Double-Step Machine Learning Based Procedure for HFOs Detection and Classification

The need for automatic detection and classification of high-frequency oscillations (HFOs) as biomarkers of the epileptogenic tissue is strongly felt in the clinical field. In this context, the employment of artificial intelligence methods could be the missing piece to achieve this goal. This work proposed a double-step procedure based on machine learning algorithms and tested it on an intracranial electroencephalogram (iEEG) dataset available online. The first step aimed to define the optimal length for signal segmentation, allowing for an optimal discrimination of segments with HFO relative to those without. In this case, binary classifiers have been tested on a set of energy features. The second step aimed to classify these segments into ripples, fast ripples and fast ripples occurring during ripples. Results suggest that LDA applied to 10 ms segmentation could provide the highest sensitivity (0.874) and 0.776 specificity for the discrimination of HFOs from no-HFO segments. Regarding the three-class classification, non-linear methods provided the highest values (around 90%) in terms of specificity and sensitivity, significantly different to the other three employed algorithms. Therefore, this machine-learning-based procedure could help clinicians to automatically reduce the quantity of irrelevant data.

[1]  Brian Litt,et al.  High-Frequency Oscillations Detected in Epileptic Networks Using Swarmed Neural-Network Features , 2007, Annals of Biomedical Engineering.

[2]  Marko Munih,et al.  A survey of methods for data fusion and system adaptation using autonomic nervous system responses in physiological computing , 2012, Interact. Comput..

[3]  Lucia Rita Quitadamo,et al.  Kurtosis-Based Detection of Intracranial High-Frequency Oscillations for the Identification of the Seizure Onset Zone , 2018, Int. J. Neural Syst..

[4]  Abdennaceur Kachouri,et al.  Detection of High Frequency Oscillations (HFOs) in the 80–500 Hz range in epilepsy recordings using decision tree analysis , 2014, International Image Processing, Applications and Systems Conference.

[5]  Jean Gotman,et al.  The morphology of high frequency oscillations (HFO) does not improve delineating the epileptogenic zone , 2016, Clinical Neurophysiology.

[6]  Fabio Martinelli,et al.  Driver and Path Detection through Time-Series Classification , 2018 .

[7]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[8]  J. Martinerie,et al.  Mapping interictal oscillations greater than 200 Hz recorded with intracranial macroelectrodes in human epilepsy. , 2010, Brain : a journal of neurology.

[9]  G. Mathern,et al.  Removing interictal fast ripples on electrocorticography linked with seizure freedom in children , 2010, Neurology.

[10]  Matthias Dümpelmann,et al.  Automatic 80–250Hz “ripple” high frequency oscillation detection in invasive subdural grid and strip recordings in epilepsy by a radial basis function neural network , 2012, Clinical Neurophysiology.

[11]  C. R. Rao,et al.  The Utilization of Multiple Measurements in Problems of Biological Classification , 1948 .

[12]  Blair A. Lock,et al.  Determining the Optimal Window Length for Pattern Recognition-Based Myoelectric Control: Balancing the Competing Effects of Classification Error and Controller Delay , 2011, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[13]  T. Pohlert.  The Pairwise Multiple Comparison of Mean Ranks Package (PMCMR) , 2016 .

[14]  Jan Cimbalnik,et al.  Progress and Remaining Challenges in the Application of High Frequency Oscillations as Biomarkers of Epileptic Brain. , 2017, Current opinion in biomedical engineering.

[15]  Ravishankar K. Iyer,et al.  Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy , 2018, Journal of neural engineering.

[16]  Héctor Pomares,et al.  Window Size Impact in Human Activity Recognition , 2014, Sensors.

[17]  C. Doshi,et al.  Methods for detecting high-frequency oscillations in ongoing brain signals: Application to the determination of epileptic seizure onset zones , 2011 .

[18]  Abdennaceur Kachouri,et al.  A Comparaison of Methods for Detection of High Frequency Oscillations (HFOs) in Human Intacerberal EEG Recordings , 2013 .

[19]  Han Yuan,et al.  Automated Detection of High Frequency Oscillations in Intracranial EEG Using the Combination of Short-Time Energy and Convolutional Neural Networks , 2019, IEEE Access.

[20]  A. Bragin,et al.  Localizing epileptogenic regions using high-frequency oscillations and machine learning. , 2019, Biomarkers in medicine.

[21]  Jeffery A. Hall,et al.  Interictal high‐frequency oscillations (80–500 Hz) are an indicator of seizure onset areas independent of spikes in the human epileptic brain , 2008, Epilepsia.

[22]  Abdennaceur Kachouri,et al.  Biomedical Signal Processing and Control Automated Detection and Classification of High Frequency Oscillations (hfos) in Human Intracereberal Eeg , 2022 .

[23]  S. Hong,et al.  High Frequency Oscillations in Epilepsy: Detection Methods and Considerations in Clinical Application , 2019, Journal of epilepsy research.

[24]  E. Basar,et al.  Wavelet entropy: a new tool for analysis of short duration brain electrical signals , 2001, Journal of Neuroscience Methods.

[25]  Mark B. Bromberg,et al.  Updating motor unit number estimation (MUNE) , 2007, Clinical Neurophysiology.

[26]  Jean Gotman,et al.  Automatic detector of High Frequency Oscillations for human recordings with macroelectrodes , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[27]  J. Jefferys,et al.  High‐frequency oscillations as a new biomarker in epilepsy , 2012, Annals of neurology.

[28]  J. S. Cramer.  The Origins of Logistic Regression , 2002 .

[29]  Justin A. Blanco,et al.  Unsupervised classification of high-frequency oscillations in human neocortical epilepsy and control patients. , 2010, Journal of neurophysiology.

[30]  Marcel van Gerven,et al.  Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges , 2018, ArXiv.

[31]  Thomas Grunwald,et al.  Resection of high frequency oscillations predicts seizure outcome in the individual patient , 2017, Scientific Reports.

[32]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[33]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[34]  S. García,et al.  An Extension on "Statistical Comparisons of Classifiers over Multiple Data Sets" for all Pairwise Comparisons , 2008 .

[35]  Mahsa Shoaran,et al.  Energy-Efficient Classification for Resource-Constrained Biomedical Applications , 2018, IEEE Journal on Emerging and Selected Topics in Circuits and Systems.

[36]  B. Brinkmann,et al.  Pathological and physiological high-frequency oscillations in focal human epilepsy. , 2013, Journal of neurophysiology.

[37]  Bernardino Castillo-Toledo,et al.  An algorithm for on-line detection of high frequency oscillations related to epilepsy , 2013, Comput. Methods Programs Biomed..

[38]  Lei Ding,et al.  Channel-Wise Characterization of High Frequency Oscillations for Automated Identification of the Seizure Onset Zone , 2020, IEEE Access.

[39]  Haibo He,et al.  ADASYN: Adaptive synthetic sampling approach for imbalanced learning , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[40]  J. M. Lina,et al.  Recording and analysis techniques for high-frequency oscillations , 2012, Progress in Neurobiology.

[41]  Fabrice Wendling,et al.  Classification of high frequency oscillations in epileptic intracerebral EEG , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[42]  Fabrice Wendling,et al.  Automatic Detection and Classification of High-Frequency Oscillations in Depth-EEG Signals , 2017, IEEE Trans. Biomed. Eng..

[43]  Ying Liang,et al.  Automated Detection of High-Frequency Oscillations in Epilepsy Based on a Convolutional Neural Network , 2019, Front. Comput. Neurosci..

[44]  Dan Wang,et al.  Automated Detector of High Frequency Oscillations in Epilepsy Based on Maximum Distributed Peak Points , 2018, Int. J. Neural Syst..

[45]  J. Gotman,et al.  High-frequency oscillations (HFOs) in clinical epilepsy , 2012, Progress in Neurobiology.

[46]  Michel Le Van Quyen,et al.  RIPPLELAB: A Comprehensive Application for the Detection, Analysis and Classification of High Frequency Oscillations in Electroencephalographic Signals , 2016, PloS one.

[47]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[48]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[49]  Tommaso Fedele,et al.  Automatic detection of high frequency oscillations during epilepsy surgery predicts seizure outcome , 2016, Clinical Neurophysiology.

[50]  C. Bénar,et al.  Pitfalls of high-pass filtering for detecting epileptic oscillations: A technical note on “false” ripples , 2010, Clinical Neurophysiology.

[51]  Charles L. Wilson,et al.  Quantitative analysis of high-frequency oscillations (80-500 Hz) recorded in human epileptic hippocampus and entorhinal cortex. , 2002, Journal of neurophysiology.

[52]  Michel Le Van Quyen,et al.  Epileptogenic Actions of GABA and Fast Oscillations in the Developing Hippocampus , 2005, Neuron.

[53]  Jean Gotman,et al.  High Frequency Oscillations and spikes: Separating real HFOs from false oscillations , 2016, Clinical Neurophysiology.

[54]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[55]  Michael I. Jordan,et al.  Machine learning: Trends, perspectives, and prospects , 2015, Science.