Analysis of fMRI data by blind separation into independent spatial components

Independent Component Analysis (ICA) is a promising tool for the analysis of functional magnetic resonance imaging (fMRI) time series. In these studies, mostly assumed is a spatially independent component map of fMRI data (spatial ICA). In this paper, we assume that the temporal courses of the signal and noises are independent within a Tiny spatial domain (temporal ICA). Then with fast-ICA algorithm, spatially neighboring fMRI data were blindly separated into several temporal courses and were preassumed to be formed by a signal time course and several noise time courses where the signal has the largest correlation coefficient with the reference signal. The final functional imaging was completed for the signals obtained from each voxel. Simulations showed that compared with the spatial ICA method, the new temporal ICA method is more effective than the spatial ICA in detecting weak signal in a fMRI dataset. As background noise, the simulations include simulated Gaussian noise and fMRI data without stimulation. Finally, vivo fMRI tests showed that the excited areas evoked by a visual stimuli are mainly in the region of the primary visual cortex and that evoked by auditory stimuli are mainly in the region of the primary temporal cortex.

SCTICA: Sub-packet constrained temporal ICA method for fMRI data analysis

A two-step super-Gaussian independent component analysis approach for fMRI data

Blind source separation (BSS) is commonly used in functional magnetic resonance imaging (fMRI) data analysis. Recently, BSS models based on restricted Boltzmann machine (RBM), one of the building blocks of deep learning models, have been shown to improve brain network identification compared to conventional single matrix factorization models such as independent component analysis (ICA). These models, however, trained RBM on fMRI volumes, and are hence challenged by model complexity and limited training set. In this article, we propose to apply RBM to fMRI time courses instead of volumes for BSS. The proposed method not only interprets fMRI time courses explicitly to take advantages of deep learning models in latent feature learning but also substantially reduces model complexity and increases the scale of training set to improve training efficiency. Our experimental results based on Human Connectome Project (HCP) datasets demonstrated the superiority of the proposed method over ICA and the one that applied RBM to fMRI volumes in identifying task-related components, resulted in more accurate and specific representations of task-related activations. Moreover, our method separated out components representing intermixed effects between task events, which could reflect inherent interactions among functionally connected brain regions. Our study demonstrates the value of RBM in mining complex structures embedded in large-scale fMRI data and its potential as a building block for deeper models in fMRI data analysis.

Independent Component Analysis (ICA) is a popular method that uses statistical principles to separate the mixture into statistically independent non-Gaussian sources. It has been well used in functional Magnetic Resonance Imaging (fMRI) data. However, real fMRI data can rarely be accurately modeled as mixtures of independent components, the convergence of ICA may be impaired. This paper is based on the idea of preconditioned ICA for real data (Picard), which involves a preprocessing L-BFGS strategy based on orthogonal matrix sets. In this study, we designed an experiment to validate the idea that Picard can improve ICA algorithms such as Infomax, Extended-Infomax, and FastICA, respectively named Picard 1, Picard 2, and Picard 3, for fMRI data analysis. Three Picard versions were performed on the simulated and noisy fMRI mixtures to verify the ability to separate independent sources. Experimental results showed that Picard 3 outperformed Picard 1 and Picard 2 on both noiseless and noisy simulated fMRI data, which implied the priority of Picard 3 in fMRI data analysis.

The impact of outliers on signal separation performance of an independent component analysis (ICA) algorithm is an important factor when selecting an ICA algorithm. If an ICA estimator has the property of B-robustness, the influence of an extreme point is bounded, leading to good separation performance in the presence of outliers. Since this property is binary, it does not give the degree of influence an outlier has on the separation performance. To address this issue, a Mamdani-type fuzzy inference, based on the location of a potential outlier and on the skewness of the data set, has been developed. It creates an outlier sensitivity map for an ICA algorithm. The implication of this work is a criterion to switch from one ICA algorithm to another in real time, as determined by the algorithms sensitivity to the data set under consideration. This paper describes estimation of the outlier impact on the separation performance of the non-B-robust FastICA algorithm using a Mamdani-type fuzzy inference. In simulations with data sets contaminated by outliers, the FastICA sensitivity map resembles the separation performance measured by the Amari performance index.

The higher-order statistics based independent component analysis (ICA) algorithm can extract natural image features. Based on the maximum likelihood ICA criterion, and using the weighted orthogonal constrained natural gradient, a new ICA algorithm is proposed. Natural image feature extraction simulation results show that, compared with other ICA algorithms, the proposed algorithm has faster convergence rate, most of the extracted basis vectors are localized in space, frequency, and orientation, which can describe the features of the natural images well, and the corresponding coefficients are very sparse, obey stronger super-Gaussian distribution with very high kurtosis.

Validating the performance of one-time decomposition for fMRI analysis using ICA with automatic target generation process

Separating 4D multi-task fMRI data of multiple subjects by independent component analysis with projection

The role of diversity in complex ICA algorithms for fMRI analysis

Our goal is to develop a novel BCI based on an eye movements system employing EEG signals on-line. Most of the analysis on EEG signals has been performed using ensemble averaging approaches. However,It is suitable to analyze raw EEG signals in signal processing methods for BCI. In order to process raw EEG signals, we used independent component analysis(ICA). However, we do not know which ICA algorithms have good performance. It is important to check which ICA algorithms have good performance to develop BCIs. Previous paper presented extraction rate of saccade-related EEG signals by five ICA algorithms and eight window size. However, three ICA algorithms, the FastICA, the NG-FICA and the JADE algorithms, are based on 4th order statistic and AMUSE algorithm has an improved algorithm named SOBI.Therefore, we must re-select ICA algorithms. In this paper, we add new algorithms; the SOBI and the MILCA. The SOBI is an improved algorithm based on the AMUSE and uses at least two covariance matrices at different time steps. The MILCA use the independency based on mutual information. Using the Fast ICA, the JADE, the AMUSE, the SOBI, and the MILCA, we extract saccade-related EEG signals and check extracting rates. Secondly, in order to get more robustness against EOG noise, we use improved FastICA with reference signals and check extracting rates.

As an important factor in the fast fixed-point algorithm of independent component analysis (ICA), noise has a significant influence on the separate performance of ICA. Unfortunately, the traditional algorithm of noisy ICA did not address the influence of impulsive components. Because the sources were signals mixed with impulsive noise, the Gaussian noisy algorithm will be invalid for separating the sources. In general, those measurements that significantly deviate from the normal pattern of sensed data are considered impulses. In this paper, we introduce a non-linear function based on the S-estimator to identify the impulsive components in the observed data. This approach guarantees that the impulse noise can be detected from the observed signal. Furthermore, a threshold for the impulse components and methods to remove impulse noise and reconstruct the signal is proposed. The proposed technique improves the separate performance of the traditional algorithm for Gaussian noisy ICA. With the proposed method, the fast fixed-point algorithm of ICA is more reliable for noisy situations. The simulation results show the effectiveness of the proposed method.

Analysis of time-evolving data is crucial to understand the functioning of dynamic systems such as the brain. For instance, analysis of functional magnetic resonance imaging (fMRI) data collected during a task may reveal spatial regions of interest, and how they evolve during the task. However, capturing underlying spatial patterns as well as their change in time is challenging. The traditional approach in fMRI data analysis is to assume that underlying spatial regions of interest are static. In this article, using fractional amplitude of low-frequency fluctuations (fALFF) as an effective way to summarize the variability in fMRI data collected during a task, we arrange time-evolving fMRI data as a subjects by voxels by time windows tensor, and analyze the tensor using a tensor factorization-based approach called a PARAFAC2 model to reveal spatial dynamics. The PARAFAC2 model jointly analyzes data from multiple time windows revealing subject-mode patterns, evolving spatial regions (also referred to as networks) and temporal patterns. We compare the PARAFAC2 model with matrix factorization-based approaches relying on independent components, namely, joint independent component analysis (ICA) and independent vector analysis (IVA), commonly used in neuroimaging data analysis. We assess the performance of the methods in terms of capturing evolving networks through extensive numerical experiments demonstrating their modeling assumptions. In particular, we show that (i) PARAFAC2 provides a compact representation in all modes, i.e., subjects, time, and voxels, revealing temporal patterns as well as evolving spatial networks, (ii) joint ICA is as effective as PARAFAC2 in terms of revealing evolving networks but does not reveal temporal patterns, (iii) IVA's performance depends on sample size, data distribution and covariance structure of underlying networks. When these assumptions are satisfied, IVA is as accurate as the other methods, (iv) when subject-mode patterns differ from one time window to another, IVA is the most accurate. Furthermore, we analyze real fMRI data collected during a sensory motor task, and demonstrate that a component indicating statistically significant group difference between patients with schizophrenia and healthy controls is captured, which includes primary and secondary motor regions, cerebellum, and temporal lobe, revealing a meaningful spatial map and its temporal change.

Independent component analysis (ICA) has proved to be a powerful method for exploratory analysis of functional magnetic resonance imaging (fMRI) data. It has been used to uncover unexpected activations in fMRI data derived from brain activation. ICA has been used to characterize other sources of variability in the fMRI signal besides task-related activity, as well as challenging some of the assumptions inherent in other fMRI analysis methods. As a data-driven fMRI analysis technique, the philosophy of ICA is often in disagreement with hypothesis-driven methods. By exploiting the fact that much of fMRI data has deterministic spatial-temporal structure, a scheme employing ICA denoising and least squares (LS) estimation of the evoked hemodynamic response (HDR) is proposed. Simulations suggest that the method is more robust to different noise models compared to naive application of LS. The result is a considerably increased level of significance of activation for a given voxel but still qualitatively similar spatial distribution of activations over all voxels. This suggests that the proposed method has the potential to substantially reduce total scanning time requirements to achieve the same level of statistically significant activation.

We apply the independent component analysis (ICA) algorithm to uncover intrinsic noise in the beam position monitor (BPM) system. Numerical simulations found that ICA is efficient in the BPM noise estimation. The ICA algorithm is applied to the turn-by-turn data at the Relativistic Heavy Ion Collider. We found the distribution of the BPM noise level, which is consistent with the Johnson-Nyquist thermal noise model. The ICA analysis of turn-by-turn data can be used in neuronetwork feasibility of monitoring a storage ring parasitically.