N. Mammone

Wavelet-ICA methodology for efficient artifact removal from Electroencephalographic recordings

Electroencephalographic (EEG) recordings are often contaminated by the artifacts, signals that have non-cerebral origin and that might mimic cognitive or pathologic activity and therefore distort the analysis of EEG. In this paper the issue of artifact extraction from Electroencephalographic data is addressed and a new technique for EEG artifact removal, based on the joint use of Wavelet transform and Independent Component Analysis (WICA), is presented and compared to two other techniques based on ICA and wavelet denoising. An artificial artifact-laden EEG dataset was created mixing a real EEG with a set of synthesized artifacts. This dataset was processed by WICA and the two other methods. The proposed technique had the best artifact separation performance for every kind of artifact also allowing for the minimum information loss.

Brain Activity Investigation by EEG Processing: Wavelet Analysis, Kurtosis and Renyi's Entropy for Artifact Detection

Electroencephalographic (EEG) recordings are employed in order to investigate the brain activity in neuro pathological subjects. Unfortunately EEG are often contaminated by the artifacts, signals that have non-cerebral origin and that might mimic cognitive or pathologic activity and therefore distort the analysis of EEG. In this paper we propose a multiresolution analysis, based on EEG wavelet processing, to extract the cerebral EEG rhythms. We also present a method based on Renyis entropy and kurtosis to automatically identify the Wavelet components affected by artifacts. Finally, we discuss as the joint use of wavelet analysis, kurtosis and Renyis entropy allows for a deeper investigation of the brain activity and we discuss the capability of this technique to become an efficient preprocessing step to optimize artifact rejection from EEG. This is the first technique that exploits the peculiarities of EEG to optimize EEG artifact detection.

PCA–ICA for automatic identification of critical events in continuous coma-EEG monitoring

Abstract Continuous monitoring of the electroencephalogram (EEG) provides information about the condition of the brain of a patient in coma and about the effects of therapy. For these reasons it is exploited to monitor cerebral events in coma patients. Declaring a patient “dead” is a very tricky procedure and it requires a long-time monitoring during which the doctor visually inspects the EEG tracings looking for any waves (critical events) that might account for restart of cerebral activity. Because of this, coma-EEG are very long and sometimes the huge size of data to be visually inspected makes the detection of critical events troublesome. A procedure for automatic critical events identification might support the doctor in the continuous monitoring of coma patients. This is why the performance of a technique, recently proposed by the authors, capable of automatically quantifying how much an EEG epoch is critical, is analysed in this paper. The technique is based on the extraction of descriptive components from overlapping EEG data segments (epochs) and on the extraction of some features from the components: entropy and kurtosis. This analysis was applied to a 3xa0h continuous coma-EEG and allowed for the detection of critical epochs that were worth being carefully inspected by the expert in order to ascertain whether they accounted for brain activity restart or not. Moreover, the step of descriptive components extraction was performed in three different ways: by Principal Component Analysis (PCA), by Independent Component Analysis (ICA) and the by the joint use of PCA–ICA. Finally the performance of the automatic detection were compared.

SVM classification of epileptic EEG recordings through multiscale permutation entropy

Electroencephalogram (EEG) is a non-invasive diagnostic tool in clinical neurophysiology, especially with respect to epilepsy. The epileptic status is characterized by reduced complexity. New markers, based on nonlinear dynamics, like Permutation Entropy (PE) have been developed to measure EEG complexity. In this paper, Multiscale Permutation Entropy (MPE) complexity measure is proposed as a potentially useful framework for detecting epileptic events in EEG data and to distinguish healthy controls from patients. The achieved results show that: 1) MPE is able to discriminate between the two categories; 2) the use of multiple scales may substantially improve the specificity of the diagnosis. This is shown through an SVM-based classification network with three different kernels. The use of the SVM approach is also useful to infer clues about the extracted features.

A Feasibility Study of Using the NeuCube Spiking Neural Network Architecture for Modelling Alzheimer’s Disease EEG Data

The paper presents a feasibility analysis of a novel Spiking Neural Network (SNN) architecture called NeuCube [10] for classification and analysis of functional changes in brain activity of Electroencephalography (EEG) data collected amongst two groups: control and Alzheimer’s Disease (AD). Excellent classification results of 100% test accuracy have been achieved and these have also been compared with traditional machine learning techniques. Outputs confirmed that the NeuCube is better suited to model, classify, interpret and understand EEG data and the brain processes involved. Future applications of a NeuCube model are discussed including its use as an indicator of the early onset of Mild Cognitive Impairment(MCI) to study degeneration of the pathology toward AD.

Algorithms and topographic mapping for epileptic seizures recognition and prediction

Epileptic seizures seem to result from an abnormal synchronization of different areas of the brain, as if a kind of recruitment occurred from a critical area towards other areas of the brain, until the brain can no longer bear the extent of this recruitment and it triggers the seizure in order to reset this abnormal condition. In order to catch these recruitment phenomena, a technique based on entropy is introduced to study the synchronization of the electric activity of neuronal sources in the brain. This technique was tested over 25 EEG dataset from patients affected by absence seizures as well as on 40 EEG dataset from healthy subjects. The results show an abnormal coupling among the electrodes that will be involved in seizure development can be hypothesized before the seizure itself, in particular, the frontal/temporal area appears steadily associated to an underlying high synchrony in absence seizure patients.

Artifact cancellation from electrocardiogram by mixed Wavelet-ICA filter

In this paper a novel method, called WICA, based on the joint use of wavelet transform (WT) and independent component analysis (ICA) is discussed. The main advantage of this method is that it encompasses the characteristics of WT and ICA. In order to show the novelty of our method, we present a biomedical signal processing application in which ICA has poor performances, whereas WICA yields good results. In particular, we discuss the artifact cancellation in electrocardiographic (ECG) signals. The results show the ability of WICA to cancel some artifact from ECG when only two signals are recorded.

Independent component and wavelet analysis for fECG extraction: the stwaveform evaluation

The aim of fetal monitoring is to identify fetuses at risk of an adverse outcome based on the ability to understand how the fetus reacts to stress before it becomes compromised. Recent works have shown that the ST waveform of the fetal electrocardiogram (fECG) provides continuous information on the capacity of the fetal heart muscle to respond to the stress of labour. The fECG can be ob- tained by a non-invasive technique that consists in collecting elec- trical signals by some sensors on the body of the mother. Unfortu- nately the fetal heartbeat signal yielded by this recording technique is quite weaker than the mother heartbeat signal, also due to the atten- uation during the propagation caused by the tissues; moreover, many other artifacts are superimposed to the two heartbeats. In this paper we propose a method based on wavelet decomposition and indepen- dent component analysis in order to approximate the real shape of the fECG. We also try to evaluate the ST waveform for fetal monitoring.

Dynamic Modeling of Heart Dipole Vector for the ECG and VCG Generation

The electrocardiogram (ECG) is the major diagnostic instrument for the analysis of cardiac electrophysiology; this is due to two simple reasons, first because it is not invasive and secondly because an ECG is a source of accurate information about the heart functionality. For these reasons, in the last years, the ECG has attracted the interest of many scientists, who have developed algorithms and models to investigate the cardiac disorders. The aim of this paper is to introduce a novel dynamic model to simulate pathologic ECGs. We discuss a generalization of a well known model for normal ECG signals generation and we show that it can be extended to simulate the effects on ECG of some cardiac diseases. We also represent the 3D vector trajectory of the cardiac cycle by reconstructing the heart dipole vector (HDV) from the Frank lead system. Finally, we propose to generate the complete 12-lead ECG system by the HDV projection. The results shows this a powerful tool for pathologic ECG generation, future research will be devoted to set up an extensive synthetic ECG database which could open the door to new theories about the genesis of the ECG as well as new models of heart functionality.

Automatic detection of critical epochs in coma-EEG using independent component analysis and higher order statistics

Previous works showed that the joint use of Principal Component Analysis (PCA) and Independent Component Analysis (ICA) allows to extract a few meaningful dominant components from the EEG of patients in coma. A procedure for automatic critical epoch detection might support the doctor in the long time monitoring of the patients, this is why we are headed to find a procedure able to automatically quantify how much an epoch is critical or not. In this paper we propose a procedure based on the extraction of some features from the dominant components: the entropy and the kurtosis. This feature analysis allowed us to detect some epochs that are likely to be critical and that are worth inspecting by the expert in order to assess the possible restarting of the brain activity.