Nadia Mammone

Automatic Artifact Rejection From Multichannel Scalp EEG by Wavelet ICA

Electroencephalographic (EEG) recordings are often contaminated by artifacts, i.e., signals with noncerebral origin that might mimic some cognitive or pathologic activity, this way affecting the clinical interpretation of traces. Artifact rejection is, thus, a key analysis for both visual inspection and digital processing of EEG. Automatic artifact rejection is needed for effective real time inspection because manual rejection is time consuming. In this paper, a novel technique (Automatic Wavelet Independent Component Analysis, AWICA) for automatic EEG artifact removal is presented. Through AWICA we claim to improve the performance and fully automate the process of artifact removal from scalp EEG. AWICA is based on the joint use of the Wavelet Transform and of ICA: it consists of a two-step procedure relying on the concepts of kurtosis and Renyis entropy. Both synthesized and real EEG data are processed by AWICA and the results achieved were compared to the ones obtained by applying to the same data the “wavelet enhanced” ICA method recently proposed by other authors. Simulations illustrate that AWICA compares favorably to the other technique. The method here proposed is shown to yield improved success in terms of suppression of artifact components while reducing the loss of residual informative data, since the components related to relevant EEG activity are mostly preserved.

Enhanced automatic artifact detection based on independent component analysis and Renyi's entropy

Artifacts are disturbances that may occur during signal acquisition and may affect their processing. The aim of this paper is to propose a technique for automatically detecting artifacts from the electroencephalographic (EEG) recordings. In particular, a technique based on both Independent Component Analysis (ICA) to extract artifactual signals and on Renyis entropy to automatically detect them is presented. This technique is compared to the widely known approach based on ICA and the joint use of kurtosis and Shannons entropy. The novel processing technique is shown to detect on average 92.6% of the artifactual signals against the average 68.7% of the previous technique on the studied available database. Moreover, Renyis entropy is shown to be able to detect muscle and very low frequency activity as well as to discriminate them from other kinds of artifacts. In order to achieve an efficient rejection of the artifacts while minimizing the information loss, future efforts will be devoted to the improvement of blind artifact separation from EEG in order to ensure a very efficient isolation of the artifactual activity from any signals deriving from other brain tasks.

Permutation entropy of scalp EEG: a tool to investigate epilepsies: suggestions from absence epilepsies.

OBJECTIVE We used permutation entropy (PE) to disclose abnormalities of cerebral activity in patients with typical absences (TAs). METHODS We evaluated 24 EEG of TA patients and 40 EEG of healthy subjects. PE was estimated channel by channel, with electrodes being divided into high-PE cluster (high randomness), low-PE cluster (low randomness), and neutral cluster. We compared PE between EEG of patients and controls, and between interictal and ictal EEG of patients. RESULTS Patients showed a recurrent behavior of PE topography, with anterior brain regions constantly associated to high PE levels and posterior brain regions constantly associated to low PE levels, during both interictal and ictal phases. On the contrary, healthy controls had a random distribution of PE topography. CONCLUSIONS In patients with TAs, a higher randomness in fronto-temporal areas and a lower randomness in posterior areas occur during both interictal and ictal phases. Such abnormalities are in keeping with evidences from different morphological and functional studies showing multifocal brain changes in TA patients. SIGNIFICANCE PE seems to be a useful tool to disclose abnormalities of cerebral electric activity not revealed by conventional EEG recordings, opening interesting prospective for future studies.

Clustering of entropy topography in epileptic electroencephalography

Epileptic seizures have been considered sudden and unpredictable events for centuries. A seizure seems to occur when a massive group of neurons in the cerebral cortex begins to discharge in a highly organized rhythmic pattern, then it develops according to some poorly described dynamics. As proved by the results reported by different research groups, seizures appear not completely random and unpredictable events. Thus, it is reasonable to wonder when, where and why the epileptogenic processes start up in the brain and how they result in a seizure. In order to detect these phenomena from the very beginning (hopefully minutes before the seizure itself), we introduced a technique, based on entropy topography, that studies the synchronization of the electric activity of neuronal sources in the brain. We tested it over 3 EEG data set from patients affected by partial epilepsy and 25 EEG recordings from patients affected by generalized seizures as well as over 40 recordings from healthy subjects. Entropy showed a very steady spatial distribution and appeared linked to the brain zone where seizures originated. A self-organizing map-based spatial clustering of entropy topography showed that the critical electrodes shared the same cluster long time before the seizure onset. The healthy subjects showed a more random behaviour.

Deep Learning Representation from Electroencephalography of Early-Stage Creutzfeldt-Jakob Disease and Features for Differentiation from Rapidly Progressive Dementia.

A novel technique of quantitative EEG for differentiating patients with early-stage Creutzfeldt-Jakob disease (CJD) from other forms of rapidly progressive dementia (RPD) is proposed. The discrimination is based on the extraction of suitable features from the time-frequency representation of the EEG signals through continuous wavelet transform (CWT). An average measure of complexity of the EEG signal obtained by permutation entropy (PE) is also included. The dimensionality of the feature space is reduced through a multilayer processing system based on the recently emerged deep learning (DL) concept. The DL processor includes a stacked auto-encoder, trained by unsupervised learning techniques, and a classifier whose parameters are determined in a supervised way by associating the known category labels to the reduced vector of high-level features generated by the previous processing blocks. The supervised learning step is carried out by using either support vector machines (SVM) or multilayer neural networks (MLP-NN). A subset of EEG from patients suffering from Alzheimers Disease (AD) and healthy controls (HC) is considered for differentiating CJD patients. When fine-tuning the parameters of the global processing system by a supervised learning procedure, the proposed system is able to achieve an average accuracy of 89%, an average sensitivity of 92%, and an average specificity of 89% in differentiating CJD from RPD. Similar results are obtained for CJD versus AD and CJD versus HC.

Differentiating Interictal and Ictal States in Childhood Absence Epilepsy through Permutation Rényi Entropy

Permutation entropy (PE) has been widely exploited to measure the complexity of the electroencephalogram (EEG), especially when complexity is linked to diagnostic information embedded in the EEG. Recently, the authors proposed a spatial-temporal analysis of the EEG recordings of absence epilepsy patients based on PE. The goal here is to improve the ability of PE in discriminating interictal states from ictal states in absence seizure EEG. For this purpose, a parametrical definition of permutation entropy is introduced here in the field of epileptic EEG analysis: the permutation Renyi entropy (PEr). PEr has been extensively tested against PE by tuning the involved parameters (order, delay time and alpha). The achieved results demonstrate that PEr outperforms PE, as there is a statistically-significant, wider gap between the PEr levels during the interictal states and PEr levels observed in the ictal states compared to PE. PEr also outperformed PE as the input to a classifier aimed at discriminating interictal from ictal states.

Visualization and modelling of STLmax topographic brain activity maps

This paper evaluates the descriptive power of brain topography based on a dynamical parameter, the Short-Term Maximum Lyapunov Exponent (STLmax), estimated from EEG, for finding out a relationship of STLmax spatial distribution with the onset zone and with the mechanisms leading to epileptic seizures. Our preliminary work showed that visual assessment of STLmax topography exhibited a link with the location of seizure onset zone. The objective of the present work is to model the spatial distribution of STLmax in order to automatically extract these features from the maps. One-hour preictal segments from four long-term continuous EEG recordings (two scalp and two intracranial) were processed and the corresponding STLmax profiles were estimated. The spatial STLmax maps were modelled by a combination of two Gaussians functions. The parameters of the fitted model allow automatic extraction of quantitative information about the spatial distribution of STLmax: the EEG signal recorded from the brain region where seizures originate exhibited low-STLmax levels, long before the seizure onset, in 3 out of 4 patients (1 out of 2 of scalp patients and 2 out of 2 in intracranial patients). Topographic maps extracted directly from the EEG power did not provide useful information about the location, therefore we conclude that the analysis so far carried out suggests the possibility of using a model of STLmax topography as a tool for monitoring the evolution of epileptic brain dynamics. In the future, a more elaborate approach will be investigated in order to improve the specificity of the method.

Independent component analysis and high-order statistics for automatic artifact rejection

One of the aims of biomedical signal processing is to extract some features from the data in order to make diagnosis and to understand the biological phenomena but, often, a preprocessing step is essential because some unwelcome signals, the artifacts, are superimposed to the useful signals we want to analyse. Automatic artifact detection is a key topic, because we aim to automatically analyse and extract features from the data. In literature, independent component analysis (ICA) has been exploited for artifact isolation and the joint use of some high order statistics, kurtosis and Shannons entropy has been exploited to automatically detect the artifacts. In this paper we propose the joint use of kurtosis and Renyis entropy as a new tool for automatic detection and we show that it outperforms the other tool thanks to the features of the Renyis entropy

Visualization of the short term maximum Lyapunov exponent topography in the epileptic brain.

In this paper, a new kind of brain topography is introduced and applied to data from four patients affected by intractable epilepsy. Experience has shown that the short term maximum Lyapunov exponent (STLmax) is a robust parameter when optimized for the dynamical analysis of the electroencephalography (EEG). The objective of this work is to map the spatial distribution of STLmax over time. STLmax is estimated from segments of each channel of long term continuous scalp EEG recordings and a movie of the STLmax segment estimates is created over the head. Movies allow for a simple visualization of which electrodes are related to the highest or lowest chaoticity for the longest time. We found out that the interictal epileptiform activity is related to the highest STLmax level, whereas the focal area is related to low STLmax levels during either the interictal and preictal stages

Permutation Disalignment Index as an Indirect, EEG-Based, Measure of Brain Connectivity in MCI and AD Patients

OBJECTIVE In this work, we introduce Permutation Disalignment Index (PDI) as a novel nonlinear, amplitude independent, robust to noise metric of coupling strength between time series, with the aim of applying it to electroencephalographic (EEG) signals recorded longitudinally from Alzheimers Disease (AD) and Mild Cognitive Impaired (MCI) patients. The goal is to indirectly estimate the connectivity between the cortical areas, through the quantification of the coupling strength between the corresponding EEG signals, in order to find a possible matching with the diseases progression. METHOD PDI is first defined and tested on simulated interacting dynamic systems. PDI is then applied to real EEG recorded from 8 amnestic MCI subjects and 7 AD patients, who were longitudinally evaluated at time [Formula: see text]0 and 3 months later (time [Formula: see text]1). At time [Formula: see text]1, 5 out of 8 MCI patients were still diagnosed MCI (stable MCI) whereas the remaining 3 exhibited a conversion from MCI to AD (prodromal AD). PDI was compared to the Spectral Coherence and the Dissimilarity Index. RESULTS Limited to the size of the analyzed dataset, both Coherence and PDI resulted sensitive to the conversion from MCI to AD, even though only PDI resulted specific. In particular, the intrasubject variability study showed that the three patients who converted to AD exhibited a significantly ([Formula: see text]) increased PDI (reduced coupling strength) in delta and theta bands. As regards Coherence, even though it significantly decreased in the three converted patients, in delta and theta bands, such a behavior was also detectable in one stable MCI patient, in delta band, thus making Coherence not specific. From the Dissimilarity Index point of view, the converted MCI showed no peculiar behavior. CONCLUSIONS PDI significantly increased, in delta and theta bands, specifically in the MCI subjects who converted to AD. The increase of PDI reflects a reduced coupling strength among the brain areas, which is consistent with the expected connectivity reduction associated to AD progression.