A multistage, multimethod approach for automatic detection and classification of epileptiform EEG

A review of signal processing and machine learning techniques for interictal epileptiform discharge detection

Brain interictal epileptiform discharges (IEDs), as one of the hallmarks of epileptic brain, are transient events captured by electroencephalogram (EEG). IEDs are generated by seizure networks, and they occur between seizures (interictal periods). The development of a robust method for IED detection could be highly informative for clinical treatment procedures and epileptic patient management. Since 1972, different machine learning techniques, from template matching to deep learning, have been developed to automatically detect IEDs from scalp EEG (scEEG) and intracranial EEG (iEEG). While the scEEG signals suffer from low information details and high attenuation of IEDs due to the high skull electrical impedance, the iEEG signals recorded using implanted electrodes enjoy higher details and are more suitable for identifying the IEDs. In this review paper, we group IED detection techniques into six categories: (1) template matching, (2) feature representation (mimetic, time-frequency, and nonlinear features), (3) matrix decomposition, (4) tensor factorization, (5) neural networks, and (6) estimation of the iEEG from the concurrent scEEG followed by detection and classification. The methods are compared quantitatively (e.g., in terms of accuracy, sensitivity, and specificity), and their general advantages and limitations are described. Finally, current limitations and possible future research paths related to this field are mentioned.

Computerized application for epilepsy in China: Does the era of artificial intelligence comes?

Epilepsy, one of the most common neurological diseases in China, is notorious for its spontaneous, unprovoked and recurrent seizures. The etiology of epilepsy varies among individual patients, including congenital gene mutation, traumatic injury, infections, etc. This heterogeneity partly hampered the accurate diagnosis and choice of appropriate treatments. Encouragingly, great achievements have been achieved in computational science, making it become a key player in medical fields gradually and bringing new hope for rapid and accurate diagnosis as well as targeted therapies in epilepsy. Here, we historically review the advances of computerized applications in epilepsy-especially those tremendous findings achieved in China-for different purposes including seizure prediction, localization of epileptogenic zone, post-surgical prognosis, etc. Special attentions are paid to the great progress based on artificial intelligence (AI), which is more "sensitive", "smart" and "in-depth" than human capacities. At last, we give a comprehensive discussion about the disadvantages and limitations of current computerized applications for epilepsy and propose some future directions as further stepping stones to embrace "the era of AI" in epilepsy.

Machine learning for detection of interictal epileptiform discharges

The electroencephalogram (EEG) is a fundamental tool in the diagnosis and classification of epilepsy. In particular, Interictal Epileptiform Discharges (IEDs) reflect an increased likelihood of seizures and are routinely assessed by visual analysis of the EEG. Visual assessment is, however, time consuming and prone to subjectivity, leading to a high misdiagnosis rate and motivating the development of automated approaches. Research towards automating IED detection started 45 years ago. Approaches range from mimetic methods to deep learning techniques. We review different approaches to IED detection, discussing their performance and limitations. Traditional machine learning and deep learning methods have yielded the best results so far and their application in the field is still growing. Standardization of datasets and outcome measures is necessary to compare models more objectively and decide which should be implemented in a clinical setting.

Multi-channel EEG epileptic spike detection by a new method of tensor decomposition

OBJECTIVE

Epilepsy is one of the most common brain disorders. For epilepsy diagnosis or treatment, the neurologist needs to observe epileptic spikes from electroencephalography (EEG) data. Since multi-channel EEG records can be naturally represented by multi-way tensors, it is of interest to see whether tensor decomposition is able to analyze EEG epileptic spikes.

APPROACH

In this paper, we first proposed the problem of simultaneous multilinear low-rank approximation of tensors (SMLRAT) and proved that SMLRAT can obtain local optimum solutions by using two well-known tensor decomposition algorithms (HOSVD and Tucker-ALS). Second, we presented a new system for automatic epileptic spike detection based on SMLRAT.

MAIN RESULTS

We propose to formulate the problem of feature extraction from a set of EEG segments, represented by tensors, as the SMLRAT problem. Efficient EEG features were obtained, based on estimating the 'eigenspikes' derived from nonnegative GSMLRAT. We compared the proposed tensor analysis method with other common tensor methods in analyzing EEG signal and compared the proposed feature extraction method with the state-of-the-art methods. Experimental results indicated that our proposed method is able to detect epileptic spikes with high accuracy.

SIGNIFICANCE

Our method, for the first time, makes a step forward for automatic detection EEG epileptic spikes based on tensor decomposition. The method can provide a practical solution to distinguish epileptic spikes from artifacts in real-life EEG datasets.

A review on the pattern detection methods for epilepsy seizure detection from EEG signals

Over several years, research had been conducted for the detection of epileptic seizures to support an automatic diagnosis system to comfort the clinicians' encumbrance. In this regard, a number of research papers have been published for the identification of epileptic seizures. A thorough review of all these papers is required. So, an attempt has been made to review on the pattern detection methods for epilepsy seizure detection from EEG signals. More than 150 research papers have been discussed to determine the techniques for detecting epileptic seizures. Further, the literature review confirms that the pattern recognition techniques required to detect epileptic seizures varies across the electroencephalogram (EEG) datasets of different conditions. This is mostly owing to the fact that EEG detected under different conditions have different characteristics. This consecutively necessitates the identification of the pattern recognition technique to efficiently differentiate EEG epileptic data from the EEG data of various conditions.

Improved Patient-Independent System for Detection of Electrical Onset of Seizures

PURPOSE

To design a non-patient-specific system to detect the electrical onset of seizures in patients with temporal lobe epilepsy.

METHODS

We used EEG data from 29 seizures of 18 temporal lobe epilepsy patients who underwent multiday video-scalp EEG monitoring as part of their presurgical evaluations. We segmented each data set into preictal and ictal phases, and identified spectral entropy, spectral energy, and signal energy as useful features for discriminating normal and seizure conditions. The performance of five different classifiers was analyzed using these features to design an automated detection system.

RESULTS

Among the five classifiers, decision tree, k-nearest neighbor, and support vector machine performed with sensitivity (specificity) of 79% (81%), 75% (85%), and 80% (86%), respectively. The other two, linear discriminant algorithm and Naive Bayes classifiers, performed with sensitivity (specificity) of 54% (94%), 47% (96%), respectively.

CONCLUSIONS

The support vector machine-based seizure detection system showed better detection capability in terms of sensitivity and specificity measures as compared to linear discriminant algorithm, Naive Bayes, decision tree, and k-nearest neighbor classifiers.

CONCLUSIONS

Our study shows that a generalized system to detect the electrical onset of seizures in temporal lobe epilepsy using scalp-recorded EEG is possible. If confirmed on a larger data set, our findings may have significant implications for the management of seizures, especially in patients with drug-resistant epilepsy.

Epilepsy detection from EEG signals: a review

Over many decades, research is being attempted for the detection of epileptic seizure to support for automatic diagnosis system to help clinicians from burdensome work. In this respect, an enormous number of research papers is published for identification of epileptic seizure. It is difficult to present a detailed review of all these literature. Therefore, in this paper, an attempt has been made to review the detection of an epileptic seizure. More than 100 research papers have been discussed to discern the techniques for detecting the epileptic seizure. Further, the literature survey shows that the pattern recognition required to detect epileptic seizure varies with different conditions of EEG datasets. This is mainly due to the fact that EEG detected under different conditions has different characteristics. This is, in turn, necessitates the identification of pattern recognition technique to effectively distinguish EEG epileptic data from a various condition of EEG data.

Crowdsourcing seizure detection: algorithm development and validation on human implanted device recordings

There exist significant clinical and basic research needs for accurate, automated seizure detection algorithms. These algorithms have translational potential in responsive neurostimulation devices and in automatic parsing of continuous intracranial electroencephalography data. An important barrier to developing accurate, validated algorithms for seizure detection is limited access to high-quality, expertly annotated seizure data from prolonged recordings. To overcome this, we hosted a kaggle.com competition to crowdsource the development of seizure detection algorithms using intracranial electroencephalography from canines and humans with epilepsy. The top three performing algorithms from the contest were then validated on out-of-sample patient data including standard clinical data and continuous ambulatory human data obtained over several years using the implantable NeuroVista seizure advisory system. Two hundred teams of data scientists from all over the world participated in the kaggle.com competition. The top performing teams submitted highly accurate algorithms with consistent performance in the out-of-sample validation study. The performance of these seizure detection algorithms, achieved using freely available code and data, sets a new reproducible benchmark for personalized seizure detection. We have also shared a 'plug and play' pipeline to allow other researchers to easily use these algorithms on their own datasets. The success of this competition demonstrates how sharing code and high quality data results in the creation of powerful translational tools with significant potential to impact patient care.

An extensive review on development of EEG-based computer-aided diagnosis systems for epilepsy detection

Epilepsy is considered as fourth most prominent neurological disorder in the world that can affect people of all age groups. Currently, around 65 million people throughout the world are suffering from epilepsy. It is evident that electroencephalograph (EEG) signals are most commonly used for detection of epileptic seizures but today many modern techniques have been developed to analyze underlying features of these EEG signals. As EEG contains a large amount of complicated information, so many researchers are trying to develop automatic systems for complete feature extraction. This paper provides a generalized review and performance comparison of popular seizure detection algorithms that are developed in the last decade. The main objective of this paper is to briefly discuss all existing developments in the field of computer-aided diagnosis system for epilepsy detection so that future researchers can find a better track for the new invention.

Feature selection using angle modulated simulated Kalman filter for peak classification of EEG signals

In the existing electroencephalogram (EEG) signals peak classification research, the existing models, such as Dumpala, Acir, Liu, and Dingle peak models, employ different set of features. However, all these models may not be able to offer good performance for various applications and it is found to be problem dependent. Therefore, the objective of this study is to combine all the associated features from the existing models before selecting the best combination of features. A new optimization algorithm, namely as angle modulated simulated Kalman filter (AMSKF) will be employed as feature selector. Also, the neural network random weight method is utilized in the proposed AMSKF technique as a classifier. In the conducted experiment, 11,781 samples of peak candidate are employed in this study for the validation purpose. The samples are collected from three different peak event-related EEG signals of 30 healthy subjects; (1) single eye blink, (2) double eye blink, and (3) eye movement signals. The experimental results have shown that the proposed AMSKF feature selector is able to find the best combination of features and performs at par with the existing related studies of epileptic EEG events classification.

Evaluation of different time domain peak models using extreme learning machine-based peak detection for EEG signal

Various peak models have been introduced to detect and analyze peaks in the time domain analysis of electroencephalogram (EEG) signals. In general, peak model in the time domain analysis consists of a set of signal parameters, such as amplitude, width, and slope. Models including those proposed by Dumpala, Acir, Liu, and Dingle are routinely used to detect peaks in EEG signals acquired in clinical studies of epilepsy or eye blink. The optimal peak model is the most reliable peak detection performance in a particular application. A fair measure of performance of different models requires a common and unbiased platform. In this study, we evaluate the performance of the four different peak models using the extreme learning machine (ELM)-based peak detection algorithm. We found that the Dingle model gave the best performance, with 72 % accuracy in the analysis of real EEG data. Statistical analysis conferred that the Dingle model afforded significantly better mean testing accuracy than did the Acir and Liu models, which were in the range 37–52 %. Meanwhile, the Dingle model has no significant difference compared to Dumpala model.

Automatic Identification of Interictal Epileptiform Discharges in Secondary Generalized Epilepsy

Ictal epileptiform discharges (EDs) are characteristic signal patterns of scalp electroencephalogram (EEG) or intracranial EEG (iEEG) recorded from patients with epilepsy, which assist with the diagnosis and characterization of various types of epilepsy. The EEG signal, however, is often recorded from patients with epilepsy for a long period of time, and thus detection and identification of EDs have been a burden on medical doctors. This paper proposes a new method for automatic identification of two types of EDs, repeated sharp-waves (sharps), and runs of sharp-and-slow-waves (SSWs), which helps to pinpoint epileptogenic foci in secondary generalized epilepsy such as Lennox-Gastaut syndrome (LGS). In the experiments with iEEG data acquired from a patient with LGS, our proposed method detected EDs with an accuracy of 93.76% and classified three different signal patterns with a mean classification accuracy of 87.69%, which was significantly higher than that of a conventional wavelet-based method. Our study shows that it is possible to successfully detect and discriminate sharps and SSWs from background EEG activity using our proposed method.

Spike pattern recognition by supervised classification in low dimensional embedding space

Epileptiform discharges in interictal electroencephalography (EEG) form the mainstay of epilepsy diagnosis and localization of seizure onset. Visual analysis is rater-dependent and time consuming, especially for long-term recordings, while computerized methods can provide efficiency in reviewing long EEG recordings. This paper presents a machine learning approach for automated detection of epileptiform discharges (spikes). The proposed method first detects spike patterns by calculating similarity to a coarse shape model of a spike waveform and then refines the results by identifying subtle differences between actual spikes and false detections. Pattern classification is performed using support vector machines in a low dimensional space on which the original waveforms are embedded by locality preserving projections. The automatic detection results are compared to experts' manual annotations (101 spikes) on a whole-night sleep EEG recording. The high sensitivity (97 %) and the low false positive rate (0.1 min-1), calculated by intra-patient cross-validation, highlight the potential of the method for automated interictal EEG assessment.

Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization

Electroencephalogram (EEG) signal peak detection is widely used in clinical applications. The peak point can be detected using several approaches, including time, frequency, time-frequency, and nonlinear domains depending on various peak features from several models. However, there is no study that provides the importance of every peak feature in contributing to a good and generalized model. In this study, feature selection and classifier parameters estimation based on particle swarm optimization (PSO) are proposed as a framework for peak detection on EEG signals in time domain analysis. Two versions of PSO are used in the study: (1) standard PSO and (2) random asynchronous particle swarm optimization (RA-PSO). The proposed framework tries to find the best combination of all the available features that offers good peak detection and a high classification rate from the results in the conducted experiments. The evaluation results indicate that the accuracy of the peak detection can be improved up to 99.90% and 98.59% for training and testing, respectively, as compared to the framework without feature selection adaptation. Additionally, the proposed framework based on RA-PSO offers a better and reliable classification rate as compared to standard PSO as it produces low variance model.

Electroencephalography in mesial temporal lobe epilepsy: a review

Electroencephalography (EEG) has an important role in the diagnosis and classification of epilepsy. It can provide information for predicting the response to antiseizure drugs and to identify the surgically remediable epilepsies. In temporal lobe epilepsy (TLE) seizures could originate in the medial or lateral neocortical temporal region, and many of these patients are refractory to medical treatment. However, majority of patients have had excellent results after surgery and this often relies on the EEG and magnetic resonance imaging (MRI) data in presurgical evaluation. If the scalp EEG data is insufficient or discordant, invasive EEG recording with placement of intracranial electrodes could identify the seizure focus prior to surgery. This paper highlights the general information regarding the use of EEG in epilepsy, EEG patterns resembling epileptiform discharges, and the interictal, ictal and postictal findings in mesial temporal lobe epilepsy using scalp and intracranial recordings prior to surgery. The utility of the automated seizure detection and computerized mathematical models for increasing yield of non-invasive localization is discussed. This paper also describes the sensitivity, specificity, and predictive value of EEG for seizure recurrence after withdrawal of medications following seizure freedom with medical and surgical therapy.

Multiscale rescaled range analysis of EEG recordings in sevoflurane anesthesia

OBJECTIVE

The Hurst exponent (HE) is a nonlinear method measuring the smoothness of a fractal time series. In this study we applied the HE index, extracted from electroencephalographic (EEG) recordings, as a measure of anesthetic drug effects on brain activity.

METHODS

In 19 adult patients undergoing sevoflurane general anesthesia, we calculated the HE of the raw EEG; comparing the maximal overlap discrete wavelet transform (MODWT) with the traditional rescaled range (R/S) analysis techniques, and with a commercial index of depth of anesthesia - the response entropy (RE). We analyzed each wavelet-decomposed sub-band as well as the combined low frequency bands (HEOLFBs). The methods were compared in regard to pharmacokinetic/pharmacodynamic (PK/PD) modeling, and prediction probability.

RESULTS

All the low frequency band HE indices decreased when anesthesia deepened. However the HEOLFB was the best index because: it was less sensitive to artifacts, most closely tracked the exact point of loss of consciousness, showed a better prediction probability in separating the awake and unconscious states, and tracked sevoflurane concentration better - as estimated by the PK/PD models.

CONCLUSIONS

The HE is a useful measure for estimating the depth of anesthesia. It was noted that HEOLFB showed the best performance for tracking drug effect.

SIGNIFICANCE

The HEOLFB could be used as an index for accurately estimating the effect of anesthesia on brain activity.

Comparison of fractal dimension estimation algorithms for epileptic seizure onset detection

Fractal dimension (FD) is a natural measure of the irregularity of a curve. In this study the performances of three waveform FD estimation algorithms (i.e. Katz's, Higuchi's and the k-nearest neighbour (k-NN) algorithm) were compared in terms of their ability to detect the onset of epileptic seizures in scalp electroencephalogram (EEG). The selection of parameters involved in FD estimation, evaluation of the accuracy of the different algorithms and assessment of their robustness in the presence of noise were performed based on synthetic signals of known FD. When applied to scalp EEG data, Katz's and Higuchi's algorithms were found to be incapable of producing consistent changes of a single type (either a drop or an increase) during seizures. On the other hand, the k-NN algorithm produced a drop, starting close to the seizure onset, in most seizures of all patients. The k-NN algorithm outperformed both Katz's and Higuchi's algorithms in terms of robustness in the presence of noise and seizure onset detection ability. The seizure detection methodology, based on the k-NN algorithm, yielded in the training data set a sensitivity of 100% with 10.10 s mean detection delay and a false positive rate of 0.27 h(-1), while the corresponding values in the testing data set were 100%, 8.82 s and 0.42 h(-1), respectively. The above detection results compare favourably to those of other seizure onset detection methodologies applied to scalp EEG in the literature. The methodology described, based on the k-NN algorithm, appears to be promising for the detection of the onset of epileptic seizures based on scalp EEG.

Mapping interictal oscillations greater than 200 Hz recorded with intracranial macroelectrodes in human epilepsy

Interictal high-frequency oscillations over 200 Hz have been recorded with microelectrodes in the seizure onset zone of epileptic patients suffering from mesial temporal lobe epilepsy. Recent work suggests that similar high-frequency oscillations can be detected in the seizure onset zone using standard diagnostic macroelectrodes. However, only a few channels were examined in these studies, so little information is available on the spatial extent of high-frequency oscillations. Here, we present data on high-frequency oscillations recorded from a larger number of intracerebral contacts spatial (mean 38) in 16 patients. Data were obtained from 1 h of interictal recording sampled at 1024 Hz and was analysed using a new semi-automatic detection procedure based on a wavelet decomposition. A detailed frequency analysis permitted a rapid and reliable discrimination of high-frequency oscillations from other high-frequency events. A total of 1932 high-frequency oscillations were detected with an average frequency of 261 +/- 53 Hz, amplitude of 11.9 +/- 6.7 microV and duration of 22.7 +/- 11.6 ms. Records from a patient often showed several different high-frequency oscillation patterns. We classified 24 patterns from 11 patients. Usually (20/24 patterns) high-frequency oscillations were nested in an epileptic paroxysm, such as a spike or a sharp wave, and typically high-frequency oscillations (19/24) were recorded from just one recording contact. Unexpectedly in other cases, high-frequency oscillations (5/24) were detected simultaneously on two or three contacts, sometimes separated by large distances. This large spatial extent suggests that high-frequency oscillations may sometimes result from a neuronal synchrony manifest on a scale of centimetres. High-frequency oscillations were almost always recorded in seizure-generating structures of patients suffering from mesial (9/9) or polar (1/3) temporal lobe epilepsy. They were never found in the epileptic or healthy basal, lateral temporal or extra temporal neocortex nor in the healthy amygdalo-hippocampal complex. These findings confirm that the generation of oscillations at frequencies higher that 200 Hz is, at this scale, a specific, intrinsic property of seizure-generating networks in medial and polar temporal lobes, which have a common archaic phylogenetic origin. We show that this activity can be detected and its spatial extent determined with conventional intracranial electroencephalography electrodes in records from patients with temporal lobe epilepsy. It is a reliable marker of the seizure onset zone that should be considered in decisions on surgical treatment.

Bluetooth-based sensor networks for remotely monitoring the physiological signals of a patient

Integrating intelligent medical microsensors into a wireless communication network makes it possible to remotely collect physiological signals of a patient, release the patient from being tethered to monitoring medical instrumentations, and facilitate the patient's early hospital discharge. This can further improve life quality by providing continuous observation without the need of disrupting the patient's normal life, thus reducing the risk of infection significantly, and decreasing the cost of the hospital and the patient. This paper discusses the implementation issues, and describes the overall system architecture of our developed Bluetooth sensor network for patient monitoring and the corresponding heart activity sensors. It also presents our approach to developing the intelligent physiological sensor nodes involving integration of Bluetooth radio technology, hardware and software organization, and our solutions for onboard signal processing.

Assessment of computerized analysis algorithms for one dimension physiologic data with multiple databases

Software technology enables computerized analysis to offer second opinion in various screening and diagnostic tasks to assist the clinicians. Yet, the performance of these computerized methods for medical images is questioned by experts in CAD research, owing to the use of different databases and criteria for evaluating the computer results for comparison. This paper intends to substantiate this statement by illustrating the effects of such issues with the use of 1D physiologic data and multiple databases. For this purpose, the detection of desaturation events in Sp02 and spike events in EEG are used. This is the first time that comparison between different algorithms on a common basis is carried out on an individual effort. The appraisal for all the algorithms is made on the same databases and criteria. It is surprising to find that issues for 2/3D images concur with those found in 1D data here. In evaluating the accuracy of a new algorithm, a single independent database gives results fast. This paper reveals weaknesses of such an approach. It is hoped that the supportive evidence shown here is enough for researchers to innovate a better platform for credibility in reporting performance comparison of computerized analysis algorithms.

A semi-automated method for epileptiform transient detection in the EEG of the fetal sheep using time-frequency analysis

Perinatal hypoxia remains a significant cause of brain damage. Currently there are no biomarkers to detect the at risk brain. Recent research, however, suggests that the appearance of epileptiform transients in the first 6-8 hours after hypoxia (the latent phase of injury) are predictive of neural outcome. To quantify this further a key need is to automate EEG signal analysis to aid clinical staff with the vast amounts of complex data to review. In this study, we present a semi-automated method for spike detection in the fetal sheep EEG. The method utilizes the short time Fourier transform and peak separation to extract spikes. The performance of the method was found to be high in sensitivity and selectivity over 3 distinct time points.

Detection of focal epileptiform events in the EEG by spatio-temporal dipole clustering

OBJECTIVE

Methods for the detection of epileptiform events can be broadly divided into two main categories: temporal detection methods that exploit the EEG's temporal characteristics, and spatial detection methods that base detection on the results of an implicit or explicit source analysis. We describe how the framework of a spatial detection method was extended to improve its performance by including temporal information. This results in a method that provides (i) automated localization of an epileptogenic focus and (ii) detection of focal epileptiform events in an EEG recording. For the detection, only one threshold value needs to be set.

METHODS

The method comprises five consecutive steps: (1) dipole source analysis in a moving window, (2) automatic selection of focal brain activity, (3) dipole clustering to arrive at the identification of the epileptiform cluster, (4) derivation of a spatio-temporal template of the epileptiform activity, and (5) template matching. Routine EEG recordings from eight paediatric patients with focal epilepsy were labelled independently by two experts. The method was evaluated in terms of (i) ability to identify the epileptic focus, (ii) validity of the derived template, and (iii) detection performance. The clustering performance was evaluated using a leave-one-out cross validation. Detection performance was evaluated using Precision-Recall curves and compared to the performance of two temporal (mimetic and wavelet based) and one spatial (dipole analysis based) detection methods.

RESULTS

The method succeeded in identifying the epileptogenic focus in seven of the eight recordings. For these recordings, the mean distance between the epileptic focus estimated by the method and the region indicated by the labelling of the experts was 8mm. Except for two EEG recordings where the dipole clustering step failed, the derived template corresponded to the epileptiform activity marked by the experts. Over the eight EEGs, the method showed a mean sensitivity and selectivity of 92 and 77%, respectively.

CONCLUSIONS

The method allows automated localization of the epileptogenic focus and shows good agreement with the region indicated by the labelling of the experts. If the dipole clustering step is successful, the method allows a detection of the focal epileptiform events, and gave a detection performance comparable or better to that of the other methods.

SIGNIFICANCE

The identification and quantification of epileptiform events is of considerable importance in the diagnosis of epilepsy. Our method allows the automatic identification of the epileptic focus, which is of value in epilepsy surgery. The method can also be used as an offline exploration tool for focal EEG activity, displaying the dipole clusters and corresponding time series.

Spike separation from EEG/MEG data using morphological filter and wavelet transform

In the analysis of epileptic electroencephalographic (EEG) and magnetoencephalography (MEG) data, spike separation is diagnostically important because localization of epileptic focus often depends on accurate extraction of spiky activity from the raw data. In this paper, we present a method to automatically extract spikes using the wavelet transform combined with morphological filtering based on a circular structuring element. Our experimental results have shown that this method is highly effective in spike separation. Comparisons with the wavelet, bandpass filter, empirical mode decomposition (EMD), and independent component analysis (ICA) methods show that the new method is more effective in estimating both spike amplitudes and locations.

An automatic analysis method for detecting and eliminating ECG artifacts in EEG

An automated method for detecting and eliminating electrocardiograph (ECG) artifacts from electroencephalography (EEG) without an additional synchronous ECG channel is proposed in this paper. Considering the properties of wavelet filters and the relationship between wavelet basis and characteristics of ECG artifacts, the concepts for selecting a suitable wavelet basis and scales used in the process are developed. The analysis via the selected basis is without suffering time shift for decomposition and detection/elimination procedures after wavelet transformation. The detection rates, above 97.5% for MIT/BIH and NTUH recordings, show a pretty good performance in ECG artifact detection and elimination.

The EEG assessment of low-grade hepatic encephalopathy: Comparison of an artificial neural network-expert system (ANNES) based evaluation with visual EEG readings and EEG spectral analysis

OBJECTIVE

The EEG provides an objective staging of hepatic encephalopathy (HE), but its interpretation may be biased by inter-observer variability. This study aims at comparing an entirely automatic EEG classification of HE based on an artificial neural network-expert system procedure (ANNES) with visual and spectral analysis based EEG classifications.

METHODS

Two hundred and thirty-eight consecutive cirrhotic patients underwent closed-eye EEG. They were followed up for up to one-year to detect bouts of overt HE and death. The EEG was classified by ANNES, qualitative visual reading, main basic rhythm frequency and spectral analysis. The classifications were assessed on the basis of: (i) match with liver function, (ii) prognostic value and (iii) repeatability.

RESULTS

All classifications were found to be related to the severity of liver failure, with cognitive findings and a history of previous bouts of HE. All of them had prognostic value on the occurrence of overt HE and on survival. The ANNES based classification was more repeatable than the qualitative visual one, and had the advantage of detecting low power EEG, but its efficiency in analyzing low-grade alterations was questionable.

CONCLUSIONS

An entirely automatic - ANNES based - EEG classification of HE can improve the repeatability of EEG assessment, but further improvement of the device is required to classify mild alterations.

SIGNIFICANCE

The ANNES based EEG grading of HE needs further improvements to be recommended in clinical practice, but it is already sufficient for detecting normal and clearly altered EEG tracings.

SADE3: an effective system for automated detection of epileptiform events in long-term EEG based on context information

Interictal spike detection is a time-consuming, low-efficiency task, but is important to epilepsy diagnosis. Automated systems reported to date usually have their practical efficacy compromised by elevated rates of false-positive detections per minute, which are caused mainly by the influence of artifacts (such as noise activity and ocular movements) and by the adoption of single or simple approaches. This work describes the development of a hybrid system for automatic detection of spikes in long-term electroencephalogram (EEG), named System for Automatic Detection of Epileptiform Events in EEG (SADE(3)), which uses wavelet transform, neural networks and artificial intelligence procedures to recognize epileptic and to reject non-epileptic activity. The system's pre-processing stage filters the EEG epochs with the Coiflet wavelet function, which showed the closest correlation to epileptogenic (EPG) activity, in opposition to some other wavelet functions that did not correlate with these events. In contrast to current attempts using continuous wavelet transform, we chose to work with fast wavelet transform to reduce processing time and data volume. Detail components at appropriate decomposition levels were used to accentuate spikes, sharp waves, high-frequency noise activity and ocular artifacts. These four detailed components were used to train four specialized neural networks, designed to detect and classify the EPG and non-EPG events. An expert module analyzes the networks' outputs, together with multichannel and context information and concludes the detection. The system was evaluated with 126,000 EEG epochs, obtained from seven different patients during long-term monitoring, under diverse behavior and mental states. More than 6,721 spikes and sharp waves were previously identified by three experienced human electroencephalographers. In these tests, the SADE(3) system simultaneously achieved 70.9% sensitivity, 99.9% specificity and a rate of 0.13 false-positives per minute, indicating its usefulness and low vulnerability to artifact influence. After tests, the SADE(3) system showed itself to be able to process bipolar cortical EEG records, from long-term monitoring, up to 32 channels, without any data preparation or event positioning. At the same time, SADE(3) revealed a high capacity to reject non-epileptic paroxysms, robustness in relation to a variety of spike morphologies, flexibility in adjustment of performance rates and the capacity to actually save time during EEG reading. Furthermore, it can be adapted to other applications for pattern recognition, with simple adjustments.

Electroencephalographic staging of hepatic encephalopathy by an artificial neural network and an expert system

AIM OF THE STUDY

To provide an objective EEG assessment of hepatic encephalopathy (HE), we set up and tested an entirely automatic procedure based on an artificial neural network-expert system software (ANNESS).

PATIENTS AND METHODS

A training set sample of 50 EEG (group A) and a test sample of 50 EEG (group B) of 100 cirrhotic patients were considered. The EEGs had been visually classified by an expert electroencephalographer, using a modified five-degree Parsons-Simith classification of HE. The efficiency of the ANNESS, trained in group A, was tested in group B.

RESULTS

Both the ANNESS and the visually-based classifications were found to be correlated to liver insufficiency, as assessed by the Child-Pugh score (Spearman's coefficient rho=0.485, P<0.0001; rho=0.489, P<0.0001, respectively) and by the biochemical indexes of hepatic function (bilirubin: rho=0.31 vs. 0.27; albumin: rho=-0.13 vs. -0.18; prothrombin time rho=-0.35 vs. -0.52). The classifications were found to be correlated to each other (rho=0.84 P<0.0001, Cohen's kappa=0.55). However, the ANNESS overestimated grade 2 EEG alterations.

CONCLUSION

An ANNESS-based classification of EEG in HE provided data comparable with a visually-based classification, except for mild alterations (class 2) that tended to be overestimated. Further optimization of automatic EEG staging of HE is desirable, as well as a prospective clinical evaluation.

Epileptic spike detection using a Kalman filter based approach

The electroencephalogram (EEG) consists of an underlying background process with superimposed transient nonstationarities such as epileptic spikes (ESs). The detection of ESs in the EEG is of particular importance in the diagnosis of epilepsy. In this paper a new approach for detecting ESs in EEG recordings is presented. It is based on a time-varying autoregressive model (TVAR) that makes use of the nonstationarities of the EEG signal. The autoregressive (AR) parameters are estimated via Kalman filtering (KF). In our method, the EEG signal is first preprocessed to accentuate ESs and attenuate background activity, and then passed through a thresholding function to determine ES locations. The proposed method is evaluated using simulated signals as well as real inter-ictal EEGs.