ICAfingerprint function

IC fingerprinting

Implements ICA fingerprinting mainly following De Martino et.al., Neuroimage 2007.

ICAfingerprint(icaobj, nbin = 256, plot = FALSE)

Arguments

• icaobj: object returned by function fmri.sICA.
• nbin: number of bins for entropy estimation
• plot: provide results as star plots.

Details

For some characteristics normalization of values differs from De Martino et. al.. Frequency bands are obtained from periodogram estimated instead of using Welch's method.

Returns

object of class ''fmriICA'' list with components - scomp: 4D array with ICA component images. Last index varies over components.

• X: pre-processed data matrix

• K: pre-processed data matrix

• W: estimated un-mixing matrix

• A: estimated mixing matrix

• mask: Brain mask

• pixdim: voxelsize

• TR: Repetition Time (TR)

• fingerprint: matrix of IC characteristics. Columns correspond to IC's .

References

De Martino et. al., Classification of fMRI independent components using IC-fingerprints and support vector machine classifiers, Neuroimage 34 (2007) 177-194.

Author(s)

Joerg Polzehl polzehl@wias-berlin.de

See Also

fmri.sICA, plot.fmriICA, fastICA