Estimating time-varying brain connectivity networks from functional MRI time series

Monti, Ricardo Pio; Hellyer, Peter J.; Sharp, David J.; Leech, Robert; Anagnostopoulos, Christoforos; Montana, Giovanni

doi:10.1016/j.neuroimage.2014.07.033

Cited by 156 publications

(182 citation statements)

References 64 publications

Supporting

Mentioning

179

Contrasting

Unclassified

Order By: Relevance

“…6 shows the estimated whole-brain directed connectivity matrices Φ [j] y between ROIs for three distinct states. Only significant connections are shown, tested based on the asymptotic normality of the f-SVAR coefficient estimator in (23), at α = 0.05 with Bonferroni correction. As expected from simulations, the TV-VAR-KM approach produces very noisy estimates for the high-dimensional connectivity matrices.…”

Section: B Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Estimating Dynamic Connectivity States in fMRI Using Regime-Switching Factor Models

Ting

Ombao

Samdin

et al. 2018

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Recent studies on analyzing dynamic brain connectivity rely on sliding-window analysis or timevarying coefficient models which are unable to capture both smooth and abrupt changes simultaneously. Emerging evidence suggests state-related changes in brain connectivity where dependence structure alternates between a finite number of latent states or regimes. Another challenge is inference of full-brain networks with large number of nodes. We employ a Markov-switching dynamic factor model in which the state-driven time-varying connectivity regimes of high-dimensional fMRI data are characterized by lower-dimensional common latent factors, following a regime-switching process. It enables a reliable, data-adaptive estimation of change-points of connectivity regimes and the massive dependencies associated with each regime. We consider the switching VAR to quantity the dynamic effective connectivity. We propose a three-step estimation procedure: (1) extracting the factors using principal component analysis (PCA) and (2) identifying dynamic connectivity states using the factor-based switching vector autoregressive (VAR) models in a state-space formulation using Kalman filter and expectationmaximization (EM) algorithm, and (3) constructing the high-dimensional connectivity metrics for each state based on subspace estimates. Simulation results show that our proposed estimator outperforms the K-means clustering of time-windowed coefficients, providing more accurate estimation of regime dynamics and connectivity metrics in high-dimensional settings. Applications to analyzing restingstate fMRI data identify dynamic changes in brain states during rest, and reveal distinct directed connectivity patterns and modular organization in resting-state networks across different states.

show abstract

Section: B Resultsmentioning

confidence: 99%

“…. , K. Following [23], the K successive timeblocks were repeated for two cycles to emulate the recurring connectivity states. Thus, the state labels and the corresponding state-dependent VAR coefficient matrices (S t , Φ 2) Benchmark with K-means Clustering: We computed factor-SVAR model-based estimates for the state sequence S t , t = 1, .…”

Section: [J]mentioning

confidence: 99%

Estimating Dynamic Connectivity States in fMRI Using Regime-Switching Factor Models

Ting

Ombao

Samdin

et al. 2018

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…ADMM is suitable for constrained optimization problems and is being used extensively since past few years [30,31,32,33]. This technique facilitates solution by decomposing the original objective function into multiple objective functions that are easy to solve.…”

Section: Algorithm Designmentioning

confidence: 99%

Double temporal sparsity based accelerated reconstruction of compressively sensed resting-state fMRI

Aggarwal

Gupta

2017

Computers in Biology and Medicine

View full text Add to dashboard Cite

A number of reconstruction methods have been proposed recently for accelerated functional Magnetic Resonance Imaging (fMRI) data collection. However, existing methods suffer with the challenge of greater artifacts at high acceleration factors. This paper addresses the issue of accelerating fMRI collection via undersampled k -space measurements combined with the proposed Double Temporal Sparsity based Reconstruction (DTSR) method with the l 1 − l 1 norm constraint. The robustness of the proposed DTSR method has been thoroughly evaluated both at the subject level and at the group level on real fMRI data. Results are presented at various acceleration factors. Quantitative analysis in terms of Peak Signal-to-Noise Ratio (PSNR) and other metrics, and qualitative analysis in terms of reproducibility of brain Resting State Networks (RSNs) demonstrate that the proposed method is accurate and robust. In addition, the proposed DTSR method preserves brain networks that are important for studying fMRI data. Compared to the existing accelerated fMRI reconstruction methods, the DTSR method shows promising potential with an improvement of 10-12dB in PSNR with acceleration factors upto 3.5. Simulation results on real data demonstrate that DTSR method can be used to acquire accelerated fMRI with accurate detection of RSNs.

show abstract

“…Previous studies have shown the great potential of SICE networks for analyzing brain connectivity patterns [17,18,19,20] and diagnosing brain diseases [21,22,23,24]. For each subject, the SICE method naturally produces a set of connectivity networks by specifying different sparsity regularization parameters.…”

Section: Introductionmentioning

confidence: 99%

“…In this case, at which sparsity level the SICE network should be used for classification becomes a critical issue, because different connectivity patterns could possess different discriminative power. A common practice is to select one sparsity level from this set of networks [20,22,23] and ignore other sparsity levels. However, there are at least two drawbacks with this approach: 1) It does not fully exploit the information contained in these ignored sparsity levels; 2) The selection of the most appropriate sparsity level is usually carried out by multi-fold cross-validation, which often has high computational complexity and becomes unreliable when the sample size is small.…”

Section: Introductionmentioning

confidence: 99%

Subject-adaptive Integration of Multiple SICE Brain Networks with Different Sparsity

Zhang

Zhou

Wang

2017

Pattern Recognition

View full text Add to dashboard Cite

As a principled method for partial correlation estimation, sparse inverse covariance estimation (SICE) has been employed to model brain connectivity networks, which holds great promise for brain disease diagnosis. For each subject, the SICE method naturally leads to a set of connectivity networks with various sparsity. However, existing methods usually select a single network from them for classification and the discriminative power of this set of networks has not been fully exploited. This paper argues that the connectivity networks at different sparsity levels present complementary connectivity patterns and therefore they should be jointly considered to achieve high classification performance.In this paper, we propose a subject-adaptive method to integrate multiple SICE networks as a unified representation for classification. The integration weight is learned adaptively for each subject in order to endow the method with the flexibility in dealing with subject variations. Furthermore, to respect the manifold geometry of SICE networks, Stein kernel is employed to embed the manifold structure into a kernel-induced feature space, which allows a linear integration of SICE networks to be designed. The optimization of the integration weight and the classification of the integrated networks are performed via a sparse representation framework. Through our method, we provide a unified and effective network representation that is transparent to the sparsity level of SICE networks, and can be readily utilized for further medical analysis. Experimental study on ADHD and ADNI data sets demonstrates that the proposed integration method achieves notable improvement of classification performance in comparison with methods using a single sparsity level of SICE networks and other commonly used integration methods, such as Multiple Kernel Learning. AbstractAs a principled method for partial correlation estimation, sparse inverse covariance estimation (SICE) has been employed to model brain connectivity networks, which holds great promise for brain disease diagnosis. For each subject, the SICE method naturally leads to a set of connectivity networks with various sparsity. However, existing methods usually select a single network from them for classification and the discriminative power of this set of networks has not been fully exploited. This paper argues that the connectivity networks at different sparsity levels present complementary connectivity patterns and therefore they should be jointly considered to achieve high classification performance.In this paper, we propose a subject-adaptive method to integrate multiple SICE networks as a unified representation for classification. The integration weight is learned adaptively for each subject in order to endow the method with the flexibility in dealing with subject variations. Furthermore, to respect the manifold geometry of SICE networks, Stein kernel is employed to embed the manifold structure into a kernel-induced feature space, which allows a linear integration of SIC...

show abstract

Estimating time-varying brain connectivity networks from functional MRI time series

Cited by 156 publications

References 64 publications

Estimating Dynamic Connectivity States in fMRI Using Regime-Switching Factor Models

Estimating Dynamic Connectivity States in fMRI Using Regime-Switching Factor Models

Double temporal sparsity based accelerated reconstruction of compressively sensed resting-state fMRI

Subject-adaptive Integration of Multiple SICE Brain Networks with Different Sparsity

Contact Info

Product

Resources

About