Artifact removal in the context of group ICA: A comparison of single-subject and group approaches.
Ontology highlight
ABSTRACT:
SUBMITTER: Du Y
PROVIDER: S-EPMC5784424 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundArtifacts contained in EEG recordings hamper both, the visual interpretation by experts as well as the algorithmic processing and analysis (e.g. for Brain-Computer Interfaces (BCI) or for Mental State Monitoring). While hand-optimized selection of source components derived from Independent Component Analysis (ICA) to clean EEG data is widespread, the field could greatly profit from automated solutions based on Machine Learning methods. Existing ICA-based removal strategies depend on explicit recordings of an individual's artifacts or have not been shown to reliably identify muscle artifacts.MethodsWe propose an automatic method for the classification of general artifactual source components. They are estimated by TDSEP, an ICA method that takes temporal correlations into account. The linear classifier is based on an optimized feature subset determined by a Linear Programming Machine (LPM). The subset is composed of features from the frequency-, the spatial- and temporal domain. A subject independent classifier was trained on 640 TDSEP components (reaction time (RT) study, n = 12) that were hand labeled by experts as artifactual or brain sources and tested on 1080 new components of RT data of the same study. Generalization was tested on new data from two studies (auditory Event Related Potential (ERP) paradigm, n = 18; motor imagery BCI paradigm, n = 80) that used data with different channel setups and from new subjects.ResultsBased on six features only, the optimized linear classifier performed on level with the inter-expert disagreement (<10% Mean Squared Error (MSE)) on the RT data. On data of the auditory ERP study, the same pre-calculated classifier generalized well and achieved 15% MSE. On data of the motor imagery paradigm, we demonstrate that the discriminant information used for BCI is preserved when removing up to 60% of the most artifactual source components.ConclusionsWe propose a universal and efficient classifier of ICA components for the subject independent removal of artifacts from EEG data. Based on linear methods, it is applicable for different electrode placements and supports the introspection of results. Trained on expert ratings of large data sets, it is not restricted to the detection of eye- and muscle artifacts. Its performance and generalization ability is demonstrated on data of different EEG studies.
| S-EPMC3175453 | biostudies-literature
Project description:Resting-state fMRI (R-fMRI) has shown considerable promise in providing potential biomarkers for diagnosis, prognosis and drug response across a range of diseases. Incorporating R-fMRI into multi-center studies is becoming increasingly popular, imposing technical challenges on data acquisition and analysis, as fMRI data is particularly sensitive to structured noise resulting from hardware, software, and environmental differences. Here, we investigated whether a novel clean up tool for structured noise was capable of reducing center-related R-fMRI differences between healthy subjects. We analyzed three Tesla R-fMRI data from 72 subjects, half of whom were scanned with eyes closed in a Philips Achieva system in The Netherlands, and half of whom were scanned with eyes open in a Siemens Trio system in the UK. After pre-statistical processing and individual Independent Component Analysis (ICA), FMRIB's ICA-based X-noiseifier (FIX) was used to remove noise components from the data. GICA and dual regression were run and non-parametric statistics were used to compare spatial maps between groups before and after applying FIX. Large significant differences were found in all resting-state networks between study sites before using FIX, most of which were reduced to non-significant after applying FIX. The between-center difference in the medial/primary visual network, presumably reflecting a between-center difference in protocol, remained statistically significant. FIX helps facilitate multi-center R-fMRI research by diminishing structured noise from R-fMRI data. In doing so, it improves combination of existing data from different centers in new settings and comparison of rare diseases and risk genes for which adequate sample size remains a challenge.
| S-EPMC4621866 | biostudies-literature
Project description:A variety of preprocessing techniques are available to correct subject-dependant artifacts in fMRI, caused by head motion and physiological noise. Although it has been established that the chosen preprocessing steps (or "pipeline") may significantly affect fMRI results, it is not well understood how preprocessing choices interact with other parts of the fMRI experimental design. In this study, we examine how two experimental factors interact with preprocessing: between-subject heterogeneity, and strength of task contrast. Two levels of cognitive contrast were examined in an fMRI adaptation of the Trail-Making Test, with data from young, healthy adults. The importance of standard preprocessing with motion correction, physiological noise correction, motion parameter regression and temporal detrending were examined for the two task contrasts. We also tested subspace estimation using Principal Component Analysis (PCA), and Independent Component Analysis (ICA). Results were obtained for Penalized Discriminant Analysis, and model performance quantified with reproducibility (R) and prediction metrics (P). Simulation methods were also used to test for potential biases from individual-subject optimization. Our results demonstrate that (1) individual pipeline optimization is not significantly more biased than fixed preprocessing. In addition, (2) when applying a fixed pipeline across all subjects, the task contrast significantly affects pipeline performance; in particular, the effects of PCA and ICA models vary with contrast, and are not by themselves optimal preprocessing steps. Also, (3) selecting the optimal pipeline for each subject improves within-subject (P,R) and between-subject overlap, with the weaker cognitive contrast being more sensitive to pipeline optimization. These results demonstrate that sensitivity of fMRI results is influenced not only by preprocessing choices, but also by interactions with other experimental design factors. This paper outlines a quantitative procedure to denoise data that would otherwise be discarded due to artifact; this is particularly relevant for weak signal contrasts in single-subject, small-sample and clinical datasets.
| S-EPMC3288007 | biostudies-other
Project description:Real-time functional magnetic resonance imaging (rtfMRI) has been proposed as a method of providing feedback to develop a participant's ability to control his or her own neuronal activity. However, this BOLD signal is vulnerable to contamination from nonneuronal sources that can also be shaped by the feedback provided. Here we illustrate an artifact found while training participants to control signal from an ROI in the insula. As the artifact was directly behind the eye and the experiment used an echo-planar imaging (EPI) sequence with phase encoding direction that included the orbits and the insula in the same line, we hypothesized that the artifact was due to eye motion. We demonstrate a reduced training effect when eyeball signal is regressed out of the data and reproduce the artifact with block design voluntary eye movement. Further, using independent components analysis on historical data, we find the artifact is common in BOLD data, but typically not task-correlated, even in tasks where one might expect differing amounts of eye movement in the active task blocks. The artifact, thus, does not significantly impact group results in typical fMRI experiments. Finally, we demonstrate this particular artifact can be avoided in rtfMRI experiments by ensuring that the phase encoding direction does not project any eye movement related artifact onto the ROI being used for feedback training. Our findings underscore the importance of taking great care in designing rtfMRI feedback procedures to avoid contamination with nonneuronal sources of BOLD signal alteration.
| S-EPMC6148359 | biostudies-literature
Project description:Resting state functional network connectivity (rsFNC) derived from functional magnetic resonance (fMRI) imaging is emerging as a possible biomarker to identify several brain disorders. Recently it has been pointed out that methods used to preprocess head motion variance might not fully remove all unwanted effects in the data. Proposed processing pipelines locate the treatment of head motion effects either close to the beginning or as one of the final steps. In this work, we assess several preprocessing pipelines applied in group independent component analysis (gICA) methods to study the rsFNC of the brain. The evaluation method utilizes patient/control classification performance based on linear support vector machines and leave-one-out cross validation. In addition, we explored group tests and correlation with severity measures in the patient population. We also tested the effect of removing high frequencies via filtering. Two real data cohorts were used: one consisting of 48 mTBI and one composed of 21 smokers, both with their corresponding matched controls. A simulation procedure was designed to test the classification power of each pipeline. Results show that data preprocessing can change the classification performance. In real data, regressing motion variance before gICA produced clearer group differences and stronger correlation with nicotine dependence.
| S-EPMC5035165 | biostudies-literature
Project description:Muscle electrical activity, or "electromyogenic" (EMG) artifact, poses a serious threat to the validity of electroencephalography (EEG) investigations in the frequency domain. EMG is sensitive to a variety of psychological processes and can mask genuine effects or masquerade as legitimate neurogenic effects across the scalp in frequencies at least as low as the alpha band (8-13 Hz). Although several techniques for correcting myogenic activity have been described, most are subjected to only limited validation attempts. Attempts to gauge the impact of EMG correction on intracerebral source models (source "localization" analyses) are rarer still. Accordingly, we assessed the sensitivity and specificity of one prominent correction tool, independent component analysis (ICA), on the scalp and in the source-space using high-resolution EEG. Data were collected from 17 participants while neurogenic and myogenic activity was independently varied. Several protocols for classifying and discarding components classified as myogenic and non-myogenic artifact (e.g., ocular) were systematically assessed, leading to the exclusion of one-third to as much as three-quarters of the variance in the EEG. Some, but not all, of these protocols showed adequate performance on the scalp. Indeed, performance was superior to previously validated regression-based techniques. Nevertheless, ICA-based EMG correction exhibited low validity in the intracerebral source-space, likely owing to incomplete separation of neurogenic from myogenic sources. Taken with prior work, this indicates that EMG artifact can substantially distort estimates of intracerebral spectral activity. Neither regression- nor ICA-based EMG correction techniques provide complete safeguards against such distortions. In light of these results, several practical suggestions and recommendations are made for intelligently using ICA to minimize EMG and other common artifacts.
| S-EPMC2818255 | biostudies-literature
Project description:Recently, the use of portable electroencephalogram (EEG) devices to record brain signals in both health care monitoring and in other applications, such as fatigue detection in drivers, has been increased due to its low cost and ease of use. However, the measured EEG signals always mix with the electrooculogram (EOG), which are results due to eyelid blinking or eye movements. The eye-blinking/movement is an uncontrollable activity that results in a high-amplitude slow-time varying component that is mixed in the measured EEG signal. The presence of these artifacts misled our understanding of the underlying brain state. As the portable EEG devices comprise few EEG channels or sometimes a single EEG channel, classical artifact removal techniques such as blind source separation methods cannot be used to remove these artifacts from a single-channel EEG signal. Hence, there is a demand for the development of new single-channel-based artifact removal techniques. Singular spectrum analysis (SSA) has been widely used as a single-channel-based eye-blink artifact removal technique. However, while removing the artifact, the low-frequency components from the non-artifact region of the EEG signal are also removed by SSA. To preserve these low-frequency components, in this paper, we have proposed a new methodology by integrating the SSA with continuous wavelet transform (CWT) and the k-means clustering algorithm that removes the eye-blink artifact from the single-channel EEG signals without altering the low frequencies of the EEG signal. The proposed method is evaluated on both synthetic and real EEG signals. The results also show the superiority of the proposed method over the existing methods.
| S-EPMC8838657 | biostudies-literature
Project description:EEG data acquired in an MRI scanner are heavily contaminated by gradient artifacts that can significantly compromise signal quality. We developed two new methods based on independent component analysis (ICA) for reducing gradient artifacts from spiral in-out and echo-planar pulse sequences at 3 T, and compared our algorithms with four other commonly used methods: average artifact subtraction (Allen, P., Josephs, O., Turner, R., 2000. A method for removing imaging artifact from continuous EEG recorded during functional MRI. NeuroImage 12, 230-239.), principal component analysis (Niazy, R., Beckmann, C., Iannetti, G., Brady, J., Smith, S., 2005. Removal of FMRI environment artifacts from EEG data using optimal basis sets. NeuroImage 28, 720-737.), Taylor series ( Wan, X., Iwata, K., Riera, J., Kitamura, M., Kawashima, R., 2006. Artifact reduction for simultaneous EEG/fMRI recording: adaptive FIR reduction of imaging artifacts. Clin. Neurophysiol. 117, 681-692.) and a conventional temporal ICA algorithm. Models of gradient artifacts were derived from simulations as well as a water phantom and performance of each method was evaluated on datasets constructed using visual event-related potentials (ERPs) as well as resting EEG. Our new methods recovered ERPs and resting EEG below the beta band (<12.5 Hz) with high signal-to-noise ratio (SNR>4). Our algorithms outperformed all of these methods on resting EEG in the theta and alpha bands (SNR>4); however, for all methods, signal recovery was modest (SNR approximately 1) in the beta band and poor (SNR<0.3) in the gamma band and above. We found that the conventional ICA algorithm performed poorly with uniformly low SNR (<0.1). Taken together, our new ICA-based methods offer a more robust technique for gradient artifact reduction when scanning at 3 T using spiral in-out and echo-planar pulse sequences. We provide new insights into the strengths and weaknesses of each method using a unified subspace framework.
| S-EPMC2745974 | biostudies-other
Project description:Deep brain stimulation (DBS) therapies have shown clinical success in the treatment of a number of neurological illnesses, including obsessive-compulsive disorder, epilepsy, and Parkinson's disease. An emerging strategy for increasing the efficacy of DBS therapies is to develop closed-loop, adaptive DBS systems that can sense biomarkers associated with particular symptoms and in response, adjust DBS parameters in real-time. The development of such systems requires extensive analysis of the underlying neural signals while DBS is on, so that candidate biomarkers can be identified and the effects of varying the DBS parameters can be better understood. However, DBS creates high amplitude, high frequency stimulation artifacts that prevent the underlying neural signals and thus the biological mechanisms underlying DBS from being analyzed. Additionally, DBS devices often require low sampling rates, which alias the artifact frequency, and rely on wireless data transmission methods that can create signal recordings with missing data of unknown length. Thus, traditional artifact removal methods cannot be applied to this setting. We present a novel periodic artifact removal algorithm for DBS applications that can accurately remove stimulation artifacts in the presence of missing data and in some cases where the stimulation frequency exceeds the Nyquist frequency. The numerical examples suggest that, if implemented on dedicated hardware, this algorithm has the potential to be used in embedded closed-loop DBS therapies to remove DBS stimulation artifacts and hence, to aid in the discovery of candidate biomarkers in real-time. Code for our proposed algorithm is publicly available on Github.
| S-EPMC9553325 | biostudies-literature
Project description:Principal component analysis (PCA) is widely used for data reduction in group independent component analysis (ICA) of fMRI data. Commonly, group-level PCA of temporally concatenated datasets is computed prior to ICA of the group principal components. This work focuses on reducing very high dimensional temporally concatenated datasets into its group PCA space. Existing randomized PCA methods can determine the PCA subspace with minimal memory requirements and, thus, are ideal for solving large PCA problems. Since the number of dataloads is not typically optimized, we extend one of these methods to compute PCA of very large datasets with a minimal number of dataloads. This method is coined multi power iteration (MPOWIT). The key idea behind MPOWIT is to estimate a subspace larger than the desired one, while checking for convergence of only the smaller subset of interest. The number of iterations is reduced considerably (as well as the number of dataloads), accelerating convergence without loss of accuracy. More importantly, in the proposed implementation of MPOWIT, the memory required for successful recovery of the group principal components becomes independent of the number of subjects analyzed. Highly efficient subsampled eigenvalue decomposition techniques are also introduced, furnishing excellent PCA subspace approximations that can be used for intelligent initialization of randomized methods such as MPOWIT. Together, these developments enable efficient estimation of accurate principal components, as we illustrate by solving a 1600-subject group-level PCA of fMRI with standard acquisition parameters, on a regular desktop computer with only 4 GB RAM, in just a few hours. MPOWIT is also highly scalable and could realistically solve group-level PCA of fMRI on thousands of subjects, or more, using standard hardware, limited only by time, not memory. Also, the MPOWIT algorithm is highly parallelizable, which would enable fast, distributed implementations ideal for big data analysis. Implications to other methods such as expectation maximization PCA (EM PCA) are also presented. Based on our results, general recommendations for efficient application of PCA methods are given according to problem size and available computational resources. MPOWIT and all other methods discussed here are implemented and readily available in the open source GIFT software.
| S-EPMC4735350 | biostudies-literature