[pymvpa] classification based on individual parameter estimates from FSL

Fri Aug 1 21:35:15 UTC 2014

Hi David,

When you use map2nifti to get an image of your searchlight, if requires 2 inputs.
img=map2nifti(dataset=ds, data=sl_res))
img.to_filename(‘foo.nii.gz’)
So once you run your searchlight like you have it set up (though I’m not sure that what you’re doing with those center_ids is necessary), just pass your original dataset to the map2nifti function along with your res dataset to the ‘data=' argument.

Only the original dataset contains the mapper info that allows you to recapitulate the 3D image, while the second argument, data, will take a result from a searchlight (or any vector/matrix of the right shape).
Hopefully that’ll help you get your searchlight into a form you can visualize.
- Gavin

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Gavin Hanson, B.S.
Research Assistant
Department of Psychology
University of Kansas
1415 Jayhawk Blvd., 534 Fraser Hall
Lawrence, KS 66045

On Aug 1, 2014, at 4:29 AM, David Soto <d.soto.b at gmail.com<mailto:d.soto.b at gmail.com>> wrote:

Thanks for the response, I have not managed to extract the whole-brain classification map...following the 1st example code below, the output from the crossvalidation is
Dataset(array([[ 0.35526316],
       [ 0.35855263]]), sa=SampleAttributesCollection(items=[ArrayCollectable(name='cvfolds', doc=None, value=array([0, 1]), length=2)]), fa=FeatureAttributesCollection(items=[]), a=DatasetAttributesCollection(items=[]))

How can i extract the whole brain classification map? Using niftires does not work either
niftires = map2nifti(res)

niftires.to_filename('/home/dsoto/Documents/fmri/wholebrainsearchlight_results.nii.gz')

Cheers
ds

On Fri, Aug 1, 2014 at 9:41 AM, Nick Oosterhof <nikolaas.oosterhof at unitn.it<mailto:nikolaas.oosterhof at unitn.it>> wrote:

On Jul 31, 2014, at 10:49 PM, David Soto <d.soto.b at gmail.com<mailto:d.soto.b at gmail.com>> wrote:

> Hi, I keep plugging away with this pretty basic classification
> [...]
> I get a whole-brain classification accuracy of around 68%
> (though did not assess significance)
> Then I run a searchlight analyses and looking at the classification accuracy maps it appears like a chance distribution with mean 50% and the max classification accuracy
> around 56%- I wonder how it be that none of the searchlights reaches the level of wholebrain classification ? and if this is the case then can it be the wholebrain classification meaningful at all?

That is quite possible because the whole-brain classification uses many more features than each searchlight.

Assuming there is sufficient signal in the data (which there seems to be in your case) which is not limited to a small subset of features (voxels), generally one sees better classification with more features. This was already reported by Cox et al 2003, and later by e.g. [disclaimer: shameless self promotion] Oosterhof et al 2011. (there are some cases where this might not be true)

There's often tradeoff between spatial selectivity and classification accuracy. In one extreme you use all features for a single classification analysis (i.e. your whole-brain classification), in the other extreme you use one feature at a time (i.e., univariate analysis). A searchlight analysis is somewhere in between, finding a compromise between getting high classification accuracy and good spatial selectivity. But also for a searchlight it holds that neighborhood (sphere or disc) size can affect both classification accuracy and spatial selectivity.

_______________________________________________
Pkg-ExpPsy-PyMVPA mailing list
Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org<mailto:Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org>
http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa

--
http://www1.imperial.ac.uk/medicine/people/d.soto/
_______________________________________________
Pkg-ExpPsy-PyMVPA mailing list
Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org<mailto:Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org>
http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20140801/ad8b926a/attachment.html>