Validating the independent components of neuroimaging time series via clustering and visualization

By Johan Himberg, Aapo Hyvärinen, Fabrizio Esposito. NeuroImage, 2004

1,317 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/4f1b49ee8da095f91f447ce8a7ab846ad1a3161a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cultural Studies

In Museology

Citations in the corpus

Advances and Pitfalls in the Analysis and Interpretation of Resting-State FMRI Data (2010, neutral): “This type of variability can be reduced when selecting more stringent convergence criteria and software now exists that enables ICA repeatability testing (e.g., ICASSO; Himberg et al., 2004), which can be used to investigate the degree of variability, and estimate ‘average’ decompositions from acros”
Estimating the number of independent components for functional magnetic resonance imaging data (2007, methodology): “The stability on the ICA estimation is studied by, e.g., Himberg et al. (2004), Meinecke et al. (2002), and Ylipaavalniemi and Vigario (2004).”
Abnormal intrinsic brain functional network dynamics in Parkinson’s disease (2017, methodology): “The reliability of the Infomax ICA algorithm’s estimation was evaluated through a comparison against 20 iterative estimates using ICASSO implemented in GIFT (Himberg et al., 2004).”
Functional segmentation of the brain cortex using high model order group PICA (2009, methodology): “The conservative cluster quality index I q was used to estimate individual component repeatability [Himberg et al., 2004].”
DirectLiNGAM: A Direct Method for Learning a Linear Non-Gaussian Structural Equation Model (2011, background): “…potential problems: i) Most ICA algorithms including FastICA [12] and gradient-based algorithms [11] may not converge to a correct solution in a ﬁnite number of steps if the initially guessed state is badly chosen [13] or if the step size is not suitably selected for those gradient-based methods.”
Multi-level bootstrap analysis of stable clusters in resting-state fMRI (2009, background): “However, and despite some initial attempts (Himberg et al., 2004), the stability of the invidual maps themselves was not assessed unless some test-retest database was available (Zuo et al.”
A Baseline for the Multivariate Comparison of Resting-State Networks (2011, methodology): “The quality of component clusters was quantified using the index I q , which ranges from 0 to 1 and reflects the difference between intra-cluster and extra-cluster similarity (Himberg et al., 2004).”
Analysis of functional image analysis contest (FIAC) data with brainvoyager QX: From single‐subject to cortically aligned group general linear model analysis and self‐organizing group independent component analysis (2006, methodology): “The similarity matrix is then transformed into a dissimilarity matrix, which is used as a “spatial distance” matrix within a hierarchical clustering algorithm [see also Himberg et al., 2004].”
Impact of Mindfulness-Based Stress Reduction Training on Intrinsic Brain Connectivity (2011, methodology): “Multiple runs (20 iterations) of ICA were performed using ICASSO to determine the reliability of the ICA algorithm (Himberg et al., 2004).”
CLASSIFICATION OF SCHIZOPHRENIA AND BIPOLAR PATIENTS USING STATIC AND DYNAMIC RESTING-STATE FMRI BRAIN CONNECTIVITY (2016, methodology): “The Infomax ICA algorithmwas repeated 20 times in ICASSO and the resulting components were clustered to estimate the reliability of the decomposition (Himberg et al., 2004).”
Reliable Intrinsic Connectivity Networks: Test-Retest Evaluation Using ICA and Dual Regression Approach (2009, neutral): “Finally, the initial values for ICA estimation are random, which introduces further variability into the findings (Himberg et al., 2004; Yang et al., 2008).”
Toward discovery science of human brain function (2010, methodology): “An alternative hierarchical clustering approach based on ICASSO (9) is described below.”
Independent component analysis of fMRI group studies by self-organizing clustering (2005, methodology): “As in a previous application of MDS to neuroimaging timeseries (Himberg et al., 2004), we used Curvilinear Component Analysis (CCA) (Demartines and Herault, 1997) for cluster visualization because we have found this variant to be computationally efficient as well as suitable for this present applica”
Causal modelling combining instantaneous and lagged effects: an identifiable model based on non-Gaussianity (2008, methodology): “We also ran the method many times to exclude the problem of the ICA estimation algorithm (used in LiNGAM estimation) getting stuck in local minima (Himberg et al., 2004), and the result was found to be robust with respect to that manipulation.”
Group information guided ICA for fMRI data analysis (2013, neutral): “In order to obtain reliable GICs, ICASSO (Himberg et al., 2004) can be used to cluster the results of multiple ICA runs.”