A Novel MEGNet for Classification of High-Frequency Oscillations in Magnetoencephalography of Epileptic Patients

Epilepsy is a neurological disease, and the location of a lesion before neurosurgery or invasive intracranial electroencephalography (iEEG) surgery using intracranial electrodes is often very challenging. The high-frequency oscillation (HFOs) mode in MEG signal can now be used to detect lesions. Due to the time-consuming and error-prone operation of HFOs detection, an automatic HFOs detector with high accuracy is very necessary in modern medicine. Therefore, an optimized capsule neural network was used, and a MEG (magnetoencephalograph) HFOs detector based on MEGNet was proposed to facilitate the clinical detection of HFOs. To the best of our knowledge, this is the first time that a neural network has been used to detect HFOs in MEG. After optimized configuration, the accuracy, precision, recall, and F1-score of the proposed detector reached 94%, 95%, 94%, and 94%, which were better than other classical machine learning models. In addition, we used the k-fold cross-validation scheme to test the performance consistency of the model. The distribution of various performance indicators shows that our model is robust.

Download Full-text

Interictal high frequency background activity as a biomarker of epileptogenic tissue

Brain Communications ◽

10.1093/braincomms/fcab188 ◽

2021 ◽

Author(s):

Truman Stovall ◽

Brian Hunt ◽

Simon Glynn ◽

William C Stacey ◽

Stephen V Gliske

Keyword(s):

Logistic Regression ◽

Confidence Interval ◽

High Frequency ◽

High Frequency Oscillation ◽

Epileptogenic Zone ◽

Odds Ratios ◽

Seizure Onset ◽

High Frequency Oscillations ◽

Seizure Onset Zone ◽

Background Data

Abstract High Frequency Oscillations are very brief events that are a well-established biomarker of the epileptogenic zone, but are rare and comprise only a tiny fraction of the total recorded EEG. We hypothesize that the interictal high frequency “background” data, which has received little attention but represents the majority of the EEG record, also may contain additional, novel information for identifying the epileptogenic zone. We analyzed intracranial EEG (30–500 Hz frequency range) acquired from 24 patients who underwent resective surgery. We computed 38 quantitative features based on all usable, interictal data (63–307 hours per subject), excluding all detected high frequency oscillations. We assessed association between each feature and the seizure onset zone and resected volume using logistic regression. A pathology score per channel was also created via principle component analysis and logistic regression, using hold-out-one-patient cross validation to avoid in-sample training. Association of the pathology score with the seizure onset zone and resected volume was quantified using an asymmetry measure. Many features were associated with the seizure onset zone: 23/38 features had odds ratios >1.3 or < 0.7 and 17/38 had odds ratios different than zero with high significance (p < 0.001/39, logistic regression with Bonferroni Correction). The pathology score, the rate of high frequency oscillations, and their channel-wise product were each strongly associated with the seizure onset zone (median asymmetry > =0.44, good surgery outcome patients; median asymmetry > =0.40, patients with other outcomes; 95% confidence interval > 0.27 in both cases). The pathology score and the channel-wise product also had higher asymmetry with respect to the seizure onset zone than the high frequency oscillation rate alone (median difference in asymmetry > =0.18, 95% confidence interval >0.05). These results support that the high frequency background data contains useful information for determining the epileptogenic zone, distinct and complementary to information from detected high frequency oscillations. The concordance between the high frequency activity pathology score and the rate of high frequency oscillations appears to be a better biomarker of epileptic tissue than either measure alone.

Download Full-text

High-Frequency Oscillations in Somatosensory System

Clinical EEG and Neuroscience ◽

10.1177/155005940503600407 ◽

2005 ◽

Vol 36 (4) ◽

pp. 278-284 ◽

Cited By ~ 5

Author(s):

Hitoshi Mochizuki ◽

Yoshikazu Ugawa

Keyword(s):

High Frequency ◽

Neurological Diseases ◽

Somatosensory System ◽

Pyramidal Cells ◽

High Frequency Oscillation ◽

Medial Lemniscus ◽

High Frequency Oscillations ◽

Primary Sensory Cortex ◽

Thalamocortical Projection ◽

Deep Brain

The recent revival of interest in high-frequency oscillation (HFO) is triggered by getting an opportunity to noninvasively monitor the timing of highly synchronized and rapidly repeating population spikes generated in the human somatosensory system. HFOs could be recorded from brainstem, cuneothalamic relay neurons, thalamus, thalamocortical radiation, thalamocortical terminals and cortex with deep brain or surface electrodes, or with magnetoencephalography. Here we briefly review the HFOs at each level of somatosensory pathways. HFOs recorded at brainstem might be produced by volume conduction from oscillations of the medial lemniscus. Thalamic HFOs at around 1000 Hz frequency would be generated within the somatosensory thalamus. Cortical HFOs would be generated by at least a few different mechanisms, thalamocortical projection terminals, interneurons and pyramidal cells of the primary sensory cortex. HFOs have been studied in several ways: their modulation by arousal changes, movements or drugs, their recovery function, effects of transcranial magnetic stimulation on them and also their changes in patients with various neurological diseases.

Download Full-text

Convolutional Neural Network Classification of Telematics Car Driving Data

Risks ◽

10.3390/risks7010006 ◽

2019 ◽

Vol 7 (1) ◽

pp. 6 ◽

Cited By ~ 9

Author(s):

Guangyuan Gao ◽

Mario Wüthrich

Keyword(s):

Neural Network ◽

Neural Networks ◽

Time Series ◽

Convolutional Neural Network ◽

High Frequency ◽

Location Data ◽

Neural Network Classification ◽

Feature Information ◽

Car Driving

The aim of this project is to analyze high-frequency GPS location data (second per second) of individual car drivers (and trips). We extract feature information about speeds, acceleration, deceleration, and changes of direction from this high-frequency GPS location data. Time series of this feature information allow us to appropriately allocate individual car driving trips to selected drivers using convolutional neural networks.

Download Full-text

Feature selection for neural network based defect classification of ceramic components using high frequency ultrasound

Ultrasonics ◽

10.1016/j.ultras.2015.05.027 ◽

2015 ◽

Vol 62 ◽

pp. 271-277 ◽

Cited By ~ 15

Author(s):

Manasa Kesharaju ◽

Romesh Nagarajah

Keyword(s):

Neural Network ◽

Feature Selection ◽

High Frequency ◽

Defect Classification ◽

High Frequency Ultrasound ◽

Ceramic Components ◽

Selection For ◽

Frequency Ultrasound

Download Full-text

Dual mechanisms of ictal high frequency oscillations in human rhythmic onset seizures

10.1101/2020.04.07.030205 ◽

2020 ◽

Author(s):

Elliot H. Smith ◽

Edward M. Merricks ◽

Jyun-You Liou ◽

Camilla Casadei ◽

Lucia Melloni ◽

...

Keyword(s):

High Frequency ◽

Activity Patterns ◽

Field Potential ◽

Information Theoretic ◽

High Frequency Oscillations ◽

Epileptiform Discharges ◽

Before And After ◽

Spatial Domains ◽

Intracranial Electrodes ◽

Seizure Localization

ABSTRACTHigh frequency oscillations (HFOs) recorded from intracranial electrodes during epileptiform discharges are a proposed biomarker of epileptic brain tissue and may also be useful for seizure forecasting, with mixed results. Despite such potential for HFOs, there is limited investigation into the spatial context of HFOs and their relationship to simultaneously recorded neuronal activity. We sought to further understand the biophysical underpinnings of ictal HFOs using unit recordings in the human neocortex and mesial temporal lobe during rhythmic onset seizures. We compare features of ictal discharges in both the seizure core and penumbra (spatial seizure domains defined by multiunit activity patterns). We report differences in spectral features, unit-local field potential coupling, and information theoretic characteristics of HFOs before and after local seizure invasion. Furthermore, we tie these timing-related differences to spatial domains of seizures, showing that penumbral discharges are widely distributed and less useful for seizure localization.

Download Full-text

Epilepsy Surgery for Refractory Focal Epilepsy based on the Analysis of High Frequency Oscillations with Intracranial Electroencephalography : A Case Report

Japanese Journal of Neurosurgery ◽

10.7887/jcns.24.32 ◽

2015 ◽

Vol 24 (1) ◽

pp. 32-39

Author(s):

Akihiko Kondo ◽

Tomoyuki Akiyama ◽

Takashi Agari ◽

Makio Oka ◽

Yoshinori Kobayashi ◽

...

Keyword(s):

Case Report ◽

Epilepsy Surgery ◽

High Frequency ◽

Focal Epilepsy ◽

High Frequency Oscillations ◽

Intracranial Electroencephalography

Download Full-text

Localization of the Epileptogenic Zone by Multimodal Neuroimaging and High-Frequency Oscillation

Frontiers in Human Neuroscience ◽

10.3389/fnhum.2021.677840 ◽

2021 ◽

Vol 15 ◽

Author(s):

Xiaonan Li ◽

Tao Yu ◽

Zhiwei Ren ◽

Xueyuan Wang ◽

Jiaqing Yan ◽

...

Keyword(s):

Surgical Outcome ◽

High Frequency ◽

Refractory Epilepsy ◽

Automated Analysis ◽

Diagnostic Value ◽

High Frequency Oscillation ◽

Epileptogenic Zone ◽

Frequency Oscillation ◽

Traditional Methods ◽

Intracranial Electrodes

Accurate localization of the epileptogenic zone (EZ) is a key factor to obtain good surgical outcome for refractory epilepsy patients. However, no technique, so far, can precisely locate the EZ, and there are barely any reports on the combined application of multiple technologies to improve the localization accuracy of the EZ. In this study, we aimed to explore the use of a multimodal method combining PET-MRI, fluid and white matter suppression (FLAWS)—a novel MRI sequence, and high-frequency oscillation (HFO) automated analysis to delineate EZ. We retrospectively collected 15 patients with refractory epilepsy who underwent surgery and used the above three methods to detect abnormal brain areas of all patients. We compared the PET-MRI, FLAWS, and HFO results with traditional methods to evaluate their diagnostic value. The sensitivities, specificities of locating the EZ, and marking extent removed versus not removed [RatioChann(ev)] of each method were compared with surgical outcome. We also tested the possibility of using different combinations to locate the EZ. The marked areas in every patient established using each method were also compared to determine the correlations among the three methods. The results showed that PET-MRI, FLAWS, and HFOs can provide more information about potential epileptic areas than traditional methods. When detecting the EZs, the sensitivities of PET-MRI, FLAWS, and HFOs were 68.75, 53.85, and 87.50%, and the specificities were 80.00, 33.33, and 100.00%. The RatioChann(ev) of HFO-marked contacts was significantly higher in patients with good outcome than those with poor outcome (p< 0.05). When intracranial electrodes covered all the abnormal areas indicated by neuroimaging with the overlapping EZs being completely removed referred to HFO analysis, patients could reach seizure-free (p < 0.01). The periphery of the lesion marked by neuroimaging may be epileptic, but not every lesion contributes to seizures. Therefore, approaches in multimodality can detect EZ more accurately, and HFO analysis may help in defining real epileptic areas that may be missed in the neuroimaging results. The implantation of intracranial electrodes guided by non-invasive PET-MRI and FLAWS findings as well as HFO analysis would be an optimized multimodal approach for locating EZ.

Download Full-text

Identification of Motor and Mental Imagery EEG in Two and Multiclass Subject-Dependent Tasks Using Successive Decomposition Index

Sensors ◽

10.3390/s20185283 ◽

2020 ◽

Vol 20 (18) ◽

pp. 5283 ◽

Cited By ~ 1

Author(s):

Muhammad Tariq Sadiq ◽

Xiaojun Yu ◽

Zhaohui Yuan ◽

Muhammad Zulkifal Aziz

Keyword(s):

Neural Network ◽

Mental Imagery ◽

Practical Applications ◽

The Public ◽

Series Of Experiments ◽

Neural Network Classifiers ◽

Public Datasets ◽

Dependent Tasks ◽

First Time

The development of fast and robust brain–computer interface (BCI) systems requires non-complex and efficient computational tools. The modern procedures adopted for this purpose are complex which limits their use in practical applications. In this study, for the first time, and to the best of our knowledge, a successive decomposition index (SDI)-based feature extraction approach is utilized for the classification of motor and mental imagery electroencephalography (EEG) tasks. First of all, the public datasets IVa, IVb, and V from BCI competition III were denoised using multiscale principal analysis (MSPCA), and then a SDI feature was calculated corresponding to each trial of the data. Finally, six benchmark machine learning and neural network classifiers were used to evaluate the performance of the proposed method. All the experiments were performed for motor and mental imagery datasets in binary and multiclass applications using a 10-fold cross-validation method. Furthermore, computerized automatic detection of motor and mental imagery using SDI (CADMMI-SDI) is developed to describe the proposed approach practically. The experimental results suggest that the highest classification accuracy of 97.46% (Dataset IVa), 99.52% (Dataset IVb), and 99.33% (Dataset V) was obtained using feedforward neural network classifier. Moreover, a series of experiments, namely, statistical analysis, channels variation, classifier parameters variation, processed and unprocessed data, and computational complexity, were performed and it was concluded that SDI is robust for noise, and a non-complex and efficient biomarker for the development of fast and accurate motor and mental imagery BCI systems.

Download Full-text

Stable high frequency background EEG activity distinguishes epileptic from healthy brain regions

Brain Communications ◽

10.1093/braincomms/fcaa107 ◽

2020 ◽

Vol 2 (2) ◽

Author(s):

Annika Minthe ◽

Wibke G Janzarik ◽

Daniel Lachner-Piza ◽

Peter Reinacher ◽

Andreas Schulze-Bonhage ◽

...

Keyword(s):

High Frequency ◽

Background Activity ◽

Sleep Stage ◽

Strong Association ◽

Brain Regions ◽

High Frequency Oscillation ◽

Seizure Onset ◽

High Frequency Oscillations ◽

Seizure Onset Zone ◽

Low Entropy

Abstract High-frequency oscillations are markers of epileptic tissue. Recently, different patterns of EEG background activity were described from which high-frequency oscillations occur: high-frequency oscillations with continuously oscillating background were found to be primarily physiological, those from quiet background were linked to epileptic tissue. It is unclear, whether these interactions remain stable over several days and during different sleep-wake stages. High-frequency oscillation patterns (oscillatory vs. quiet background) were analysed in 23 patients implanted with depth and subdural grid electrodes. Pattern scoring was performed on every channel in 10 s intervals in three separate day- and night-time EEG segments. An entropy value, measuring variability of patterns per channel, was calculated. A low entropy value indicated a stable occurrence of the same pattern in one channel, whereas a high value indicated pattern instability. Differences in pattern distribution and entropy were analysed for 143 280 10 s intervals with allocated patterns from inside and outside the seizure onset zone, different electrode types and brain regions. We found a strong association between high-frequency oscillations out of quiet background activity, and channels of the seizure onset zone (35.2% inside versus 9.7% outside the seizure onset zone, P < 0.001), no association was found for high-frequency oscillations from continuous oscillatory background (P = 0.563). The type of background activity remained stable over the same brain region over several days and was independent of sleep stage and recording technique. Stability of background activity was significantly higher in channels of the seizure onset zone (entropy mean value 0.56 ± 0.39 versus 0.64 ± 0.41; P < 0.001). This was especially true for the presumed epileptic high-frequency oscillations out of quiet background (0.57 ± 0.39 inside versus 0.72 ± 0.37 outside the seizure onset zone; P < 0.001). In contrast, presumed physiological high-frequency oscillations from continuous oscillatory backgrounds were significantly more stable outside the seizure onset zone (0.72 ± 0.45 versus 0.48 ± 0.53; P < 0.001). The overall low entropy values suggest that interactions between high-frequency oscillations and background activity are a stable phenomenon specific to the function of brain regions. High-frequency oscillations occurring from a quiet background are strongly linked to the seizure onset zone whereas high-frequency oscillations from an oscillatory background are not. Pattern stability suggests distinct underlying mechanisms. Analysing short time segments of high-frequency oscillations and background activity could help distinguishing epileptic from physiologically active brain regions.

Download Full-text