Turn off MathJax
Article Contents
Yuxiao DU and Gaoming LI, “A study of Epileptogenic Foci Localization Algorithm Based on Automatic Detection of Comprehensive Feature HFOs and RF-LR,” Chinese Journal of Electronics, vol. x, no. x, pp. 1–12, xxxx doi: 10.23919/cje.2023.00.213
Citation: Yuxiao DU and Gaoming LI, “A study of Epileptogenic Foci Localization Algorithm Based on Automatic Detection of Comprehensive Feature HFOs and RF-LR,” Chinese Journal of Electronics, vol. x, no. x, pp. 1–12, xxxx doi: 10.23919/cje.2023.00.213

A study of Epileptogenic Foci Localization Algorithm Based on Automatic Detection of Comprehensive Feature HFOs and RF-LR

doi: 10.23919/cje.2023.00.213
More Information
  • Author Bio:

    Yuxiao DU was born in 1973. He received the Ph.D. degree in School of Information Science and Engineering, Central South University, Changsha, China, in 2004. He is an Associate Pro fessor of School of Automation, Guang dong University of Technology. His re search interests include intelligent manu facturing and industrial robot techno logy and brain computer interface technology. (Email: yuxiaodu@gdut.edu.cn)

    Gaoming LI was born in 1996. He received the B.E. degree in automation, Zhengzhou University, Zhengzhou, China, in 2020. He is currently pursing the M.E. degree in con trol science and engineering from Guang dong University of Technology, Guang zhou, China. His research interests in epilepsy EEG processing. (Email: qq1334676416@163.com)

  • Corresponding author: Email: qq1334676416@163.com
  • Available Online: 2024-04-01
  • Studies have shown that fast ripples of 250-500 HZ in epileptic EEG signals are more pathological and closer to the epileptogenic focus itself compared to ripples of 80-250 HZ. However, artifacts of fast ripples and HFOs are easily confused and difficult to discriminate, and manual visual screening is both time-consuming and unable to avoid subjectivity. To this end, this paper presents a method for localizing epileptogenic foci based on the automatic detection of integrated feature HFOs and RF-LR. In this paper, we first extract multivariate features from the preprocessed epileptic EEG signals, and use the random forest algorithm to filter out three features with high importance, based on which, suspicious leads containing HFOs are identified. Then, wavelet time-frequency maps were used for the primary screening of suspected leads to improve the signal calibration efficiency and further localize HFOs in time and frequency. Finally, a logistic regression model was used to automatically classify and identify ripples and fast ripples in HFOs. The results show that the sensitivity, specificity, and accuracy of the model for detecting ripple are 89.37%, 88.26% and 90.1%, respectively; the sensitivity, specificity, and accuracy for detecting fast ripple are 94.31%, 94.83% and 93.46%, respectively. Compared with single features, the multivariate features in this paper more comprehensively characterize the complex epileptic EEG signals and provide more accurate information for the localization of epileptogenic foci. The automatic detection algorithm of HFOs proposed in this paper can analyze a large amount of data in a short time and has a good detection performance, which can help clinicians accurately determine the region of epileptogenic foci.
  • loading
  • [1]
    C. M. Huang and L. E. Jr. White, “High-frequency components in epileptiform EEG,” Journal of Neuroscience Methods, vol. 30, no. 3, pp. 197–201, 1989. doi: 10.1016/0165-0270(89)90130-1
    [2]
    J. D. Jirsch, E. Urrestarazu, P. LeVan, et al., “High-frequency oscillations during human focal seizures,” Brain, vol. 129, no. 6, pp. 1593–1608, 2006. doi: 10.1093/brain/awl085
    [3]
    L. P. Andrade-Valenca, F. Dubeau, F. Mari, et al., “Interictal scalp fast oscillations as a marker of the seizure onset zone,” Neurology, vol. 77, no. 6, pp. 524–531, 2011. doi: 10.1212/WNL.0b013e318228bee2
    [4]
    H. Fujiwara, H. M. Greiner, K. H. Lee, et al., “Resection of ictal high-frequency oscillations leads to favorable surgical outcome in pediatric epilepsy,” Epilepsia, vol. 53, no. 9, pp. 1607–1617, 2012. doi: 10.1111/j.1528-1167.2012.03629.x
    [5]
    J. M. Scott, S. J. Ren, S. V. Gliske, et al., “Preictal variability of high-frequency oscillation rates in refractory epilepsy,” Epilepsia, vol. 61, no. 11, pp. 2521–2533, 2020. doi: 10.1111/epi.16680
    [6]
    L. Qi, X. Fan, X. R. Tao, Q. Chai, et al., “Identifying the epileptogenic zone with the relative strength of high-frequency oscillation: A stereoelectroencephalography study,” Frontiers in Human Neuroscience, vol. 14, article no. 186, 2020. doi: 10.3389/fnhum.2020.00186
    [7]
    H. Nariai, S. A. Hussain, D. Bernardo, et al., “Prospective observational study: Fast ripple localization delineates the epileptogenic zone,” Clinical Neurophysiology, vol. 130, no. 11, pp. 2144–2152, 2019. doi: 10.1016/j.clinph.2019.08.026
    [8]
    M. A. van’t Klooster, N. E. C. van Klink, F. S. S. Leijten, et al., “Residual fast ripples in the intraoperative corticogram predict epilepsy surgery outcome,” Neurology, vol. 85, no. 2, pp. 120–128, 2015. doi: 10.1212/WNL.0000000000001727
    [9]
    T. Wan, M. Wu, X. B. Wan, et al., “Automatic detection of high frequency oscillations based on fuzzy entropy and fuzzy neural network,” in Proceedings of the 35th Chinese Control Conference, Chengdu, China, pp. 5027–5032, 2016.
    [10]
    Y. Höller, R. Kutil, L. Klaffenböck, et al., “High-frequency oscillations in epilepsy and surgical outcome. A meta-analysis,” Frontiers in Human Neuroscience, vol. 9, article no. 574, 2015. doi: 10.3389/fnhum.2015.00574
    [11]
    R. J. Staba, C. L. Wilson, A. Bragin, et al., “Quantitative analysis of high-frequency oscillations (80–500 Hz) recorded in human epileptic hippocampus and entorhinal cortex,” Journal of Neurophysiology, vol. 88, no. 4, pp. 1743–1752, 2002. doi: 10.1152/jn.2002.88.4.1743
    [12]
    A. B. Gardner, G. A. Worrell, E. Marsh, et al., “Human and automated detection of high-frequency oscillations in clinical intracranial EEG recordings,” Clinical Neurophysiology, vol. 118, no. 5, pp. 1134–1143, 2007. doi: 10.1016/j.clinph.2006.12.019
    [13]
    B. Crépon, V. Navarro, D. Hasboun, et al., “Mapping interictal oscillations greater than 200 Hz recorded with intracranial macroelectrodes in human epilepsy,” Brain, vol. 133, no. 1, pp. 33–45, 2010. doi: 10.1093/brain/awp277
    [14]
    S. Chaibi, T. Lajnef, Z. Sakka, et al., “A comparaison of methods for detection of high frequency oscillations (HFOs) in human intacerberal EEG recordings,” American Journal of Signal Processing, vol. 3, no. 2, pp. 25–34, 2013. doi: 10.5923/j.ajsp.20130302.02
    [15]
    N. von Ellenrieder, L. P. Andrade-Valença, F. Dubeau, et al., “Automatic detection of fast oscillations (40–200 Hz) in scalp EEG recordings,” Clinical Neurophysiology, vol. 123, no. 4, pp. 670–680, 2012. doi: 10.1016/j.clinph.2011.07.050
    [16]
    M. Amiri, J. M. Lina, F. Pizzo, et al., “High frequency oscillations and spikes: Separating real HFOs from false oscillations,” Clinical Neurophysiology, vol. 127, no. 1, pp. 187–196, 2016. doi: 10.1016/j.clinph.2015.04.290
    [17]
    M. Dümpelmann, J. Jacobs, K. Kerber, et al., “Automatic 80–250 Hz “ripple” high frequency oscillation detection in invasive subdural grid and strip recordings in epilepsy by a radial basis function neural network,” Clinical Neurophysiology, vol. 123, no. 9, pp. 1721–1731, 2012. doi: 10.1016/j.clinph.2012.02.072
    [18]
    T. Wan, M. Wu, X. B. Wan, et al., “Automatic detection of high frequency oscillations based on fuzzy entropy and fuzzy neural network,” in Proceedings of the 35th Chinese Control Conference, Chengdu, China, pp. 5027–5032, 2016. (查阅网上资料,本条文献与第9条文献重复,请确认).

    T. Wan, M. Wu, X. B. Wan, et al., “Automatic detection of high frequency oscillations based on fuzzy entropy and fuzzy neural network,” in Proceedings of the 35th Chinese Control Conference, Chengdu, China, pp. 5027–5032, 2016. (查阅网上资料,本条文献与第9条文献重复,请确认).
    [19]
    Y. X. Du, B. Sun, R. Q. Lu, et al., “A method for detecting high-frequency oscillations using semi-supervised k-means and mean shift clustering,” Neurocomputing, vol. 350, pp. 102–107, 2019. doi: 10.1016/j.neucom.2019.03.055
    [20]
    C. Migliorelli, A. Bachiller, J. F. Alonso, et al., “SGM: A novel time-frequency algorithm based on unsupervised learning improves high-frequency oscillation detection in epilepsy,” Journal of Neural Engineering, vol. 17, no. 2, article no. 026032, 2020. doi: 10.1088/1741-2552/ab8345
    [21]
    M. Wu, T. Wan, X. B. Wan, et al., “Fast, accurate localization of epileptic seizure onset zones based on detection of high-frequency oscillations using improved wavelet transform and matching pursuit methods,” Neural Computation, vol. 29, no. 1, pp. 194–219, 2017. doi: 10.1162/NECO_a_00899
    [22]
    C. Migliorelli, S. Romero, A. Bachiller, et al., “Improving the ripple classification in focal pediatric epilepsy: Identifying pathological high-frequency oscillations by Gaussian mixture model clustering,” Journal of Neural Engineering, vol. 18, no. 4, article no. 0460f2, 2021. doi: 10.1088/1741-2552/ac1d31
    [23]
    S. Burnos, P. Hilfiker, O. Sürücü, et al., “Human intracranial high frequency oscillations (HFOs) detected by automatic time-frequency analysis,” PLoS One, vol. 9, no. 4, article no. e94381, 2014. doi: 10.1371/journal.pone.0094381
    [24]
    J. R. Cho, D. L. Koo, E. Y. Joo, et al., “Resection of individually identified high-rate high-frequency oscillations region is associated with favorable outcome in neocortical epilepsy,” Epilepsia, vol. 55, no. 11, pp. 1872–1883, 2014. doi: 10.1111/epi.12808
    [25]
    M. Cotic, Y. Chinvarun, M. del Campo, et al., “Spatial coherence profiles of ictal high-frequency oscillations correspond to those of interictal low-frequency oscillations in the ECoG of epileptic patients,” IEEE Transactions on Biomedical Engineering, vol. 63, no. 1, pp. 76–85, 2016. doi: 10.1109/TBME.2014.2386791
    [26]
    X. Y. Wang, X. H. Li, Z. G. Chen, et al., “Localization of epileptogenic foci by automatic detection of high-frequency oscillations based on waveform feature templates,” International Journal of Intelligent Systems, vol. 37, no. 12, pp. 11506–11521, 2022. doi: 10.1002/int.23052
    [27]
    L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. doi: 10.1023/A:1010933404324
    [28]
    S. Chaibi, R. Bouet, J. Jung, et al., “Developement of matlab-based graphical user interface (GUI) for detection of high frequency oscillations (HFOs) in epileptic patients,” in Proceedings of 2012 IEEE International Conference on Emerging Signal Processing Applications, Las Vegas, NV, USA, pp. 56–62, 2012.
    [29]
    Y. X. Du and B. Sun, “Accurate localization of seizure onset zones based on multi-feature extraction and wavelet time-frequency map,” in Proceedings of 2018 37th Chinese Control Conference, Wuhan, China, pp. 4283–4288, 2018.
    [30]
    P. F. Liang, C. Deng, J. Wu, et al., “Intelligent fault diagnosis of rotating machinery via wavelet transform, generative adversarial nets and convolutional neural network,” Measurement, vol. 159, article no. 107768, 2020. doi: 10.1016/j.measurement.2020.107768
    [31]
    S. Chaibi, T. Lajnef, Z. Sakka, et al., “A comparaison of methods for detection of high frequency oscillations (HFOs) in human intacerberal EEG recordings,” American Journal of Signal Processing, vol. 3, no. 2, pp. 25–34, 2013,doi: 10.5923/j.ajsp.20130302.02. (查阅网上资料,本条文献与第14条文献重复,请确认).

    S. Chaibi, T. Lajnef, Z. Sakka, et al., “A comparaison of methods for detection of high frequency oscillations (HFOs) in human intacerberal EEG recordings,” American Journal of Signal Processing, vol. 3, no. 2, pp. 25–34, 2013,doi: 10.5923/j.ajsp.20130302.02. (查阅网上资料,本条文献与第14条文献重复,请确认).
    [32]
    K. M. Tsiouris, S. Markoula, S. Konitsiotis, et al., “A robust unsupervised epileptic seizure detection methodology to accelerate large EEG database evaluation,” Biomedical Signal Processing and Control, vol. 40, pp. 275–285, 2018. doi: 10.1016/j.bspc.2017.09.029
    [33]
    T. Das, A. Ghosh, S. Guha, et al., “Early detection of diabetes based on skin impedance spectrogram and heart rate variability noninvasively,” in Proceedings of the 1st International Conference on Electronics, Materials Engineering and Nano-Technology, Kolkata, India, pp. 1–5, 2017.
    [34]
    K. F. Ma, D. K. Lai, Z. C. Chen, et al., “Automatic detection of high frequency oscillations (80-500Hz) based on convolutional neural network in human intracerebral electroencephalogram,” in Proceedings of 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Berlin, Germany, pp. 5133–5136, 2019.
    [35]
    N. Jrad, A. Kachenoura, I. Merlet, et al., “Automatic detection and classification of high-frequency oscillations in depth-EEG signals,” IEEE Transactions on Biomedical Engineering, vol. 64, no. 9, pp. 2230–2240, 2017. doi: 10.1109/TBME.2016.2633391
    [36]
    S. Chaibi, Z. Sakka, T. Lajnef, et al., “Automated detection and classification of high frequency oscillations (HFOs) in human intracereberal EEG,” Biomedical Signal Processing and Control, vol. 8, no. 6, pp. 927–934, 2013. doi: 10.1016/j.bspc.2013.08.009
    [37]
    W. L. Li, L. F. Zhong, W. X. Xiang, et al., “A novel unsupervised autoencoder-based HFOs detector in intracranial EEG signals,” in Proceedings of 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, Singapore, pp. 1426–1430, 2022.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(13)  / Tables(3)

    Article Metrics

    Article views (9) PDF downloads(2) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return