sorry for just a brief reply... > the dataset with a new mask for each ROI. However, I wonder if there is > a quicker option, using the Searchlight and the "center id" parameter? iirc... not
> The idea would be to start with a list of peak voxel coordinates for > each ROI from the nifti image, map these to feature IDs somehow, and > pass the list of ROI IDs to the Searchlight. The result would then be a > (fast!) searchlight analysis, that runs a spherical classifier centered > on each ROI in turn. The resulting classification map should only > contain one voxel per ROI. since I don't know how you set things up, if you assume that ds is full bold NiftiDataset you want to extract roi's from roi_map -- just silly dataset where you loaded your rois with the same mask as you had in ds then just use smth like for roi_coord in [(0,1,2), (0,3,1)]: # to do voxel -> feature_id mapping roi_featureid = ds.mapper.getOutId(roi_coord) # just remember that NiftiImage has reverted coordinates # so you need to use (z,y,x) here # figure out the 'color' of ROI roi_id = roi_map.samples[roi_featureid] # extract all the features from that ROI ds_roi = ds.selectFeatures(N.where(roi_map == roi_id)[0]) # assess what you like to assess on that ds_roi it might not work... just coding right in the email... but it might give you hints... for mapping back and forth of coordinates between voxels/features use ds.mapper.getOutId / getInId hope this helps > Has anyone attempted something similar? I can't quite figure out how to > map the ROI coordinates in the original nifti to the feature ID that > the classifier runs on. > Any help would be greatly appreciated. > Johan > _______________________________________________ > Pkg-ExpPsy-PyMVPA mailing list > [email protected] > http://lists.alioth.debian.org/mailman/listinfo/pkg-exppsy-pymvpa -- Yaroslav Halchenko Research Assistant, Psychology Department, Rutgers-Newark Student Ph.D. @ CS Dept. NJIT Office: (973) 353-1412 | FWD: 82823 | Fax: (973) 353-1171 101 Warren Str, Smith Hall, Rm 4-105, Newark NJ 07102 WWW: http://www.linkedin.com/in/yarik _______________________________________________ Pkg-ExpPsy-PyMVPA mailing list [email protected] http://lists.alioth.debian.org/mailman/listinfo/pkg-exppsy-pymvpa
