DOI:
https://doi.org/10.14483/23448350.19068Publicado:
2023-01-02Número:
Vol. 46 Núm. 1 (2023): Enero-Abril 2023Sección:
Ingeniería y TecnologíaEvaluation of Strategies Based on Wavelet-ICA and ICLabel for Artifact Correction in EEG Recordings
Evaluación de estrategias basadas en Wavelet-ICA e ICLabel para la corrección de artefactos sobre registros EEG
Palabras clave:
Artifacts, Alzheimer, alpha, electroencephalography, effect size, E280A, pipelines, precuneus, preprocessing, wICA (en).Palabras clave:
Artefactos, Alzheimer, Alfa, electroencefalografía, E280A, precuña, preprocesamiento, tamaño del efecto, wICA (es).Descargas
Resumen (en)
In quantitative electroencephalography, it is of vital importance to eliminate non-neural components, as these can lead to an erroneous analysis of the acquired signals, limiting their use in diagnosis and other clinical applications. In light of this drawback, preprocessing pipelines based on the joint use of the Wavelet Transform and the Independent Component Analysis technique (wICA) were proposed in the 2000s. Recently, with the advent of data-driven methods, deep learning models were developed for the automatic labeling of independent components, which constitutes an opportunity for the optimization of ICA-based techniques. In this paper, ICLabel, one of these deep learning models, was added to the wICA methodology in order to explore its improvement. To assess the usefulness of this approach, it was compared to different pipelines which feature the use of wICA and ICLabel independently and a lack thereof. The impact of each pipeline was measured by its capacity to highlight known statistical differences between asymptomatic carriers of the PSEN-1 E280A mutation and a healthy control group. Specifically, the between-group effect size and the P-values were calculated to compare the pipelines. The results show that using ICLabel for artifact removal can improve the effect size (ES) and that, by leveraging it with wICA, an artifact smoothing approach that is less prone to the loss of neural information can be built.
Resumen (es)
En la electroencefalografía cuantitativa es de vital importancia la eliminación de componentes no neuronales, ya que estos pueden conducir a un análisis erróneo de las señales adquiridas, limitando su uso al diagnóstico y otras aplicaciones clínicas. Dado este inconveniente, en la década de 2000 se propusieron flujos de preprocesamiento basados en el uso conjunto de la Transformada Wavelet y la técnica de Análisis de Componentes Independientes (wICA). Recientemente, con la llegada de los métodos basados en datos, se desarrollaron modelos de aprendizaje profundo para el etiquetado automático de componentes independientes, lo que generó una oportunidad para la optimización de las técnicas basadas en ICA. En este estudio, se añadió ICLabel, uno de estos modelos de aprendizaje profundo, a la metodología de wICA para explorar su mejora. Para evaluar la utilidad de este enfoque, se comparó con diferentes flujos que muestran el uso de wICA e ICLabel de forma independiente y en su ausencia. El impacto de cada flujo se midió mediante su capacidad para resaltar diferencias estadísticas conocidas entre los portadores asintomáticos de la mutación PSEN-1 E280A y un grupo de control sano. Se calcularon específicamente el tamaño del efecto entre grupos y los valores P para comparar los flujos. Los resultados muestran que el uso de ICLabel para la eliminación de artefactos puede mejorar el tamaño del efecto (ES) y que, al aprovecharlo con wICA, se puede construir un enfoque de suavizado de artefactos menos susceptible a la pérdida de información neuronal.
Referencias
Babiloni, C., Barry, R. J., Başar, E., Blinowska, K. J., Cichocki, A., Drinkenburg, W. H. I. M., Klimesch, W., Knight, R. T., Lopes da Silva, F., Nunez, P., Oostenveld, R., Jeong, J., Pascual-Marqui, R., Valdes-Sosa, P., Hallett, M. (2020). International Federation of Clinical Neurophysiology (IFCN) – EEG research workgroup: Recommendations on frequency and topographic analysis of resting state EEG rhythms. Part 1: Applications in clinical research studies. Clinical Neurophysiology, 131(1), 285-307. https://doi.org/10.1016/J.CLINPH.2019.06.234
Bigdely-Shamlo, N., Mullen, T., Kothe, C., Su, K. M., Robbins, K. A. (2015). The PREP pipeline: Standardized preprocessing for large-scale EEG analysis. Frontiers in Neuroinformatics, 9, 1-19. https://doi.org/10.3389/FNINF.2015.00016/BIBTEX
Castellanos, N. P., Makarov, V. A. (2006). Recovering EEG brain signals: Artifact suppression with wavelet enhanced independent component analysis. Journal of Neuroscience Methods, 158(2), 300-312. https://doi.org/10.1016/J.JNEUMETH.2006.05.033
Chen, Z., Lu, G., Xie, Z., Shang, W. (2020). A unified framework and method for EEG-Based early epileptic seizure detection and epilepsy diagnosis. IEEE Access, 8, 20080-20092. https://doi.org/10.1109/ACCESS.2020.2969055
Cohen, B. A., Sances, A. (1977). Stationarity of the human electroencephalogram. Medical & Biological Engineering & Computing, 15(5), 513-518. https://doi.org/10.1007/BF02442278
Cohen, J. (1988). Statistical power anaylsis for the behavioral sciences (2nd ed.). Lawrence Erlbaum Associates
Donoho, D. L., Johnstone, I. M. (1992). Ideal spatial adaptation by wavelet shrinkage. Department of Statistics, Stanford University
Duque-Grajales, J. E., Tobón, C., Aponte-Restrepo, C. P., Ochoa-Gómez, J. F., Muñoz-Zapata, C., Hernández-Valdivieso, A. M., Quiroz-Zapata, Y. T., Lopera, F. (2014). Quantitative EEG analysis disease during resting and memory task in carriers and non-carriers of PS-1 E280A mutation of familial Alzheimer's. Revista CES Medicina, 28(2), 165-175
Fabietti, M., Mahmud, M., Lotfi, A., Averna, A., Guggenmos, D., Nudo, R., Chiappalone, M. (2020). Artifact detection in chronically recorded local field potentials using long-short term memory neural network. En 14th IEEE International Conference on Application of Information and Communication Technologies, Tashkent, Uzbekistan. https://doi.org/10.1109/AICT50176.2020.9368638
Glerean, E. (2015). Bramila t-test. https://version.aalto.fi/gitlab/BML/bramila/-/blob/master/README.md
He, B., Sohrabpour, A., Brown, E., Liu, Z. (2018). Electrophysiological source imaging: A noninvasive window to brain dynamics. Annual Review of Biomedical Engineering, 20, 171-196. https://doi.org/10.1146/annurev-bioeng-062117-120853
Iversen, J. R., Makeig, S. (2019). MEG/EEG data analysis using EEGLAB. In S. Supek & C. Aine (Eds.), Magnetoencephalography: From Signals to Dynamic Cortical Networks (2nd ed., pp. 391-406). Springer. https://doi.org/10.1007/978-3-030-00087-5_8
Jadah, R. H. S. (2020). Basic electroencephalogram and its common clinical applications in children. In H. Nakano (Ed.), Electroencephalography - From Basic Research to Clinical Applications. IntechOpen. https://doi.org/10.5772/INTECHOPEN.94247
Jiang, X., Bian, G. Bin, Tian, Z. (2019). Removal of artifacts from EEG signals: A review. Sensors, 19(5), e987. https://doi.org/10.3390/S19050987
Kaur, R., Korolkov, M., Hernández, M. E., Sowers, R. (2020). Automatic identification of brain independent components in electroencephalography data collected while standing in a virtually immersive environment - A Deep Learning-Based approach. En 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada. https://doi.org/10.1109/EMBC44109.2020.9175741
Kim, J., Cho, Y. H., Sung, K., Park, T. K., Lee, G. Y., Lee, J. M., Song, Y. Bin, Hahn, J.-Y., Choi, J.-H., Choi, S.-H., Gwon, H.-C., Yang, J. H. (2019). Impact of cannula size on clinical outcomes in peripheral venoarterial extracorporeal membrane oxygenation. ASAIO Journal, 65(6), 573-579. https://doi.org/10.1097/MAT.0000000000000858
Klug, M., Gramann, K. (2020). Identifying key factors for improving ICA-based decomposition of EEG data in mobile and stationary experiments. bioRxiv. https://doi.org/10.1101/2020.06.02.129213
Lee, S. S., Lee, K., Kang, G. (2020). EEG artifact removal by Bayesian Deep Learning ICA. En 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada. https://doi.org/10.1109/EMBC44109.2020.9175785
Lema-Condo, E. L., Bueno-Palomeque, F. L., Castro-Villalobos, S. E., Ordóñez-Morales, E. F., Serpa-Andrade, L. J. (2017). Comparison of wavelet transform symlets (2-10) and daubechies (2-10) for an electroencephalographic signal analysis. En IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON), Cusco, Peru. https://doi.org/10.1109/INTERCON.2017.8079702
Maestú, F., Cuesta, P., Hasan, O., Fernandéz, A., Funke, M., Schulz, P. E. (2019). The importance of the validation of M/EEG with current biomarkers in Alzheimer’s disease. Frontiers in Human Neuroscience, 13, e17. https://doi.org/10.3389/fnhum.2019.00017
Mamun, M., Al-Kadi, M., Marufuzzaman, M. (2013). Effectiveness of wavelet denoising on electroencephalogram signals. Journal of Applied Research and Technology, 11, e339. https://doi.org/10.1016/S1665-6423(13)71524-4
Monachino, A. D., López, K. L., Pierce, L. J. B., Gabard-Durnam. (n.d.). The HAPPE plus Event-Related (HAPPE+ER) software: A standardized processing pipeline for event-related potential analyses. bioRxiv. https://doi.org/10.1101/2021.07.02.450946
Ochoa, J. F., Alonso, J. F., Duque, J. E., Tobón, C. A., Baena, A., Lopera, F., Mañanas, M. A., Hernández, A. M. (2017a). Precuneus failures in subjects of the PSEN1 E280A family at risk of developing Alzheimer’s disease detected using quantitative electroencephalography. Journal of Alzheimer’s Disease, 58(4), 1229-1244. https://doi.org/10.3233/JAD-161291
Ochoa, J. F., Alonso, J. F., Duque, J. E., Tobón, C. A., Mañanas, M. A., Lopera, F., Hernández, A. M. (2017). Successful object encoding induces increased directed connectivity in presymptomatic early-onset Alzheimer’s disease. Journal of Alzheimer’s Disease, 55(3), 1195-1205. https://doi.org/10.3233/JAD-160803
Paradeshi, K. P., Kolekar, U. D. (2017). Removing jaw clench, teeth squeeze and forehead movement EMG artifacts from EEG signal using dynamic size segmentation and multilevel decomposed wavelet with adaptive thresholding. Indian Journal of Science and Technology, 10(29), 1-7. https://doi.org/10.17485/IJST/2017/V10I29/115354
Pedroni, A., Bahreini, A., Langer, N. (2019). Automagic: Standardized preprocessing of big EEG data. NeuroImage, 200, 460-473. https://doi.org/10.1016/j.neuroimage.2019.06.046
Pion-Tonachini, L., Kreutz-Delgado, K., Makeig, S. (2019). ICLabel: An automated electroencephalographic independent component classifier, dataset, and website. NeuroImage, 198, 181-197. https://doi.org/10.1016/j.neuroimage.2019.05.026
Salis, C. I., Malissovas, A. E., Bizopoulos, P. A., Tzallas, A. T., Angelidis, P. A., Tsalikakis, D. G. (2013). Denoising simulated EEG signals: A comparative study of EMD, wavelet transform and Kalman filter. En 13th IEEE International Conference on BioInformatics and BioEngineering, Chania, Greece. https://doi.org/10.1109/BIBE.2013.6701613
Sintra, T. (1992). Independent component analysis, A new concept. http://mlsp.cs.cmu.edu/courses/fall2014/lectures/extra/ICA.pdf
Suárez-Revelo, J., Ochoa-Gómez, J., Duque-Grajales, J. (2016). Improving test-retest reliability of quantitative electroencephalography using different preprocessing approaches. En 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA. https://doi.org/10.1109/EMBC.2016.7590861
Swarnkar, R., Miyapuram, K. P. (2020). Temporal EEG neural activity predicts visuo-spatial motor sequence learning. Communications in Computer and Information Science, 1333, 204-211. https://doi.org/10.1007/978-3-030-63823-8_25
Thomson, D. J. (1982). Spectrum estimation and harmonic analysis. Proceedings of the IEEE, 70(9), 1055-1096. https://doi.org/10.1109/PROC.1982.12433
Vajravelu, A., Abdul Jamil, M. M., Wan Zaki, W. S, Govindassamy, M. (2021). Survey and analysis of preprocessing of EEG signal. https://www.lens.org/lens/scholar/article/036-198-693-947-283/main
Wessel, J. R. (2018). Testing multiple psychological processes for common neural mechanisms using EEG and Independent Component Analysis. Brain Topography, 31(1), 90-100. https://doi.org/10.1007/S10548-016-0483-5/tables/1
Winkler, I., Debener, S., Muller, K. R., Tangermann, M. (2015). On the influence of high-pass filtering on ICA-based artifact reduction in EEG-ERP. En 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy. https://doi.org/10.1109/EMBC.2015.7319296
Cómo citar
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Descargar cita
Licencia
Derechos de autor 2023 Luisa-María Zapata-Saldarriaga, Angie-Dahiana Vargas-Serna, Jesica Gil-Gutiérrez, Yorguin-Jose Mantilla-Ramos, John-Fredy Ochoa-Gómez

Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
El (los) autor(es) al enviar su artículo a la Revista Científica certifica que su manuscrito no ha sido, ni será presentado ni publicado en ninguna otra revista científica.
Dentro de las políticas editoriales establecidas para la Revista Científica en ninguna etapa del proceso editorial se establecen costos, el envío de artículos, la edición, publicación y posterior descarga de los contenidos es de manera gratuita dado que la revista es una publicación académica sin ánimo de lucro.