A (very) brief introduction to multivoxel analysis “stuff”. Jo Etzel, Social Brain Lab firstname.lastname@example.org. Mass univariate (spm) Test every voxel separately Fit a linear model to each voxel Look for brain structures where the blobs occur Obtain a p -value for each voxel
A (very) brief introduction to multivoxel analysis “stuff”
Jo Etzel, Social Brain Lab
Mass univariate (spm)
Test every voxel separately
Fit a linear model to each voxel
Look for brain structures where the blobs occur
Obtain a p-value for each voxel
Use parametric (or permutation) statistics to evaluate significance
Test groups of voxels (ROIs) at once
Use machine learning algorithms
Structures first (no blobs)
Obtain a classification accuracy for each ROI
Evaluate significance of accuracy by permutation testing and perhaps subsetting (parametric statistics also possible)
listening to hand action sounds
listening to mouth action sounds
Is the brain activity in this ROI different while listening to hand and mouth action sounds?
Can the activity in the right premotor cortex classify the volumes into hand and mouth action sounds?
- or -
temporal compression; extract GLM parameter estimates
for each ROI in each volume (or summary volume)
2nd test: mouth vs. hand?
1st train: mouth vs. hand?
accuracy (from test set)
* P < 0. 0042, permutation test
(Bonferroni correction) of 0.05 for
So, have which ROIs allowed significant classification accuracy for separating mouth and hand action sounds: preML, preMR, M1L, S2R, audL, audR.
null hypothesis is arbitrary labeling
If labeling is arbitrary (random), then there is no relationship between the labels and the activity, so classification should not be possible.
real data classified about the same as arbitrary data: no evidence for a relationship between the labels and the activity: not significant.
real data is classified better than the arbitrary data: it is “unusual:” significant.
classify the real data
make many randomized-label data sets (arbitrary or “fake” data).
classify each fake data set in the same way as the real data
proportion of fake data sets classified better than the real data is the p-value
1. Analyze the real data (get accuracy).
M1 L = 0.6000
2. Make lots of permuted-label data sets (all if possible, at least 1,000).
3. Analyze the fake data sets (get accuracies).
0.4944 0.510 0.499 0.5211 0.480 0.5002 0.498 0.519 0.5720 0.4789 …
4. Count how many of the fake data sets were classified more accurately than the real data.
Of 1000 fake data sets, none had accuracy higher than 0.60.
5. Divide and get the p-value.
(50/1001 = 0.0499)
1/1001 = 0.000999, so
M1 L p = 0.001
Permutation test results, showing true results with uncorrected p-value cutoff lines. True mean accuracy lines that fall above the range of the permuted lines are highly significant (p= 0.002).
Random Forests (RFs)
first fMRI use, I think
algorithm makes 10,000 CARTs, all try to classify, majority vote final class
algorithm makes random variable selections for the “forest” of “trees”
support vector machines (svms)
previously used with fMRI data
algorithm converts data to a higher dimension to try to find a linear separating line (hyperplane) between the classes.
Linear discriminant analysis
Gaussian Naïve Bayes
Hidden Markov Models
Partial Least Squares
For more info/review:
Mitchell, Machine Learning, 2004, 145-175;
O’toole, Journal of Cognitive Neuroscience, 2007, 1735-1753.
Other classification-type algorithms
volumes when recalling
volumes when learning items in each category
“For each brain scan, the classifier produced an estimate of the match between the current testing pattern and each of the three study contexts.”
“However, follow-up analyses indicated that voxels outside of peak category-selective areas are also important for establishing this result.”
The permutation and t-test p-values are very highly correlated, though not always identical.
Calculated correlation line in solid, perfect in dotted.