Neonatal EEG Seizure Research Articles

Deep Learning for Generalized EEG Seizure Detection after Hypoxia-Ischemia-Preclinical Validation.

Brain maturity and many clinical treatments such as therapeutic hypothermia (TH) can significantly influence the morphology of neonatal EEG seizures after hypoxia-ischemia (HI), and so there is a need for generalized automatic seizure identification. This study validates efficacy of advanced deep-learning pattern classifiers based on a convolutional neural network (CNN) for seizure detection after HI in fetal sheep and determines the effects of maturation and brain cooling on their accuracy. The cohorts included HI-normothermia term (n = 7), HI-hypothermia term (n = 14), sham-normothermia term (n = 5), and HI-normothermia preterm (n = 14) groups, with a total of >17,300 h of recordings. Algorithms were trained and tested using leave-one-out cross-validation and k-fold cross-validation approaches. The accuracy of the term-trained seizure detectors was consistently excellent for HI-normothermia preterm data (accuracy = 99.5%, area under curve (AUC) = 99.2%). Conversely, when the HI-normothermia preterm data were used in training, the performance on HI-normothermia term and HI-hypothermia term data fell (accuracy = 98.6%, AUC = 96.5% and accuracy = 96.9%, AUC = 89.6%, respectively). Findings suggest that HI-normothermia preterm seizures do not contain all the spectral features seen at term. Nevertheless, an average 5-fold cross-validated accuracy of 99.7% (AUC = 99.4%) was achieved from all seizure detectors. This significant advancement highlights the reliability of the proposed deep-learning algorithms in identifying clinically translatable post-HI stereotypic seizures in 256Hz recordings, regardless of maturity and with minimal impact from hypothermia.

Neonatal EEG seizure detection using a new signal structural complexity measure based on matching pursuit decomposition with nonstationary dictionary

Background and objectiveIn newborns, it is often difficult to accurately differentiate between seizure and non-seizure based solely on clinical manifestations. This highlights the importance of electroencephalogram (EEG) in the recognition and management of neonatal seizures. This paper proposes an effective algorithm for the detection of neonatal seizure using multichannel EEG. MethodsNeonatal EEG changes morphology as it alternates between seizure and non-seizure states. A new signal complexity measure based on matching pursuit (MP) decomposition is proposed and used to detect transitions between these two states. The new measure, referred to as weighted structural complexity (WSC), was used for the detection of seizures in 30 newborn EEG records. Multiple IIR filters and an MP-based filter were designed and used to remove artifacts from the EEG data. Geometrical correlation between the EEG data channels was applied to reduce the number of false detections caused by remnant artifacts. The seizure detector's performance was assessed using several epoch-based (e.g., accuracy) and event-based (GDR = good detection rate and FD/h = false detections per hour) metrics. ResultsCompared to the neurologist marking, the proposed detector was able to detect EEG seizures with 94% accuracy, 90.9% GDR, and 0.14 FD/h (95% CI: [0.06, 0.34]). ConclusionsThe high performance of the MP-based detector may have significant implications for the accurate diagnosis of neonatal seizures and the appropriate use of anticonvulsants and ongoing clinical assessment and care of the newborn.

Robustness of time frequency distribution based features for automated neonatal EEG seizure detection.

In this paper we examined the robustness of a feature-set based on time-frequency distributions (TFDs) for neonatal EEG seizure detection. This feature-set was originally proposed in literature for neonatal seizure detection using a support vector machine (SVM). We tested the performance of this feature-set with a smoothed Wigner-Ville distribution and modified B distribution as the underlying TFDs. The seizure detection system using time-frequency signal and image processing features from the TFD of the EEG signal using modified B distribution was able to achieve a median receiver operator characteristic area of 0.96 (IQR 0.91-0.98) tested on a large clinical dataset of 826 h of EEG data from 18 full-term newborns with 1389 seizures. The mean AUC was 0.93.

Risk factors for EEG seizures in neonates treated with hypothermia

To assess the risk factors for electrographic seizures among neonates treated with therapeutic hypothermia for hypoxic-ischemic encephalopathy (HIE). Three-center observational cohort study of 90 term neonates treated with hypothermia, monitored with continuous video-EEG (cEEG) within the first day of life (median age at onset of recording 9.5 hours, interquartile range 6.3-14.5), and continued for >24 hours (total recording 93.3 hours, interquartile range 80.1-112.8 among survivors). A pediatric electroencephalographer at each site reviewed cEEGs for electrographic seizures and initial EEG background category. A total of 43 (48%) had electrographic seizures, including 9 (10%) with electrographic status epilepticus. Abnormal initial EEG background classification (excessively discontinuous, depressed and undifferentiated, burst suppression, or extremely low voltage), but not clinical variables (including pH <6.8, base excess ≤-20, or 10-minute Apgar ≤ 3), was strongly associated with seizures. Electrographic seizures are common among neonates with HIE undergoing hypothermia and are difficult to predict based on clinical features. These results justify the recommendation for cEEG monitoring in neonates treated with hypothermia.

Effective implementation of time–frequency matched filter with adapted pre and postprocessing for data-dependent detection of newborn seizures

Neonatal EEG seizures often manifest as nonstationary and multicomponent signals, necessitating analysis in the time–frequency (TF) domain. This paper presents a novel neonatal seizure detector based on effective implementation of the TF matched filter. In the detection process, the TF signatures of EEG seizure are extracted to construct the TF templates used by the matched filter. Matching pursuit (MP) decomposition and narrowband filtering are proposed for the reduction of artifacts prior to seizure detection. Geometrical correlation is used to consolidate the multichannel detections and to reduce the number of false detections due to remnant artifacts. A data-dependent threshold is defined for the classification of EEG. Using 30 newborn EEG records with seizures, the classification process yielded an overall detection accuracy of 92.4% with good detection rate (GDR) of 84.8% and false detection rate of 0.36FD/h. Better detection performance (accuracy >95%) was recorded for relatively long EEG records with short seizure events.

A nonparametric feature for neonatal EEG seizure detection based on a representation of pseudo-periodicity

AbstractAutomated methods of neonatal EEG seizure detection attempt to highlight the evolving, stereotypical, pseudo-periodic, nature of EEG seizure while rejecting the nonstationary, modulated, coloured stochastic background in the presence of various EEG artefacts. An important aspect of neonatal seizure detection is, therefore, the accurate representation and detection of pseudo-periodicity in the neonatal EEG. This paper describes a method of detecting pseudo-periodic components associated with neonatal EEG seizure based on a novel signal representation; the nonstationary frequency marginal (NFM). The NFM can be considered as an alternative time-frequency distribution (TFD) frequency marginal. This method integrates the TFD along data-dependent, time-frequency paths that are automatically extracted from the TFD using an edge linking procedure and has the advantage of reducing the dimension of a TFD. The reduction in dimension simplifies the process of estimating a decision statistic designed for the detection of the pseudo-periodicity associated with neonatal EEG seizure. The use of the NFM resulted in a significant detection improvement compared to existing stationary and nonstationary methods. The decision statistic estimated using the NFM was then combined with a measurement of EEG amplitude and nominal pre- and post-processing stages to form a seizure detection algorithm. This algorithm was tested on a neonatal EEG database of 18 neonates, 826h in length with 1389 seizures, and achieved comparable performance to existing second generation algorithms (a median receiver operating characteristic area of 0.902; IQR 0.835–0.943 across 18 neonates).

Fast activity during EEG seizures in neonates

Paroxysmal fast activity (FA) has been proposed as a marker for epileptic networks. We explore the presence and significance of ictal FA on scalp video EEG seizures (EEG Sz) recorded in neonates. Forty two babies had 159 EEG Szs. The seizures were analysed for ictal FA, using a low frequency filter of 30 Hz. We explored the relationship of ictal FA to the occurrence of electroclinical and electrographic seizures, the use of phenobarbitone and to neurodevelopmental outcomes. Ictal FA occurred in 62 (39%) of the 159 EEG Szs. In the 62 seizures with ictal FA, 34 (55%) were electroclinical seizures (ECSz) and 28 (45%) were electrographic (ESz). In the remaining 97 seizures without ictal FA, 27 (28%) were ECSz and 70 (72%) ESz. There was a significant correlation (p=0.0006) between ictal FA and electroclinical seizures. There was no relationship between phenobarbitone and presence of ictal FA. There was no significant difference in the background EEG, neuroimaging abnormalities, neurodevelopmental impairment or post neonatal seizures between those with and without ictal FA. Ictal FA is highly correlated to the occurrence of clinical features during an EEG seizure. The presence of ictal FA does not appear to influence neurodevelopmental outcomes.

A Multistage System for the Automated Detection of Epileptic Seizures in Neonatal Electroencephalography

This paper describes the design and test results of a three-stage automated system for neonatal EEG seizure detection. Stage I of the system is the initial detection stage and identifies overlapping 5-second segments of suspected seizure activity in each EEG channel. In stage II, the detected segments from stage I are spatiotemporally clustered to produce multichannel candidate seizures. In stage III, the candidate seizures are processed further using measures of quality and context-based rules to eliminate false candidates. False candidates because of artifacts and commonly occurring EEG background patterns such as bifrontal delta activity are also rejected. Seizures at least 10 seconds in duration are considered for reporting results. The testing data consisted of recordings of 28 seizure subjects (34 hours of data) and 48 nonseizure subjects (87 hours of data) obtained in the neonatal intensive care unit. The data were not edited to remove artifacts and were identical in every way to data normally processed visually. The system was able to detect seizures of widely varying morphology with an average detection sensitivity of almost 80% and a subject sensitivity of 96%, in comparison with a team of clinical neurophysiologists who had scored the same recordings. The average false detection rate obtained in nonseizure subjects was 0.74 per hour.

Defining the gap between electrographic seizure burden, clinical expression and staff recognition of neonatal seizures

Background:Neonatal seizures are often subclinical, making accurate diagnosis difficult.Objective:To describe the clinical manifestations of electrographic seizures recorded on continuous video-EEG, and to compare this description with the recognition of clinical...

Time–frequency based newborn EEG seizure detection using low and high frequency signatures

The nonstationary and multicomponent nature of newborn EEG seizures tend to increase the complexity of the seizure detection problem. In dealing with this type of problem, time–frequency based techniques were shown to outperform classical techniques. Neonatal EEG seizures have signatures in both low frequency (lower than 10 Hz) and high frequency (higher than 70 Hz) areas. Seizure detection techniques have been proposed that concentrate on either low frequency or high frequency signatures of seizures. They, however, tend to miss seizures that reveal themselves only in one of the frequency areas. To overcome this problem, we propose a detection method that uses time–frequency seizure features extracted from both low and high frequency areas. Results of applying the proposed method on five newborn EEGs are very encouraging.

SVD-based newborn EEG seizure detection in the time-frequency domain

This paper utilises the Singular Value Decomposition (SVD) technique applied to the time-frequency representation of Electroencephalogram (EEG) signals for detecting EEG seizures in neonates. Seizure in EEG signal may have signature in different frequency areas. This paper, is concentrated on the low frequency (lower than 10 Hz) signature of the seizures. The proposed technique uses the estimated distribution function of the singular vectors associated with the time-frequency representation of the EEG epoch to characterise the patterns embedded in the signal. The estimated distributed functions related to the seizure and nonseizure epochs were used to train a neural network to discriminate between seizure and nonseizure patterns.

Wavelet analysis for neonatal electroencephalographic seizures

Electroencepholographs (EEGs) of neonatal seizures differ from those of children and adults. This study evaluated whether wavelet transform analysis, a nonstationary frequency analysis of EEG, can recognize and characterize neonatal seizures. Twenty-second segments were analyzed from 69 EEG seizures in 15 neonatal patients whose seizures lasted 10 seconds or longer. The wavelet transform results were examined, as were EEG seizure durations and dominant frequencies. The wavelet transform results were correlated with the occurrence, after an 18-month follow-up, of postneonatal seizures. Wavelet transform analysis identified 40 seizures (58%) with a “sustained dominant frequency component” that lasted 10 seconds or longer and 29 seizures without a sustained dominant frequency component. The mean seizure duration of the 40 seizures with sustained dominant frequency components was 63.3 seconds, longer than the mean duration (33.6 seconds) of the seizures without sustained dominant frequency components, P < 0.01. Eleven patients manifested postneonatal epileptic seizures. Fifty-two EEG seizures in these 11 patients revealed more sustained dominant frequency components (74%) than 17 seizures in the 4 patients without postneonatal seizures (only 12%), P < 0.05. Wavelet transform analysis can identify neonatal EEG seizures and characterize their epileptic components. The presence of sustained dominant frequency components may predict postneonatal epileptic seizures.Kitayama M, Otsubo H, Parvez S, Lodha A, Ying E, Parvez B, Ishii R, Mizuno-Matsumoto Y, Zoroofi RA, Snead OC III. Wavelet analysis for neonatal electroencephalographic seizures.