Hi FSL experts,
I am hoping that you will be able to help me with this sticky problem. I am attempting to run my independent component analysis using FastICA. I am doing this so that I can use the ICASSO program to determine stable components.
I am wondering if there is any way to take the 2d IC results from the FastICA and use the ICA mixing matrix (created during the PCA run in FSL ) to project back into the space of the original data, to create the full timeseries associated with each ICA component (so that the PCA dimensionality reduction is reversed).
Or perhaps FSL has something like ICASSO in its coffers?
Hope you can help - thank you very much,
Lesley
|