On Clustering fMRI Time Series

@article{Goutte1999OnCF,
  title={On Clustering fMRI Time Series},
  author={Cyril Goutte and Peter Aundal Toft and Egill Rostrup and Finn {\AA}rup Nielsen and Lars Kai Hansen},
  journal={NeuroImage},
  year={1999},
  volume={9},
  pages={298-310}
}
Analysis of fMRI time series is often performed by extracting one or more parameters for the individual voxels. Methods based, e.g., on various statistical tests are then used to yield parameters corresponding to probability of activation or activation strength. However, these methods do not indicate whether sets of voxels are activated in a similar way or in different ways. Typically, delays between two activated signals are not identified. In this article, we use clustering methods to detect… 
View on Elsevier
doi.org
505 Citations
Highly Influential Citations
16
Background Citations
100
Methods Citations
193
Results Citations
6

Figures from this paper

505 Citations

Citation Type

Citation Type

Extracting activated regions of fMRI data using unsupervised learning
TLDR
An improved version of Growing Neural Gas algorithm is applied, which automatically operates on the optimal number of clusters, and shows that the proposed algorithm outperforms them in both artificial and real datasets.
Spatiotemporal clustering of fMRI time series in the spectral domain
Feature‐space clustering for fMRI meta‐analysis
TLDR
It is shown that the feature space clustering approach yields nontrivial results and, in particular, shows interesting differences between individual voxel analysis performed with traditional methods.
Feature Space Clustering for Fmri Meta-analysis Feature-space Clustering
TLDR
This contribution investigates the applicability of a clustering method applied to features extracted from the fMRI data, and shows that the feature space clustering approach yields non-trivial results, and in particular shows interesting di erences between individual voxel analysis performed with traditional methods.
A Spectral Clustering Approach to fMRI Activation Detection
  • Lin Shi, P. Heng, T. Wong
  • Computer Science
    2005 IEEE Engineering in Medicine and Biology 27th Annual Conference
  • 2005
TLDR
An alternative clustering method is proposed, namely spectral cluster analysis (SCA), which uses eigenvectors of a matrix derived from the dataset to cluster the wavelet coefficients extracted from the fMRI time series.
Neural networks approach to clustering of activity in fMRI data
TLDR
Exploiting the intracluster correlations, it is shown that regions of substantial correlation with an external stimulus can be unambiguously separated from other activity.
Detection of Spatial Activation Patterns as Unsupervised Segmentation of fMRI Data
TLDR
This work proposes to simultaneously estimate the optimal representative time courses that summarize the fMRI data well and the partition of the volume into a set of disjoint regions that are best explained by these Representative time courses.
Discovering Structure in the Space of Activation Profiles in fMRI
TLDR
A mixture model is designed that finds the major activation patterns along with their localization maps and derive an algorithm for fitting the model to the fMRI data, which enables functional group analysis independent of spatial correspondence among subjects.
Estimation and classification of fMRI hemodynamic response patterns
Visualizing Brain Activity from fMRI Data
TLDR
This paper proposes a methodology to visualize brain function in a time-varying fashion that will allow neurologists to not only validate the static activation maps, but also to develop a better understanding of temporal characteristics of the activation patterns.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 59 REFERENCES
Analysis of fMRI Time-Series Revisited
TLDR
The approach is predicated on an extension of the general linear model that allows for correlations between error terms due to physiological noise or correlations that ensue after temporal smoothing, and uses the effective degrees of freedom associated with the error term.
Processing strategies for time‐course data sets in functional mri of the human brain
TLDR
The most effective method for image processing involves thresholding by shape as characterized by the correlation coefficient of the data with respect to a reference waveform followed by formation of a cross‐correlation image.
Analysis of fMRI Time-Series Revisited—Again
TLDR
Correct results are presented that replace those of the previous paper and solve the same problem without recourse to heuristic arguments and a proper and unbiased estimator for the error terms are introduced.
Non‐linear Fourier Time Series Analysis for Human Brain Mapping by Functional Magnetic Resonance Imaging
TLDR
A non-linear parametric model for brain activation detection by functional magnetic resonance imaging (FMRI) is proposed that generalizes an existing method for human brain mapping.
Space-time analysis of fMRI by feature space clustering
Quantification in functional magnetic resonance imaging: fuzzy clustering vs. correlation analysis.
Fuzzy clustering of gradient‐echo functional MRI in the human visual cortex. Part I: Reproducibility
TLDR
Fuzzy clustering is a robust, model‐independent method to extract functional information in time and space and intertrial reproducibility of cortical activation is significantly improved by the capability of fuzzy clustering.
Assessment and optimization of functional MRI analyses
TLDR
This report compared several commonly‐used data analysis strategies for conventional fMRI data by evaluating statistical testing, spatial filtering, and thresholding, and found that the independent t‐test and crosscorrelation coefficient were the most powerful statistical tests, performing identically well.
Fuzzy clustering of gradient‐echo functional MRI in the human visual cortex. Part II: Quantification
TLDR
Fuzzy clustering of fMRI data is a robust and efficient method to separate functional brain activation from noise or other sources resulting in time‐dependent signal changes as proven by simulated f MRI data analysis and in vivo data from the visual cortex.
Pattern Recognition and Neural Networks
TLDR
Professor Ripley brings together two crucial ideas in pattern recognition; statistical methods and machine learning via neural networks in this self-contained account.
...
1
2
3
4
5
...