Identification and monitoring of brain activity based on stochastic relevance analysis of short–time EEG rhythms

Abstract

BackgroundThe extraction of physiological rhythms from electroencephalography (EEG) data and their automated analyses are extensively studied in clinical monitoring, to find traces of interictal/ictal states of epilepsy.MethodsBecause brain wave rhythms in normal and interictal/ictal events, differently influence neuronal activity, our proposed methodology measures the contribution of each rhythm. These contributions are measured in terms of their stochastic variability and are extracted from a Short Time Fourier Transform to highlight the non–stationary behavior of the EEG data. Then, we performed a variability–based relevance analysis by handling the multivariate short–time rhythm representation within a subspace framework. This maximizes the usability of the input information and preserves only the data that contribute to the brain activity classification. For neural activity monitoring, we also developed a new relevance rhythm diagram that qualitatively evaluates the rhythm variability throughout long time periods in order to distinguish events with different neuronal activities.ResultsEvaluations were carried out over two EEG datasets, one of which was recorded in a noise–filled environment. The method was evaluated for three different classification problems, each of which addressed a different interpretation of a medical problem. We perform a blinded study of 40 patients using the support–vector machine classifier cross–validation scheme. The obtained results show that the developed relevance analysis was capable of accurately differentiating normal, ictal and interictal activities.ConclusionsThe proposed approach provides the reliable identification of traces of interictal/ictal states of epilepsy. The introduced relevance rhythm diagrams of physiological rhythms provides effective means of monitoring epileptic seizures; additionally, these diagrams are easily implemented and provide simple clinical interpretation. The developed variability–based relevance analysis can be translated to other monitoring applications involving time–variant biomedical data.

Analysis of EEG Signal Processing Techniques based on Spectrograms

“…The classification of an epileptic seizure [23] employs the extraction of Frequency Cepstral Coefficients and stochastic relevance analyses on spectrograms of different rhythms. SVM is applied, obtaining competitive accuracies for different datasets.…”

“…In section two, the steps to follow in the EEG analysis were presented. The first step removes artifacts and noise; a few experiments [19,23,25] apply low-pass and band-pass filters, which can be implemented easily, as the band frequencies are known. Most experiments do not apply this phase, although the datasets were acquired from the experiments.…”

“…GLCM y VF. From the different, it was noted that for the analysis of epilepsy diseases, there is a set of data that different authors [3,20,23,24] employ, for example use a dataset created by the University of Bonn with five different subsets (A-E), with 100 single channel signals, a duration of 26.3 seconds and a sampling frequency of 173.61 Hz. This database contains high quality information (number of studies, time and number of seizures), which were validated by experts.…”

“…This database contains high quality information (number of studies, time and number of seizures), which were validated by experts. Table 2 shows four works where this dataset was used; although only one implemented the preprocessing stage [23] and the accuracy obtained was between 95.78% and 100%.…”

Time-Frequency Analysis of EEG Spectrograms using 2-D Gabor Filters for Epileptic Seizure Classification

“…Epilepsy is a neurological disease or disorder distinguished by recurrent unprovoked seizures and caused by the transient and unexpected disturbance, occurring throughout the brain due to hypersynchronous neuronal discharges, which decrease and increase amplitudes of brain activity [7,21]. Epilepsy affects about 1-2% of the world population and it is divided into two types: focal epilepsy, which involves a part of the cerebral hemisphere and provokes symptoms in some parts of body or related with mental functions; the other kind of epilepsy is the generalized one, which involve the entire brain and produces bilateral motor symptoms, normally resulting in unconsciousness.…”