[pymvpa] the effect of ROI size on classification accuracy
rawi707 at yahoo.com
Mon Jul 21 15:57:49 UTC 2014
If it is not due to C of SVM, maybe you could try smoothing before MNI normalization to see how much it would affect your results. (e.g., due to normalization and voxel oversampling).
> On Monday, July 21, 2014 12:37 PM, Brian Murphy <brian.murphy at qub.ac.uk> wrote:
> > Hi Meng,
> I don't use SVMs so often, but I wonder if it is related to the setting
> of the C or shrinkage parameter? With smoothing you increase the amount
> of co-linearity between the input features, which can make it harder for
> your algorithm to choose among features with similar informativity.
> On Sun, 2014-07-20 at 17:10 +0100, Meng Liang wrote:
>> Dear Jo,
>> Thanks for your reply!
>> I generated a series of smoothed images with Gaussian sigma from 1 mm
>> to 5 mm using the same code (a for loop was used to run different
>> sigma, and FSL smoothing command was used). Smoothing was done on the
>> 4d nifti file directly, so I suppose it is unlikely to change the
>> order of the 3d volumes. By visually inspecting the unsmoothed image
>> and the smoothed image with sigma=1 mm, they look almost identical.
>> The classification accuracies for all different datasets and ROIs were
>> the following:
>> sigma0 sigma1 sigma2 sigma3 sigma4 sigma5
>> ROI1 0.7500 0.7917 0.8333 0.8750 0.8750 0.8750
>> ROI2 0.7917 0.7917 0.7500 0.7500 0.6667 0.6667
>> ROI3 0.7917 0.7917 0.7500 0.7500 0.6250 0.5833
>> Now my impression is that it wasn't due to some mistake but smoothing
>> somehow changed the distribution of the data points in the hyperspace
>> in a strange way for ROI3 so that the classification accuracy was
>> changed. I guess it is theorectically possible.
>> If this is true, it raises another question: can we use smoothing as a
>> way to test whether it is the fine-grained pattern across neiggbouring
>> voxels or the very coarse pattern across different brain regions that
>> drives the successful classification? The above example seems to make
>> the interpretation of the results from such test a bit complicated, as
>> the smoothing can have very different effect on a combined ROI (ROI3)
>> than on the separate ROIs (ROI1 and ROI2). Any thoughts?
>> > Date: Fri, 18 Jul 2014 16:53:54 -0500
>> > From: jetzel at artsci.wustl.edu
>> > To: pkg-exppsy-pymvpa at lists.alioth.debian.org
>> > Subject: Re: [pymvpa] the effect of ROI size on classification
>> > On 7/18/2014 12:06 PM, Meng Liang wrote:
>> > > That's one reason I'm puzzled about the results. Having
> said that,
>> > > sigma=5mm smoothing equals FWHM=11.8mm smoothing, so the smoothed
>> > > image does look considerably smoother than the unsmoothed image.
>> > That helps - I'm more used to thinking in FWHM. 11.8 with 2x2x2
>> > is fairly substantial and likely make some sort of difference in the
>> > results.
>> > > I was also wondering whether this was due to some mistakes. But
>> > > results were generated from the same code (the only difference is
>> > > nifti image files being read into the script). Not sure what
>> > > things to check... Ideas?
>> > Hmm. So you have 4d niftis with the (smoothed or not) functional
>> > plus 3d niftis with the ROI masks, and just send different 4d niftis
>> > the same classification code? I think you're right then to look at
>> > smoothed niftis. Perhaps something went strange with the smoothing
>> > procedure, say resulting in some sort of reordering? You could try
>> > something like running the images through the smoothing code, but
>> > zero (or nearly zero) smoothing, which shouldn't change the actual
>> > functional data, to see if it turns up anything weird (i.e. if the
>> > zero-smoothed images don't exactly match the before-smoothing
>> > Jo
>> > --
>> > Joset A. Etzel, Ph.D.
>> > Research Analyst
>> > Cognitive Control & Psychopathology Lab
>> > Washington University in St. Louis
>> > http://mvpa.blogspot.com/
>> > _______________________________________________
>> > Pkg-ExpPsy-PyMVPA mailing list
>> > Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
> Dr. Brian Murphy
> Lecturer (Assistant Professor)
> Knowledge & Data Engineering (EEECS)
> Queen's University Belfast
> brian.murphy at qub.ac.uk
> Pkg-ExpPsy-PyMVPA mailing list
> Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
More information about the Pkg-ExpPsy-PyMVPA