Eng Comput 2006;44(6):511–5.
• [29] Guarnizo C, Orozco A, Castellanos G. Microelectrode signals segmentation using stationary wavelet transform. 2008 International Conference on BioMedical Engineering and Informatics; vol. 2; 2008. pp. 450–4.
• [30] Nejedly P, Cimbalnik J, Klimes P, Plesinger F, Halamek J, Kremen V, et al. Intracerebral EEG artifact identification using convolutional neural networks. Neuroinformatics 2019;17(2):225–34.
• [31] Roy Y, Banville H, Albuquerque I, Gramfort A, Falk TH, Faubert J. Deep learning-based electroencephalography analysis: a systematic review. Neural Eng 2019;16(5):051001.
• [32] Yin Z, Zhang J. Cross-session classification of mental workload levels using EEG and an adaptive deep learning model. Biomed Signal Process Control 2017;33:30–47.
• [33] Oh SL, Hagiwara Y, Raghavendra U, Yuvaraj R, Arunkumar N, Murugappan M, et al. A deep learning approach for Parkinson's disease diagnosis from EEG signals. Neural Comput Appl 2018;5.
• [34] Tan JH, Hagiwara Y, Pang W, Lim I, Oh SL, Adam M, et al. Application of stacked convolutional and long short-term memory network for accurate identification of CAD ECG signals. Comput Biol Med 2018;94:19–26.
• [35] Baloglu UB, Talo M, Yildirim O, Tan RS, Acharya UR. Classification of myocardial infarction with multi-lead ECG signals and deep CNN. Pattern Recognit Lett 2019;122:23–30.
• [36] Acharya UR, Fujita H, Oh SL, Raghavendra U, Tan JH, Adam M, et al. Automated identification of shockable and non- shockable life-threatening ventricular arrhythmias using convolutional neural network. Future Gener Comput Syst 2018;79:952–9.
• [37] Acharya UR, Fujita H, Lih OS, Hagiwara Y, Tan JH, Adam M. Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Inf Sci 2017;405:81–90.
• [38] Acharya UR, Fujita H, Oh SL, Hagiwara Y, Tan JH, Adam M. Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals. Inf Sci 2017;415–416:190–8.
• [39] Hasasneh A, Kampel N, Sripad P, Shah NJ, Dammers J. Deep learning approach for automatic classification of ocular and cardiac artifacts in MEG data. J Eng 2018;2018:1–10.
• [40] Kim D, Keene S. Automatic artifact annotator for EEG waves using recurrent and convolutional neural networks [Master's thesis]. The Cooper Union for the Advancement of Science and Art; 2019.
• [41] Klempír O, Krupicka R, Bakštein E, Jech R. Identification of microrecording artifacts with wavelet analysis and convolutional neural network: an image recognition approach. Meas Sci Rev 2019;19(5):222–31.
• [42] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521(7553):436–44.
• [43] Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput Biol Med 2018;100:270–8.
• [44] Acharya UR, Fujita H, Oh SL, Hagiwara Y, Tan JH, Adam M, et al. Deep convolutional neural network for the automated diagnosis of congestive heart failure using ECG signals. Appl Intell 2019;49(1):16–27.
• [45] Michielli N, Acharya UR, Molinari F. Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals. Comput Biol Med 2019;106:71–81.
• [46] Oh SL, Vicnesh J, Ciaccio EJ, Yuvaraj R, Acharya UR. Deep convolutional neural network model for automated diagnosis of schizophrenia using EEG signals. Appl Sci 2019;9(14):2870.
• [47] Hefron RG, Borghetti BJ, Christensen JC, Kabban CMS. Deep long short-term memory structures model temporal dependencies improving cognitive workload estimation. Pattern Recognit Lett 2017;94:96–104.
• [48] Yildirim [602]Ö]. A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification. Comput Biol Med 2018;96:189–202.
• [49] Li X, Wu X. Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition. 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 2015; 2015. 978-1-4673-6997-8pp. 4520–4.
• [50] Murad A, Pyun JY. Deep recurrent neural networks for human activity recognition. Sensors 2017;17(11):2556.
• [51] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput 1997;9(8):1735–80.
• [52] Yildirim Ö, Baloglu UB, Acharya UR. A deep convolutional neural network model for automated identification of abnormal EEG signals. Neural Comput Appl 2018;1–12.
• [53] Kingma DP, Ba J, Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980; 2014.
• [54] Sharma N, Jain V, Mishra A. An analysis of convolutional neural networks for image classification. Procedia Comput Sci 2018;132:377–84.
• [55] Klempír O, Krupicka R, Jech R. Microelectrode neuronal activity of the internal globus pallidus in dystonia correlates with postoperative neuromodulation effects and placement of the stimulation electrode. IRBM 2019;40 (4):193–200.
• [56] Vadera S, Chan A, Lo T, Gill A, Morenkova A, Phielipp NM, et al. Frameless stereotactic robot-assisted subthalamic nucleus deep brain stimulation: case report. World Neurosurg 2015;97.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).