Is Independent Component Analysis Research Articles

Identification method of independent components related to artifacts in electroencephalograms

When an electroencephalogram (EEG) is measured, artifacts due to eye blinks and eye movements contaminate the EEG signal. One of the solutions applied to this problem is independent component analysis (ICA), which can separate the artifact components from EEG data. However, the identification of independent components (ICs) related to artifacts, particularly in the case of multiple noise signals from eye blinks and movements, has not been investigated fully. The purpose of this work is to identify ICs related to eye‐blink and eye‐movement artifacts in EEG data. In the proposed method, an artificial EEG with 28 channels was first created by superimposing eye‐blink and eye‐movement templates, and then ICA was applied to the artificial EEG to obtain ICs. Afterward, feature amounts of kurtosis for each IC and the cross‐correlation coefficient between each IC and the eye‐blink template and eye‐movement template were extracted, and clustering was performed by K‐means clustering. As a result, the most reasonable ICs related to multiple artifacts were identified in comparison with the results of round‐robin ICs. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

A hierarchical independent component analysis model for longitudinal neuroimaging studies

In recent years, longitudinal neuroimaging study has become increasingly popular in neuroscience research to investigate disease-related changes in brain functions, to study neurodevelopment or to evaluate treatment effects on neural processing. One of the important goals in longitudinal imaging analysis is to study changes in brain functional networks across time and how the changes are modulated by subjects' clinical or demographic variables. In current neuroscience literature, one of the most commonly used tools to extract and characterize brain functional networks is independent component analysis (ICA), which separates multivariate signals into linear mixture of independent components. However, existing ICA methods are only applicable to cross-sectional studies and not suited for modeling repeatedly measured imaging data. In this paper, we propose a novel longitudinal independent component model (L-ICA) which provides a formal modeling framework for extending ICA to longitudinal studies. By incorporating subject-specific random effects and visit-specific covariate effects, L-ICA is able to provide more accurate estimates of changes in brain functional networks on both the population- and individual-level, borrow information across repeated scans within the same subject to increase statistical power in detecting covariate effects on the networks, and allow for model-based prediction for brain networks changes caused by disease progression, treatment or neurodevelopment. We develop a fully traceable exact EM algorithm to obtain maximum likelihood estimates of L-ICA. We further develop a subspace-based approximate EM algorithm which greatly reduce the computation time while still retaining high accuracy. Moreover, we present a statistical testing procedure for examining covariate effects on brain network changes. Simulation results demonstrate the advantages of our proposed methods. We apply L-ICA to ADNI2 study to investigate changes in brain functional networks in Alzheimer disease. Results from the L-ICA provide biologically insightful findings which are not revealed using existing methods.

INVESTIGATING DIFFERENCES IN BRAIN FUNCTIONAL NETWORKS USING HIERARCHICAL COVARIATE-ADJUSTED INDEPENDENT COMPONENT ANALYSIS.

Human brains perform tasks via complex functional networks consisting of separated brain regions. A popular approach to characterize brain functional networks in fMRI studies is independent component analysis (ICA), which is a powerful method to reconstruct latent source signals from their linear mixtures. In many fMRI studies, an important goal is to investigate how brain functional networks change according to specific clinical and demographic variabilities. Existing ICA methods, however, cannot directly incorporate covariate effects in ICA decomposition. Heuristic post-ICA analysis to address this need can be inaccurate and inefficient. In this paper, we propose a hierarchical covariate-adjusted ICA (hc-ICA) model that provides a formal statistical framework for estimating covariate effects and testing differences between brain functional networks. Our method provides a more reliable and powerful statistical tool for evaluating group differences in brain functional networks while appropriately controlling for potential confounding factors. We present an analytically tractable EM algorithm to obtain maximum likelihood estimates of our model. We also develop a subspace-based approximate EM that runs significantly faster while retaining high accuracy. To test the differences in functional networks, we introduce a voxel-wise approximate inference procedure which eliminates the need of computationally expensive covariance matrix estimation and inversion. We demonstrate the advantages of our methods over the existing method via simulation studies. We apply our method to an fMRI study to investigate differences in brain functional networks associated with post-traumatic stress disorder (PTSD).

In search of biomarkers in psychiatry: EEG‐based measures of brain function

Current clinical parameters used for diagnosis and phenotypic definitions of psychopathology are both highly variable and subjective. Intensive research efforts for specific and sensitive biological markers, or biomarkers, for psychopathology as objective alternatives to the current paradigm are ongoing. While biomarker research in psychiatry has focused largely on functional neuroimaging methods for identifying the neural functions that associate with psychopathology, scalp electroencephalography (EEG) has been viewed, historically, as offering little specific brain source information, as scalp appearance is only loosely correlated to its brain source dynamics. However, ongoing advances in signal processing of EEG data can now deliver functional EEG brain-imaging with distinctly improved spatial, as well as fine temporal, resolution. One computational approach proving particularly useful for EEG cortical brain imaging is independent component analysis (ICA). ICA decomposition can be used to identify distinct cortical source activities that are sensitive and specific to the pathophysiology of psychiatric disorders. Given its practical research advantages, relatively low cost, and ease of use, EEG-imaging is now both feasible and attractive, in particular for studies involving the large samples required by genetically informative designs to characterize causal pathways to psychopathology. The completely non-invasive nature of EEG data acquisition, coupled with ongoing advances in dry, wireless, and wearable EEG technology, makes EEG-imaging increasingly attractive and appropriate for psychiatric research, including the study of developmentally young samples. Applied to large genetically and developmentally informative samples, EEG imaging can advance the search for robust diagnostic biomarkers and phenotypes in psychiatry.

EMBEDDED IMPLEMENTATION OF EEG ANALYSIS USING INDEPENDENT COMPONENT APPROACH

Brain signals are important in diagnosing various disorders and abnormalities in the human body. These signals are recorded by scalp electrodes and are called as EEG signals. EEG signals are a mixture of signals from different brain regions which contain artefacts along with original information. These contaminated mixtures are analysed such that diagnosis of various diseases is possible. One of the effective methods available is Independent Component Analysis (ICA) for removing artefacts and for separation and analysis of the desired sources from within the EEGs. This paper focuses on the analysis of EEG signals using ICA approach. Two ICA algorithms- Pearson ICA and JADE ICA are analysed in this paper. Comparison of these ICA algorithms in removing artefacts from EEG has been carried out by simulation using MATLAB. Then the Pearson ICA algorithm simulation is done using Visual C#. The algorithm has been implemented in an Embedded Development Kit (EDK) using .NET Micro Framework and the results are presented.

A Novel Group ICA Approach Based on Multi-scale Individual Component Clustering. Application to a Large Sample of fMRI Data

Functional connectivity-based analysis of functional magnetic resonance imaging data (fMRI) is an emerging technique for human brain mapping. One powerful method for the investigation of functional connectivity is independent component analysis (ICA) of concatenated data. However, this research field is evolving toward processing increasingly larger database taking into account inter-individual variability. Concatenated data analysis only handles these features using some additional procedures such as bootstrap or including a model of between-subject variability during the preprocessing step of the ICA. In order to alleviate these limitations, we propose a method based on group analysis of individual ICA components, using a multi-scale clustering (MICCA). MICCA start with two steps repeated several times: 1) single subject data ICA followed by 2) clustering of all subject independent components according to a spatial similarity criterion. A final third step consists in selecting reproducible clusters across the repetitions of the two previous steps. The core of the innovation lies in the multi-scale and unsupervised clustering algorithm built as a chain of three processes: robust proto-cluster creation, aggregation of the proto-clusters, and cluster consolidation. We applied MICCA to the analysis of 310 fMRI resting state dataset. MICCA identified 28 resting state brain networks. Overall, the cluster neuroanatomical substrate included 98% of the cerebrum gray matter. MICCA results proved to be reproducible in a random splitting of the data sample and more robust than the classical concatenation method.

ADJUST: An automatic EEG artifact detector based on the joint use of spatial and temporal features

A successful method for removing artifacts from electroencephalogram (EEG) recordings is Independent Component Analysis (ICA), but its implementation remains largely user-dependent. Here, we propose a completely automatic algorithm (ADJUST) that identifies artifacted independent components by combining stereotyped artifact-specific spatial and temporal features. Features were optimized to capture blinks, eye movements, and generic discontinuities on a feature selection dataset. Validation on a totally different EEG dataset shows that (1) ADJUST's classification of independent components largely matches a manual one by experts (agreement on 95.2% of the data variance), and (2) Removal of the artifacted components detected by ADJUST leads to neat reconstruction of visual and auditory event-related potentials from heavily artifacted data. These results demonstrate that ADJUST provides a fast, efficient, and automatic way to use ICA for artifact removal.

Functional source separation improves the quality of single trial visual evoked potentials recorded during concurrent EEG-fMRI

EEG quality is a crucial issue when acquiring combined EEG-fMRI data, particularly when the focus is on using single trial (ST) variability to integrate the data sets. The most common method for improving EEG data quality following removal of gross MRI artefacts is independent component analysis (ICA), a completely blind source separation technique. In the current study, a different approach is proposed based on the functional source separation (FSS) algorithm. FSS is an extension of ICA that incorporates prior knowledge about the signal of interest into the data decomposition. Since in general the part of the EEG signal that will contain the most relevant information is known beforehand (i.e. evoked potential peaks, spectral bands), FSS separates the signal of interest by exploiting this prior knowledge without renouncing the advantages of using only information contained in the original signal waveforms.A reversing checkerboard stimulus was used to generate visual evoked potentials (VEPs) in healthy control subjects. Gradient and ballistocardiogram artefacts were removed with template subtraction techniques to form the raw data, which were then subjected to ICA denoising and FSS. The resulting EEG data sets were compared using several metrics derived from average and ST data and correlated with fMRI data. In all cases, ICA was an improvement on the raw data, but the most obvious improvement was provided by FSS, which consistently outperformed ICA. The results show the benefit of FSS for the recovery of good quality single trial evoked potentials during concurrent EEG-fMRI recordings.

Improved (I)CA-noise elimination of electrophysiological data using band-pass filtered components

Event Abstract Back to Event Improved (I)CA-noise elimination of electrophysiological data using band-pass filtered components Removal of signal components unrelated to the signals of interest, so called 'noise', is a general problem in many types of data. One method for identifying and removing noise (e.g. eye movement artifacts or power-line noise) from electrophysiological data is independent component analysis (ICA) (e.g. Jung et al., 1998). A shortcoming of this method is that it does not guarantee a complete separation of physiological signals and noise sources into different components. Thus, those components containing obvious noise contributions might also contain physiological data. This phenomenon is called 'leakage'. Rejecting these components might therefore not only clean the noise but may additionally and erroneously take out parts of the physiological data. Here, we suggest that this leakage can be reduced using prior knowledge about the spectral features of the noise. After identification of the noise components, we applied band-pass filtering to these components at the frequencies of the noise before subtracting the back-projected components from the data. This effectively prevents deletion of physiological signals in frequency bands beyond the a priori specified noise frequency bands. To test this method, we applied it to simulated data and physiological signals obtained from ECoG recordings in macaque monkey. Our results demonstrate that this method (a) is as efficient as the standard ICA correction, (b) also works for data available only as short time segments ('trials'), (c) results in a clearer noise time-course allowing the subtraction of less non-noise activity, and (d) does not - in contrast to the standard unfiltered ICA method - change the power spectra of the cleared signals in spectral regions outside the noise regions. Additionally, we present a simple and computationally efficient method to find noise components with sharp frequency tunings (e.g. line noise), which can be used independently of or prior to ICA to improve its performance. To achieve this, we band-pass filter the original signal prior to component identification (which can consequently be done using standard component analysis techniques, e.g. PCA/ICA). We thereby reduce the influence of components whose main contribution lies in other frequency bands, thereby rendering the noise components more salient to the component identification algorithm. This method is especially useful when no clear noise-components can be detected using standard ICA on the unfiltered data. In summary, we show that ICA noise elimination is improved using prior knowledge about the spectral features of the noise, ultimately enhancing the signal-to-noise ratio of neurophysiological data recordings. Conference: Computational and systems neuroscience 2009, Salt Lake City, UT, United States, 26 Feb - 3 Mar, 2009. Presentation Type: Poster Presentation Topic: Poster Presentations Citation: (2009). Improved (I)CA-noise elimination of electrophysiological data using band-pass filtered components. Front. Syst. Neurosci. Conference Abstract: Computational and systems neuroscience 2009. doi: 10.3389/conf.neuro.06.2009.03.257 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 03 Feb 2009; Published Online: 03 Feb 2009. Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract Supplemental Data The Authors in Frontiers Google Google Scholar PubMed Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

Statistical Process Control Charts for Batch Operations Based on Independent Component Analysis

A significant step forward in recent years, in regard to multivariate statistical process control (MSPC) for operational condition monitoring and fault diagnosis, has been the introduction of principal component analysis (PCA) for the compression of process data. An alternative technique that has been studied more recently for data compression is independent component analysis (ICA). Published work has shown that, in some applications of statistical process monitoring, ICA-based methods have exhibited advantages over those based on other data compression techniques. However, it is inappropriate to use ICA in the same way as PCA to derive Hotelling's T2 and SPE (squared prediction error) charts, because the independent components are separated by maximizing their non-Gaussianity, whereas the satisfying Gaussian distribution is the basis of T2 and SPE monitoring charts, as well as univariate statistical process control (SPC) charts. In this paper, we propose a new method for deriving SPC charts based on ICA...

INDEPENDENT COMPONENT ANALYSIS FOR CLASSIFYING MULTISPECTRAL IMAGES WITH DIMENSIONALITY LIMITATION

Airborne and spaceborne remote sensors can acquire invaluable information about earth surface, which have many important applications. The acquired information usually is represented as two-dimensional grids, i.e. images. One of techniques to processing such images is Independent Component Analysis (ICA), which is particularly useful for classifying objects with unknown spectral signatures in an unknown image scene, i.e. unsupervised classification. Since the weight matrix in ICA is a square matrix for the purpose of mathematical tractability, the number of objects that can be classified is equal to the data dimensionality, i.e. the number of spectral bands. When the number of sensors (or spectral channels) is very small (e.g. a 3-band CIR photograph and 6-band Landsat image with the thermal band being removed), it is impossible to classify all the different objects present in an image scene using the original data. In order to solve this problem, we present a data dimensionality expansion technique to generate artificial bands. Its basic idea is to use nonlinear functions to capture and highlight the similarity/dissimilarity between original spectral measurements, which can provide more data with additional information for detecting and classifying more objects. The results from such a nonlinear band generation approach are compared with a linear band generation method using cubic spline interpolation of pixel spectral signatures. The experiments demonstrate that nonlinear band generation approach can significantly improve unsupervised classification accuracy, while linear band generation method cannot since no new information can be provided. It is also demonstrated that ICA is more powerful than other frequently used unsupervised classification algorithms such as ISODATA.