A multi-level wavelet approach for automatic detection of epileptic spikes in the electroencephalogram

A self-adapting system for the automated detection of inter-ictal epileptiform discharges

PURPOSE

Scalp EEG remains the standard clinical procedure for the diagnosis of epilepsy. Manual detection of inter-ictal epileptiform discharges (IEDs) is slow and cumbersome, and few automated methods are used to assist in practice. This is mostly due to low sensitivities, high false positive rates, or a lack of trust in the automated method. In this study we aim to find a solution that will make computer assisted detection more efficient than conventional methods, while preserving the detection certainty of a manual search.

METHODS

Our solution consists of two phases. First, a detection phase finds all events similar to epileptiform activity by using a large database of template waveforms. Individual template detections are combined to form "IED nominations", each with a corresponding certainty value based on the reliability of their contributing templates. The second phase uses the ten nominations with highest certainty and presents them to the reviewer one by one for confirmation. Confirmations are used to update certainty values of the remaining nominations, and another iteration is performed where ten nominations with the highest certainty are presented. This continues until the reviewer is satisfied with what has been seen. Reviewer feedback is also used to update template accuracies globally and improve future detections.

KEY FINDINGS

Using the described method and fifteen evaluation EEGs (241 IEDs), one third of all inter-ictal events were shown after one iteration, half after two iterations, and 74%, 90%, and 95% after 5, 10 and 15 iterations respectively. Reviewing fifteen iterations for the 20-30 min recordings 1 took approximately 5 min.

SIGNIFICANCE

The proposed method shows a practical approach for combining automated detection with visual searching for inter-ictal epileptiform activity. Further evaluation is needed to verify its clinical feasibility and measure the added value it presents.

Model-based spike detection of epileptic EEG data

Accurate automatic spike detection is highly beneficial to clinical assessment of epileptic electroencephalogram (EEG) data. In this paper, a new two-stage approach is proposed for epileptic spike detection. First, the k-point nonlinear energy operator (k-NEO) is adopted to detect all possible spike candidates, then a newly proposed spike model with slow wave features is applied to these candidates for spike classification. Experimental results show that the proposed system, using the AdaBoost classifier, outperforms the conventional method in both two- and three-class EEG pattern classification problems. The proposed system not only achieves better accuracy for spike detection, but also provides new ability to differentiate between spikes and spikes with slow waves. Though spikes with slow waves occur frequently in epileptic EEGs, they are not used in conventional spike detection. Identifying spikes with slow waves allows the proposed system to have better capability for assisting clinical neurologists in routine EEG examinations and epileptic diagnosis.

A physiology-based seizure detection system for multichannel EEG

Background

Epilepsy is a common chronic neurological disorder characterized by recurrent unprovoked seizures. Electroencephalogram (EEG) signals play a critical role in the diagnosis of epilepsy. Multichannel EEGs contain more information than do single-channel EEGs. Automatic detection algorithms for spikes or seizures have traditionally been implemented on single-channel EEG, and algorithms for multichannel EEG are unavailable.

Methodology

This study proposes a physiology-based detection system for epileptic seizures that uses multichannel EEG signals. The proposed technique was tested on two EEG data sets acquired from 18 patients. Both unipolar and bipolar EEG signals were analyzed. We employed sample entropy (SampEn), statistical values, and concepts used in clinical neurophysiology (e.g., phase reversals and potential fields of a bipolar EEG) to extract the features. We further tested the performance of a genetic algorithm cascaded with a support vector machine and post-classification spike matching.

Principal Findings

We obtained 86.69% spike detection and 99.77% seizure detection for Data Set I. The detection system was further validated using the model trained by Data Set I on Data Set II. The system again showed high performance, with 91.18% detection of spikes and 99.22% seizure detection.

Conclusion

We report a de novo EEG classification system for seizure and spike detection on multichannel EEG that includes physiology-based knowledge to enhance the performance of this type of system.

Automated quantification of spikes

Methods for rapid and objective quantification of interictal spikes in raw, unprocessed electroencephalogram (EEG) samples are scarce. We evaluated the accuracy of a tailored automated spike quantification algorithm. The automated quantification was compared with the quantification by two board-certified clinical neurophysiologists (gold-standard) in five steps: 1) accuracy in a single EEG channel (5 EEG samples), 2) accuracy in multiple EEG channels and across different stages of the sleep-wake cycles (75 EEG samples), 3) capacity to detect lateralization of spikes (6 EEG samples), 4) accuracy after application of a machine-learning mechanism (11 EEG samples), and 5) accuracy during wakefulness only (8 EEG samples). Our method was accurate during all stages of the sleep-wake cycle and improved after the application of the machine-learning mechanism. Spikes were correctly lateralized in all cases. Our automated method was accurate in quantifying and detecting the lateralization of interictal spikes in raw unprocessed EEG samples.

Morphology-based wavelet features and multiple mother wavelet strategy for spike classification in EEG signals

New wavelet-derived features and strategies that can improve autonomous EEG classifier performance are presented. Various feature sets based on the morphological structure of wavelet subband coefficients are derived and evaluated. The performance of these new feature sets is superior to Guler's classic features in both sensitivity and specificity. In addition, the use of (scalp electrode) spatial information is also shown to improve EEG classification. Finally, a new strategy based upon concurrent use of several mother wavelets is shown to result in increased sensitivity and specificity. Various attempts at reducing feature vector dimension are shown. A non-parametric method, k-NNR, is implemented for classification and 10-fold cross-validation is used for assessment.

Standardized database development for EEG epileptiform transient detection: EEGnet scoring system and machine learning analysis

The routine scalp electroencephalogram (rsEEG) is the most common clinical neurophysiology procedure. The most important role of rsEEG is to detect evidence of epilepsy, in the form of epileptiform transients (ETs), also known as spike or sharp wave discharges. Due to the wide variety of morphologies of ETs and their similarity to artifacts and waves that are part of the normal background activity, the task of ET detection is difficult and mistakes are frequently made. The development of reliable computerized detection of ETs in the EEG could assist physicians in interpreting rsEEGs. We report progress in developing a standardized database for testing and training ET detection algorithms. We describe a new version of our EEGnet software system for collecting expert opinion on EEG datasets, a completely web-browser based system. We report results of EEG scoring from a group of 11 board-certified academic clinical neurophysiologists who annotated 30-s excepts from rsEEG recordings from 100 different patients. The scorers had moderate inter-scorer reliability and low to moderate intra-scorer reliability. In order to measure the optimal size of this standardized rsEEG database, we used machine learning models to classify paroxysmal EEG activity in our database into ET and non-ET classes. Based on our results, it appears that our database will need to be larger than its current size. Also, our non-parametric classifier, an artificial neural network, performed better than our parametric Bayesian classifier. Of our feature sets, the wavelet feature set proved most useful for classification.

Spike detection in the preterm fetal sheep EEG using Haar wavelet analysis

Perinatal hypoxia is a significant cause of brain injury in preterm infants. Neuroprotective treatments have proven beneficial when commenced within 6-8 hours post hypoxic-ischemic insult. However, as the exact time of injury is unknown, there are no current means to determine which infants are in the treatment phase of the evolving injury. Recent studies suggest epileptiform transients in the first 6-8 hours are predictive of outcome. To quantify this further an automated means of transient identification is required. In this paper we describe a method using Haar wavelets to detect spikes in the preterm fetal sheep EEG after asphyxia in utero. The method exhibits good sensitivity and selectivity over 3 specific time periods and demonstrates the feasibility of using wavelets for spike detection in fetal sheep.

DFAspike: a new computational proposition for efficient recognition of epileptic spike in EEG

An automated method has been presented for the detection of epileptic spikes in the electroencephalogram (EEG) using a deterministic finite automata (DFA) and has been named as DFAspike. EEG data (sampled, 256 Hz) files are the inputs to the DFAspike. The DFAspike was tested with different data files containing epileptic spikes. The obtained recognition rate of epileptic spike was 99.13% on an average. This system does not require any kind of prior training or human intrusion. The result shows that the designed system can be very effectively used for the detection of spikes present in the recorded EEG signals.

Quantifying time-varying multiunit neural activity using entropy based measures

Modern micro-electrode arrays make it possible to simultaneously record population neural activity. However, methods to analyze multiunit activity (MUA), which reflects the aggregate spiking activity of a population of neurons, have remained underdeveloped in comparison to those used for studying single unit activity (SUA). In scenarios where SUA is hard to record and maintain or is not representative of brains response, MUA is informative in deciphering the brains complex time-varying response to stimuli or to clinical insults. Here, we present two quantitative methods of analysis of the time-varying dynamics of MUA without spike detection. These methods are based on the multiresolution discrete wavelet transform (DWT) of an envelope of MUA followed by information theoretic measures: multiresolution entropy (MRE) and the multiresolution Kullback-Leibler distance (MRKLD). We test the proposed quantifiers on both simulated and experimental MUA recorded from rodent cortex in an experimental model of global hypoxic-ischemic brain injury. First, our results validate the use of the envelope of MUA as an alternative to detecting and analyzing transient and complex spike activity. Second, the MRE and MRKLD are shown to respond to dynamic changes due to the brains response to global injury and to identify the transient changes in the MUA.

SVM detection of epileptiform activity in routine EEG

Routine electroencephalogram (EEG) is an important test in aiding the diagnosis of patients with suspected epilepsy. These recordings typically last 20-40 minutes, during which signs of abnormal activity (spikes, sharp waves) are looked for in the EEG trace. It is essential that events of short duration are detected during the routine EEG test. The work presented in this paper examines the effect of changing a range of input values to the detection system on its ability to distinguish between normal and abnormal EEG activity. It is shown that the length of analysis window in the range of 0.5s to 1s are well suited to the task. Additionally, it is reported that patient specific systems should be used where possible due to their better performance.

An accuracy aware low power wireless EEG unit with information content based adaptive data compression

We present a digital system for adaptive data compression for low power wireless transmission of Electroencephalography (EEG) data. The proposed system acts as a base-band processor between the EEG analog-to-digital front-end and RF transceiver. It performs a real-time accuracy energy trade-off for multi-channel EEG signal transmission by controlling the volume of transmitted data. We propose a multi-core digital signal processor for on-chip processing of EEG signals, to detect signal information of each channel and perform real-time adaptive compression. Our analysis shows that the proposed approach can provide significant savings in transmitter power with minimal impact on the overall signal accuracy.