Testing the ICA mixing matrix based on inter-subject or inter-session consistency

Independent component analysis (ICA) is increasingly used for analyzing brain imaging data. ICA typically gives a large number of components, many of which may be just random, due to insufficient sample size, violations of the model, or algorithmic problems. Few methods are available for computing the statistical significance (reliability) of the components. We propose to approach this problem by performing ICA separately on a number of subjects, and finding components which are sufficiently consistent (similar) over subjects. Similarity is defined here as the similarity of the mixing coefficients, which usually correspond to spatial patterns in EEG and MEG. The threshold of what is "sufficient" is rigorously defined by a null hypothesis under which the independent components are random orthogonal components in the whitened space. Components which are consistent in different subjects are found by clustering under the constraint that a cluster can only contain one source from each subject, and by constraining the number of the false positives based on the null hypothesis. Instead of different subjects, the method can also be applied on different recording sessions from a single subject. The testing method is particularly applicable to EEG and MEG analysis.     

Identifying reliable independent components via split-half comparisons

Independent component analysis (ICA) is a family of unsupervised learning algorithms that have proven useful for the analysis of the electroencephalogram (EEG) and magnetoencephalogram (MEG). ICA decomposes an EEG/MEG data set into a basis of maximally temporally independent components (ICs) that are learned from the data. As with any statistic, a concern with using ICA is the degree to which the estimated ICs are reliable. An IC may not be reliable if ICA was trained on insufficient data, if ICA training was stopped prematurely or at a local minimum (for some algorithms), or if multiple global minima were present. Consequently, evidence of ICA reliability is critical for the credibility of ICA results. In this paper, we present a new algorithm for assessing the reliability of ICs based on applying ICA separately to split-halves of a data set. This algorithm improves upon existing methods in that it considers both IC scalp topographies and activations, uses a probabilistically interpretable threshold for accepting ICs as reliable, and requires applying ICA only three times per data set. As evidence of the method's validity, we show that the method can perform comparably to more time intensive bootstrap resampling and depends in a reasonable manner on the amount of training data. Finally, using the method we illustrate the importance of checking the reliability of ICs by demonstrating that IC reliability is dramatically increased by removing the mean EEG at each channel for each epoch of data rather than the mean EEG in a prestimulus baseline.     

Unified SPM-ICA for fMRI analysis

A widely used tool for functional magnetic resonance imaging (fMRI) data analysis, statistical parametric mapping (SPM), is based on the general linear model (GLM). SPM therefore requires a priori knowledge or specific assumptions about the time courses contributing to signal changes. In contradistinction, independent component analysis (ICA) is a data-driven method based on the assumption that the causes of responses are statistically independent. Here we describe a unified method, which combines ICA, temporal ICA (tICA), and SPM for analyzing fMRI data. tICA was applied to fMRI datasets to disclose independent components, whose number was determined by the Bayesian information criterion (BIC). The resulting components were used to construct the design matrix of a GLM. Parameters were estimated and regionally-specific statistical inferences were made about activations in the usual way. The sensitivity and specificity were evaluated using Monte Carlo simulations. The receiver operating characteristic (ROC) curves indicated that the unified SPM-ICA method had a better performance. Moreover, SPM-ICA was applied to fMRI datasets from twelve normal subjects performing left and right hand movements. The areas identified corresponded to motor (premotor, sensorimotor areas and SMA) areas and were consistently task related. Part of the frontal lobe, parietal cortex, and cingulate gyrus also showed transiently task-related responses. The unified method requires less supervision than the conventional SPM and enables classical inference about the expression of independent components. Our results also suggest that the method has a higher sensitivity than SPM analyses.     

Analyzing consistency of independent components: an fMRI illustration

Independent component analysis (ICA) is a powerful data-driven signal processing technique. It has proved to be helpful in, e.g., biomedicine, telecommunication, finance and machine vision. Yet, some problems persist in its wider use. One concern is the reliability of solutions found with ICA algorithms, resulting from the stochastic changes each time the analysis is performed. The consistency of the solutions can be analyzed by clustering solutions from multiple runs of bootstrapped ICA. Related methods have been recently published either for analyzing algorithmic stability or reducing the variability. The presented approach targets the extraction of additional information related to the independent components, by focusing on the nature of the variability. Practical implications are illustrated through a functional magnetic resonance imaging (fMRI) experiment.     

A K-means multivariate approach for clustering independent components from magnetoencephalographic data

Independent component analysis (ICA) is typically applied on functional magnetic resonance imaging, electroencephalographic and magnetoencephalographic (MEG) data due to its data-driven nature. In these applications, ICA needs to be extended from single to multi-session and multi-subject studies for interpreting and assigning a statistical significance at the group level. Here a novel strategy for analyzing MEG independent components (ICs) is presented, Multivariate Algorithm for Grouping MEG Independent Components K-means based (MAGMICK). The proposed approach is able to capture spatio-temporal dynamics of brain activity in MEG studies by running ICA at subject level and then clustering the ICs across sessions and subjects. Distinctive features of MAGMICK are: i) the implementation of an efficient set of "MEG fingerprints" designed to summarize properties of MEG ICs as they are built on spatial, temporal and spectral parameters; ii) the implementation of a modified version of the standard K-means procedure to improve its data-driven character. This algorithm groups the obtained ICs automatically estimating the number of clusters through an adaptive weighting of the parameters and a constraint on the ICs independence, i.e. components coming from the same session (at subject level) or subject (at group level) cannot be grouped together. The performances of MAGMICK are illustrated by analyzing two sets of MEG data obtained during a finger tapping task and median nerve stimulation. The results demonstrate that the method can extract consistent patterns of spatial topography and spectral properties across sessions and subjects that are in good agreement with the literature. In addition, these results are compared to those from a modified version of affinity propagation clustering method. The comparison, evaluated in terms of different clustering validity indices, shows that our methodology often outperforms the clustering algorithm. Eventually, these results are confirmed by a comparison with a MEG tailored version of the self-organizing group ICA, which is largely used for fMRI IC clustering.     

Independent component analysis of fMRI group studies by self-organizing clustering

Independent component analysis (ICA) is a valuable technique for the multivariate data-driven analysis of functional magnetic resonance imaging (fMRI) data sets. Applications of ICA have been developed mainly for single subject studies, although different solutions for group studies have been proposed. These approaches combine data sets from multiple subjects into a single aggregate data set before ICA estimation and, thus, require some additional assumptions about the separability across subjects of group independent components. Here, we exploit the application of similarity measures and a related visual tool to study the natural self-organizing clustering of many independent components from multiple individual data sets in the subject space. Our proposed framework flexibly enables multiple criteria for the generation of group independent components and their random-effects evaluation. We present real visual activation fMRI data from two experiments, with different spatiotemporal structures, and demonstrate the validity of this framework for a blind extraction and selection of meaningful activity and functional connectivity group patterns. Our approach is either alternative or complementary to the group ICA of aggregated data sets in that it exploits commonalities across multiple subject-specific patterns, while addressing as much as possible of the intersubject variability of the measured responses. This property is particularly of interest for a blind group and subgroup pattern extraction and selection.     

Latency (in)sensitive ICA. Group independent component analysis of fMRI data in the temporal frequency domain

Independent component analysis (ICA), a data-driven approach utilizing high-order statistical moments to find maximally independent sources, has found fruitful application in functional magnetic resonance imaging (fMRI). A limitation of the standard fMRI ICA model is that a given component's time course is required to have the same delay at every voxel. As spatially varying delays (SVDs) may be found in fMRI data, using an ICA model with a fixed temporal delay for each source will have two implications. Larger SVDs can result in the splitting of regions with different delays into different components. Second, smaller SVDs can result in a biased ICA amplitude estimate due to only a slight delay difference. We propose a straightforward approach for incorporating this prior temporal information and removing the limitation of a fixed source delay by performing ICA on the amplitude spectrum of the original fMRI data (thus removing latency information). A latency map is then estimated for each component using the resulting component images and the raw data. We show that voxels with similar time courses, but different delays, are grouped into the same component. Additionally, when using traditional ICA, the amplitudes of motor areas are diminished due to systematic delay differences between visual and motor areas. The amplitudes are more accurately estimated when using a latency-insensitive ICA approach. The resulting time courses, the component maps, and the latency maps may prove useful as an addition to the collection of methods for fMRI data analysis.     

Localization of individual area neuronal activity

A family of methods, collectively known as independent component analysis (ICA), has recently been added to the array of methods designed to decompose a multi-channel signal into components. ICA methods have been applied to raw magnetoencephalography (MEG) and electroencephalography (EEG) signals to remove artifacts, especially when sources such as power line or cardiac activity generate strong components that dominate the signal. More recently, successful ICA extraction of stimulus-evoked responses has been reported from single-trial raw MEG and EEG signals. The extraction of weak components has often been erratic, depending on which ICA method is employed and even on what parameters are used. In this work, we show that if the emphasis is placed on individual "independent components," as is usually the case with standard ICA applications, differences in the results obtained for different components are exaggerated. We propose instead the reconstruction of regional brain activations by combining tomographic estimates of individual independent components that have been selected by appropriate spatial and temporal criteria. Such localization of individual area neuronal activity (LIANA) allows reliable semi-automatic extraction of single-trial regional activations from raw MEG data. We demonstrate the new method with three different ICA algorithms applied to both computer-generated signals and real data. We show that LIANA provides almost identical results with each ICA method despite the fact that each method yields different individual components.     

Independent component analysis applied to self-paced functional MR imaging paradigms

Self-paced functional MR imaging (fMRI) paradigms, in which the task timing is determined by the subject's performance, can offer several advantages over commonly applied paradigms with predetermined stimulus timing. Independent component analysis (ICA) does not require specification of a timed response function, and could be an advantageous method of deriving results from fMRI data sets with varying response timings and durations. In this study normal volunteers (N = 10) each performed two self-paced fMRI motor and arithmetic paradigms. Individual data sets were analyzed with the Infomax spatial ICA algorithm. Conventional regression analysis was performed for comparison purposes. Spatial ICA effectively produced task-related components from each of the self-paced data sets, even in a few cases where regression analysis yielded non-specific functional maps. For the motor paradigm, these components consistently mapped to primary motor areas. ICA of the arithmetic paradigm yielded multiple task-related components that variably mapped to regions of parietal and frontal lobes. Regression analysis generally yielded similar spatial maps. The multiple task-related ICA components that were sometimes produced from each self-paced data set can be challenging to identify and evaluate for significance. These preliminary results indicate that ICA is useful as an exploratory and complementary method to conventional regression analysis for fMRI of self-paced paradigms.     

Automatic independent component labeling for artifact removal in fMRI

Blood oxygenation level dependent (BOLD) signals in functional magnetic resonance imaging (fMRI) are often small compared to the level of noise in the data. The sources of noise are numerous including different kinds of motion artifacts and physiological noise with complex patterns. This complicates the statistical analysis of the fMRI data. In this study, we propose an automatic method to reduce fMRI artifacts based on independent component analysis (ICA). We trained a supervised classifier to distinguish between independent components relating to a potentially task-related signal and independent components clearly relating to structured noise. After the components had been classified as either signal or noise, a denoised fMR time-series was reconstructed based only on the independent components classified as potentially task-related. The classifier was a novel global (fixed structure) decision tree trained in a Neyman-Pearson (NP) framework, which allowed the shape of the decision regions to be controlled effectively. Additionally, the conservativeness of the classifier could be tuned by modifying the NP threshold. The classifier was tested against the component classifications by an expert with the data from a category learning task. The test set as well as the expert were different from the data used for classifier training and the expert labeling the training set. The misclassification rate was between 0.2 and 0.3 for both the event-related and blocked designs and it was consistent among variety of different NP thresholds. The effects of denoising on the group-level statistical analyses were as expected: The denoising generally decreased Z-scores in the white matter, where extreme Z-values can be expected to reflect artifacts. A similar but weaker decrease in Z-scores was observed in the gray matter on average. These two observations suggest that denoising was likely to reduce artifacts from gray matter and could be useful to improve the detection of activations. We conclude that automatic ICA-based denoising offers a potentially useful approach to improve the quality of fMRI data and consequently increase the accuracy of the statistical analysis of these data.     

基于独立元分析的脑磁图数据分析和处理(英文)

背景:诱发响应信号是由刺激的时间锁定的,对于一些特定的刺激呈现小的个人差距,脑磁图数据中诱发响应的提取对人脑功能的认识很重要。目的:将独立元分析应用于分离混迭的脑磁图多通道信号中的信号源,提出一个简单有效的基于独立元分析的脑磁图数据分析和处理方法。设计:单一样本分析。单位:复旦大学电子工程系和复旦大学脑科学研究中心。对象:实验于2002-09在日本通信综合研究所关西先端研究中心完成,选择日本东京药科大学的健康志愿者1例,男性;年龄23岁。受试者自愿参加。方法:①对脑磁图进行必要的预处理,如低通滤波和主成分分解。②采用独立元分析的方法对取自148个通道的脑磁图的数据进行分析和处理,尤其是诱发反应的提取。③对提取的各独立成分进行周期平均。主要观察指标:应用独立元分析方法对脑磁图数据分析。结果:①脑磁图信号有较高的冗余度,信号能量的绝大部分集中在前30个主成分中,从前30个主成分中抽取干扰源和诱发响应活动源。②眼动干扰源仍被清楚地检测和分离在第1个独立元中,心电干扰被分离在第20个独立元中。③α波呈现在第2,3,7和9等独立元中。波(13～30Hz)呈现在第11和第12独立元中。④诱发响应是响应于刺激的周期性波形,集中在第5独立元中。结论:利用独立元分析,可从混迭的脑磁图数据中分离这些干扰源,更进一步,消除这些干扰成分,可得到净化的脑磁图数据。借助独立元分析,有效的分离α波、β波以及眼动、眨眼等神经活动源,有可能为它们的脑神经活动研究提供新的方法和途径。利用独立元分析方法成功的进行了听觉诱发反应的分离和提取。     

A unified framework for group independent component analysis for multi-subject fMRI data

Independent component analysis (ICA) is becoming increasingly popular for analyzing functional magnetic resonance imaging (fMRI) data. While ICA has been successfully applied to single-subject analysis, the extension of ICA to group inferences is not straightforward and remains an active topic of research. Current group ICA models, such as the GIFT [Calhoun, V.D., Adali, T., Pearlson, G.D., Pekar, J.J., 2001. A method for making group inferences from functional MRI data using independent component analysis. Hum. Brain Mapp. 14, 140–151.] and tensor PICA [Beckmann, C.F., Smith, S.M., 2005. Tensorial extensions of independent component analysis for multisubject FMRI analysis. Neuroimage 25, 294–311.], make different assumptions about the underlying structure of the group spatio-temporal processes and are thus estimated using algorithms tailored for the assumed structure, potentially leading to diverging results. To our knowledge, there are currently no methods for assessing the validity of different model structures in real fMRI data and selecting the most appropriate one among various choices. In this paper, we propose a unified framework for estimating and comparing group ICA models with varying spatio-temporal structures. We consider a class of group ICA models that can accommodate different group structures and include existing models, such as the GIFT and tensor PICA, as special cases. We propose a maximum likelihood (ML) approach with a modified Expectation–Maximization (EM) algorithm for the estimation of the proposed class of models. Likelihood ratio tests (LRT) are presented to compare between different group ICA models. The LRT can be used to perform model comparison and selection, to assess the goodness-of-fit of a model in a particular data set, and to test group differences in the fMRI signal time courses between subject subgroups. Simulation studies are conducted to evaluate the performance of the proposed method under varying structures of group spatio-temporal processes. We illustrate our group ICA method using data from an fMRI study that investigates changes in neural processing associated with the regular practice of Zen meditation.     

ICA-based procedures for removing ballistocardiogram artifacts from EEG data acquired in the MRI scanner

Electroencephalogram (EEG) data acquired in the MRI scanner contains significant artifacts, one of the most prominent of which is ballistocardiogram (BCG) artifact. BCG artifacts are generated by movement of EEG electrodes inside the magnetic field due to pulsatile changes in blood flow tied to the cardiac cycle. Independent Component Analysis (ICA) is a statistical algorithm that is useful for removing artifacts that are linearly and independently mixed with signals of interest. Here, we demonstrate and validate the usefulness of ICA in removing BCG artifacts from EEG data acquired in the MRI scanner. In accordance with our hypothesis that BCG artifacts are physiologically independent from EEG, it was found that ICA consistently resulted in five to six independent components representing the BCG artifact. Following removal of these components, a significant reduction in spectral power at frequencies associated with the BCG artifact was observed. We also show that our ICA-based procedures perform significantly better than noise-cancellation methods that rely on estimation and subtraction of averaged artifact waveforms from the recorded EEG. Additionally, the proposed ICA-based method has the advantage that it is useful in situations where ECG reference signals are corrupted or not available.     

Mapping single-trial EEG records on the cortical surface through a spatiotemporal modality

Event-related potentials (ERPs) induced by visual perception and cognitive tasks have been extensively studied in neuropsychological experiments. ERP activities time-locked to stimulus presentation and task performance are often observed separately at individual scalp channels based on averaged time series across epochs and experimental subjects. An analysis using averaged EEG dynamics could discount information regarding interdependency between ongoing EEG and salient ERP features. Advanced tools such as independent component analysis (ICA) have been developed for decomposing collections of single-trial EEG records into separate features. Those features (or independent components) can then be mapped onto the cortical surface using source localization algorithms to visualize brain activation maps and to study between-subject consistency. In this study, we propose a statistical framework for estimating the time course of spatiotemporally independent EEG components simultaneously with their cortical distributions. Within this framework, we implemented Bayesian spatiotemporal analysis for imaging the sources of EEG features on the cortical surface. The framework allows researchers to include prior knowledge regarding spatial locations as well as spatiotemporal independence of different EEG sources. The use of the Electromagnetic Spatiotemporal ICA (EMSICA) method is illustrated by mapping event-related EEG dynamics induced by events in a visual two-back continuous performance task. The proposed method successfully identified several interesting components with plausible corresponding cortical activation topographies, including processes contributing to the late positive complex (LPC) located in central parietal, frontal midline, and anterior cingulate cortex, to atypical mu rhythms associated with the precentral gyrus, and to the central posterior alpha activity in the precuneus.     

Automatic identification of gray and white matter components in polarized light imaging

Polarized light imaging (PLI) enables the visualization of fiber tracts with high spatial resolution in microtome sections of postmortem brains. Vectors of the fiber orientation defined by inclination and direction angles can directly be derived from the optical signals employed by PLI analysis. The polarization state of light propagating through a rotating polarimeter is varied in such a way that the detected signal of each spatial unit describes a sinusoidal signal. Noise, light scatter and filter inhomogeneities, however, interfere with the original sinusoidal PLI signals, which in turn have direct impact on the accuracy of subsequent fiber tracking. Recently we showed that the primary sinusoidal signals can effectively be restored after noise and artifact rejection utilizing independent component analysis (ICA). In particular, regions with weak intensities are greatly enhanced after ICA based artifact rejection and signal restoration.Here, we propose a user independent way of identifying the components of interest after decomposition; i.e., components that are related to gray and white matter. Depending on the size of the postmortem brain and the section thickness, the number of independent component maps can easily be in the range of a few ten thousand components for one brain. Therefore, we developed an automatic and, more importantly, user independent way of extracting the signal of interest. The automatic identification of gray and white matter components is based on the evaluation of the statistical properties of the so-called feature vectors of each individual component map, which, in the ideal case, shows a sinusoidal waveform. Our method enables large-scale analysis (i.e., the analysis of thousands of whole brain sections) of nerve fiber orientations in the human brain using polarized light imaging.     

Model-free fMRI group analysis using FENICA

Exploratory analysis of functional MRI data allows activation to be detected even if the time course differs from that which is expected. Independent Component Analysis (ICA) has emerged as a powerful approach, but current extensions to the analysis of group studies suffer from a number of drawbacks: they can be computationally demanding, results are dominated by technical and motion artefacts, and some methods require that time courses be the same for all subjects or that templates be defined to identify common components. We have developed a group ICA (gICA) method which is based on single-subject ICA decompositions and the assumption that the spatial distribution of signal changes in components which reflect activation is similar between subjects. This approach, which we have called Fully Exploratory Network Independent Component Analysis (FENICA), identifies group activation in two stages. ICA is performed on the single-subject level, then consistent components are identified via spatial correlation. Group activation maps are generated in a second-level GLM analysis. FENICA is applied to data from three studies employing a wide range of stimulus and presentation designs. These are an event-related motor task, a block-design cognition task and an event-related chemosensory experiment. In all cases, the group maps identified by FENICA as being the most consistent over subjects correspond to task activation. There is good agreement between FENICA results and regions identified in prior GLM-based studies. In the chemosensory task, additional regions are identified by FENICA and temporal concatenation ICA that we show is related to the stimulus, but exhibit a delayed response. FENICA is a fully exploratory method that allows activation to be identified without assumptions about temporal evolution, and isolates activation from other sources of signal fluctuation in fMRI. It has the advantage over other gICA methods that it is computationally undemanding, spotlights components relating to activation rather than artefacts, allows the use of familiar statistical thresholding through deployment of a higher level GLM analysis and can be applied to studies where the paradigm is different for all subjects.     

Multiple neural networks supporting a semantic task: An fMRI study using independent component analysis

A visual task for semantic access involves a number of brain regions. However, previous studies either examined the role of each region separately using univariate approach, or analyzed a single brain network using covariance connectivity analysis. We hypothesize that these brain regions construct several functional networks underpinning a word semantic access task, these networks being engaged in different cognitive components with distinct temporal characters. In this paper, multivariate independent component analysis (ICA) was used to reveal these networks based on functional magnetic resonance imaging (fMRI) data acquired during a visual and an auditory word semantic judgment task. Our results demonstrated that there were three task-related independent components (ICs), corresponding to various cognitive components involved in the visual task. Furthermore, ICA separation on the auditory task showed consistency of the results with our hypothesis, regardless of the input modalities.     

Application of independent component analysis to magnetic resonance imaging for enhancing the contrast of gray and white matter

An application of independent component analysis (ICA) was attempted to develop a method of processing magnetic resonance (MR) images to extract physiologically independent components representing tissue relaxation times and achieve improved visualization of normal and pathologic structures. Anatomical T1-weighted, T2-weighted and proton density images were obtained from 10 normal subjects, 3 patients with brain tumors and 1 patient with multiple sclerosis. The data sets were analyzed using ICA based on the learning rule of Bell and Sejnowski after prewhitening operations. The three independent components obtained from the three original data sets corresponded to (1) short T1 components representing myelin of white matter and lipids, (2) relatively short T1 components representing gray matter and (3) long T2 components representing free water. The involvement of gray or white matter in brain tumor cases and the demyelination in the case of multiple sclerosis were enhanced and visualized in independent component images. ICA can potentially achieve separation of tissues with different relaxation characteristics and generate new contrast images of gray and white matter. With the proper choice of contrast for the original images, ICA may be useful not only for extracting subtle or hidden changes but also for preprocessing transformation before clustering and segmenting the structure of the human brain.     

Independent component analysis of short-time Fourier transforms for spontaneous EEG/MEG analysis

Analysis of spontaneous EEG/MEG needs unsupervised learning methods. While independent component analysis (ICA) has been successfully applied on spontaneous fMRI, it seems to be too sensitive to technical artifacts in EEG/MEG. We propose to apply ICA on short-time Fourier transforms of EEG/MEG signals, in order to find more “interesting” sources than with time-domain ICA, and to more meaningfully sort the obtained components. The method is especially useful for finding sources of rhythmic activity. Furthermore, we propose to use a complex mixing matrix to model sources which are spatially extended and have different phases in different EEG/MEG channels. Simulations with artificial data and experiments on resting-state MEG demonstrate the utility of the method.