Showing papers by "Tulay Adali published in 2012"

Multisubject Independent Component Analysis of fMRI: A Decade of Intrinsic Networks, Default Mode, and Neurodiagnostic Discovery

Abstract: Since the discovery of functional connectivity in fMRI data (i.e., temporal correlations between spatially distinct regions of the brain) there has been a considerable amount of work in this field. One important focus has been on the analysis of brain connectivity using the concept of networks instead of regions. Approximately ten years ago, two important research areas grew out of this concept. First, a network proposed to be “a default mode of brain function” since dubbed the default mode network was proposed by Raichle. Secondly, multisubject or group independent component analysis (ICA) provided a data-driven approach to study properties of brain networks, including the default mode network. In this paper, we provide a focused review of how ICA has contributed to the study of intrinsic networks. We discuss some methodological considerations for group ICA and highlight multiple analytic approaches for studying brain networks. We also show examples of some of the differences observed in the default mode and resting networks in the diseased brain. In summary, we are in exciting times and still just beginning to reap the benefits of the richness of functional brain networks as well as available analytic approaches.

Joint Blind Source Separation With Multivariate Gaussian Model: Algorithms and Performance Analysis

Abstract: In this paper, we consider the joint blind source separation (JBSS) problem and introduce a number of algorithms to solve the JBSS problem using the independent vector analysis (IVA) framework. Source separation of multiple datasets simultaneously is possible when the sources within each and every dataset are independent of one another and each source is dependent on at most one source within each of the other datasets. In addition to source separation, the IVA framework solves an essential problem of JBSS, namely the identification of the dependent sources across the datasets. We propose to use the multivariate Gaussian source prior to achieve JBSS of sources that are linearly dependent across datasets. Analysis within the paper yields the local stability conditions, nonidentifiability conditions, and induced Cramer-Rao lower bound on the achievable interference to source ratio for IVA with multivariate Gaussian source priors. Additionally, by exploiting a novel nonorthogonal decoupling of the IVA cost function we introduce both Newton and quasi-Newton optimization algorithms for the general IVA framework.

High classification accuracy for schizophrenia with rest and task FMRI data.

Abstract: We present a novel method to extract classification features from functional magnetic resonance imaging (fMRI) data collected at rest or during the performance of a task. By combining a two-level feature identification scheme with kernel principal component analysis (KPCA) and Fisher’s linear discriminant analysis (FLD), we achieve high classification rates in discriminating healthy controls from patients with schizophrenia. Experimental results using leave-one-out cross-validation show that features extracted from the default mode network (DMN) lead to a classification accuracy of over 90% in both data sets. Moreover, using a majority vote method that uses multiple features, we achieve a classification accuracy of 98% in auditory oddball (AOD) task and 93% in rest data. Several components, including DMN, temporal, and medial visual regions, are consistently present in the set of features that yield high classification accuracy. The features we have extracted thus show promise to be used as biomarkers for schizophrenia. Results also suggest that there may be different advantages to using resting fMRI data or task fMRI data.

Group Study of Simulated Driving fMRI Data by Multiset Canonical Correlation Analysis

Abstract: In this work, we apply a novel statistical method, multiset canonical correlation analysis (M-CCA), to study a group of functional magnetic resonance imaging (fMRI) datasets acquired during simulated driving task. The M-CCA method jointly decomposes fMRI datasets from different subjects/sessions into brain activation maps and their associated time courses, such that the correlation in each group of estimated activation maps across datasets is maximized. Therefore, the functional activations across all datasets are extracted in the order of consistency across different dataset. On the other hand, M-CCA preserves the uniqueness of the functional maps estimated from each dataset by avoiding concatenation of different datasets in the analysis. Hence, the cross-dataset variation of the functional activations can be used to test the hypothesis of functional-behavioral association. In this work, we study 120 simulated driving fMRI datasets and identify parietal-occipital regions and frontal lobe as the most consistently engaged areas across all the subjects and sessions during simulated driving. The functional-behavioral association study indicates that all the estimated brain activations are significantly correlated with the steering operation during the driving task. M-CCA thus provides a new approach to investigate the complex relationship between the brain functions and multiple behavioral variables, especially in naturalistic tasks as demonstrated by the simulated driving study.

Constrained source-based morphometry identifies structural networks associated with default mode network.

Abstract: We present constrained source-based morphometry (SBM), a multivariate semiblind data-driven approach, to explore a possible brain-wide structural network in both gray matter (GM) and white matter (WM) associated with the functional default mode network (DMN). With this approach, we utilize seed regions associated with the DMN as constraints on GM maps and derive a joint GM and WM structural network automatically through a multivariate data-driven approach. In this article, we first provide a simulation to validate the constrained SBM approach. The approach was then applied to structural magnetic resonance imaging and diffusion tensor imaging data obtained from 102 healthy controls. Regions that have consistently reported to be associated with the DMN were used to create an a priori mask that was integrated within an independent component analysis framework to derive the structural network associated with the DMN. We identified a set of GM and corresponding WM regions contributing to a structural ...

An effective decoupling method for matrix optimization and its application to the ICA problem

Abstract: Matrix optimization of cost functions is a common problem. Construction of methods that enable each row or column to be individually optimized, i.e., decoupled, are desirable for a number of reasons. With proper decoupling, the convergence characteristics such as local stability can be improved. Decoupling can enable density matching in applications such as independent component analysis (ICA). Lastly, efficient Newton algorithms become tractable after decoupling. The most common method for decoupling rows is to reduce the optimization space to orthogonal matrices. Such restrictions can degrade performance. We present a decoupling procedure that uses standard vector optimization procedures while still admitting nonorthogonal solutions. We utilize the decoupling procedure to develop a new decoupled ICA algorithm that uses Newton optimization enabling superior performance when the sample size is limited.

Complex-Valued Linear and Widely Linear Filtering Using MSE and Gaussian Entropy

Abstract: In this paper, we study the performance of mean square error (MSE) and Gaussian entropy criteria for linear and widely linear complex filtering. The MSE criterion has been extensively studied, and with a widely linear filter form, it can take into account the full second-order statistics of the input signal. However, it cannot exploit the full second-order statistics of the error, and doubles the dimension of the parameter vector to be estimated. In this paper, we introduce the use of Gaussian entropy criterion such that full second-order statistics of the error can be taken into account, and compare the performance of the Gaussian entropy and MSE criteria for a linear and widely linear filter implementation in batch and adaptive implementations. Detailed performance analysis with numerical examples is presented to investigate the relationship and performance differences of the two criteria in diverse scenarios.

Three-way FMRI-DTI-methylation data fusion based on mCCA+jICA and its application to schizophrenia

Abstract: Multi-modal fusion is an effective approach in biomedical imaging which combines multiple data types in a joint analysis and overcomes the problem that each modality provides a limited view of the brain. In this paper, we propose an exploratory fusion model, we term “mCCA+jICA”, by combining two multivariate approaches: multi-set canonical correlation analysis (mCCA) and joint independent component analysis (jICA). This model can freely combine multiple, disparate data sets and explore their joint information in an accurate and effective manner, so that high decomposition accuracy and valid modal links can be achieved simultaneously. We compared mCCA+jICA with its alternatives in simulation and applied it to real fMRI-DTI-methylation data fusion, to identify brain abnormalities in schizophrenia. The results replicate previous reports and add to our understanding of the neural correlates of schizophrenia, and suggest more generally a promising approach to identify potential brain illness biomarkers.

A Class of Adaptive Algorithms Based on Entropy Estimation Achieving CRLB for Linear Non-Gaussian Filtering

Abstract: Adaptive filtering has been extensively studied under the assumption that the noise is Gaussian. The most commonly used least-mean-square-error (LMSE) filter is optimal when the noise is Gaussian. However, in many practical applications, the noise can be modeled more accurately using a non-Gaussian distribution. In this correspondence, we consider non-Gaussian distributions for the noise model and show that the filter of using entropy bound minimization (EBM) leads to significant performance gain compared to the LMSE filter. The least mean p-norm (LMP) filter using the α-stable distribution to model noise is shown to be the maximum-likelihood solution when using the generalized Gaussian distribution (GGD) to model noise. The GGD model for noise allows us to compute the Cramer-Rao lower bound (CRLB) for the error in estimating the weights. Simulations show that both the EBM and LMP filters achieve the CRLB as the sample size increases. The EBM filter is shown to be less committed with respect to unseen data yielding generally superior performance in online learning when compared to LMP. We also show that, when the noise comes from impulsive α -stable distributions, both the EBM and LMP filters provide better performance than LMSE. In addition, the EBM filter offers the advantage that it does not assume a certain parametric model for the noise, and by proper selection of the measuring functions, it can be adapted to a wide range of noise distributions.

IVA and ICA: Use of diversity in independent decompositions

Abstract: Starting with a simple linear generative model and the assumption of statistical independence of the underlying components, independent component analysis (ICA) decomposes a given set of observations by making use of the diversity in the data. Most of the ICA algorithms introduced to date have made use of one of the two types of diversity, non-Gaussianity or sample dependence. We first discuss the main results for ICA in terms of identifiability and performance with these two types of diversity, and then introduce independent vector analysis (IVA), generalization of ICA for decomposition of multiple datasets at a time. We show that the role of diversity in this case parallels that in ICA, and discuss identifiability conditions and performance bounds in a maximum likelihood framework.

Structural Angle and Power Images Reveal Interrelated Gray and White Matter Abnormalities in Schizophrenia

Abstract: We present a feature extraction method to emphasize the interrelationship between gray and white matter and identify tissue distribution abnormalities in schizophrenia. This approach utilizes novel features called structural phase and magnitude images. The phase image indicates the relative contribution of gray and white matter, and the magnitude image reflects the overall tissue concentration. Three different analyses are applied to the phase and magnitude images obtained from 120 healthy controls and 120 schizophrenia patients. First, a single-subject subtraction analysis is computed for an initial evaluation. Second, we analyze the extracted features using voxel based morphometry (VBM) to detect voxelwise group differences. Third, source based morphometry (SBM) analysis was used to determine abnormalities in structural networks that co-vary in a similar way. Six networks were identified showing significantly lower white-to-gray matter in schizophrenia, including thalamus, right precentral-postcentral, left pre/post-central, parietal, right cuneus-frontal, and left cuneus-frontal sources. Interestingly, some networks look similar to functional patterns, such as sensory-motor and vision. Our findings demonstrate that structural phase and magnitude images can naturally and efficiently summarize the associated relationship between gray and white matter. Our approach has wide applicability for studying tissue distribution differences in the healthy and diseased brain.

A Novel Approach for Target Detection and Classification Using Canonical Correlation Analysis

Abstract: We present a novel detection approach, detection with canonical correlation (DCC), for target detection without prior information on the interference. We use the maximum canonical correlations between the target set and the observation data set as the detection statistic, and the coefficients of the canonical vector are used to determine the indices of components from a given target library, thus enabling both detection and classification of the target components that might be present in the mixture. We derive an approximate distribution of the maximum canonical correlation when targets are present. For applications where the contributions of components are non-negative, non-negativity constraints are incorporated into the canonical correlation analysis framework and a recursive algorithm is derived to obtain the solution. We demonstrate the effectiveness of DCC and its nonnegative variant by applying them on detection of surface-deposited chemical agents in Raman spectroscopy.

Order detection for dependent samples using entropy rate

Abstract: Detecting the number of signals in a given number of observations, or order detection, is one of the key issues in many signal processing problems. Information theoretic criteria are widely used to estimate the order. In many applications, data does not follow the independently and identically distributed (i.i.d.) sampling assumption. Previous approaches address dependent samples by downsampling the dataset so that existing order detection methods can be used. By downsampling the data, the sample size is decreased so that the accuracy of the order estimation is degraded. In this paper, we introduce two linear mixture models with dependent samples. The likelihood for each model is developed based on the entire data set and used in an information theoretic framework to improve the order estimation performance for dependent samples. Experimental results show performance improvement using this new method.

Order Selection of the Linear Mixing Model for Complex-Valued FMRI Data

Abstract: Functional magnetic resonance imaging (fMRI) data are originally acquired as complex-valued images, which motivates the use of complex-valued data analysis methods. Due to the high dimension and high noise level of fMRI data, order selection and dimension reduction are important procedures for multivariate analysis methods such as independent component analysis (ICA). In this work, we develop a complex-valued order selection method to estimate the dimension of signal subspace using information-theoretic criteria. To correct the effect of sample dependence to information-theoretic criteria, we develop a general entropy rate measure for complex Gaussian random process to calibrate the independent and identically distributed (i.i.d.) sampling scheme in the complex domain. We show the effectiveness of the approach for order selection on both simulated and actual fMRI data. A comparison between the results of order selection and ICA on real-valued and complex-valued fMRI data demonstrates that a fully complex analysis extracts more meaningful components about brain activation.

Complex-valued analysis and visualization of fMRI data for event-related and block-design paradigms

Abstract: Independent Component Analysis (ICA) has been noted to be promising for the study of functional magnetic resonance imaging (fMRI) data also in its native complex-valued form. In this paper, we demonstrate the first successful application of group ICA to complex-valued fMRI data of an event-related paradigm. We show that networks associated with event-related responses as well as intrinsic fluctuations of hemodymamic activity can be extracted for data collected during an auditory oddball paradigm. The intrinsic networks are of particular interest due to their potential to study cognitive function and mental illness, including schizophrenia. More importantly, we show that analysis of fMRI data in its complex form can increase the sensitivity and specificity in the detection of activated brain regions both for event-related and block design paradigms when compared to magnitude-only applications. In addition, we introduce a novel fMRI phase-based visualization (FPV) technique to identify activated voxels such that the complex nature of the data is fully taken into account.

Joint blind source separation: Applications in medical image analysis

Abstract: Blind source separation (BSS) is based on a simple generative model and hence minimizes the assumptions on the nature of data. It provides a promising alternative to the traditional model-based approaches in many applications where the underlying dynamics are hard to characterize. Independent component analysis (ICA), in particular, has been a popular BSS approach and an active area of research. By imposing the constraint of statistical independence on the underlying components, ICA recovers linearly mixed components subject to only a scaling and permutation ambiguity, and has been successfully applied to numerous problems in areas as diverse as biomedicine, communications, finance, geophysics, and remote sensing.