StarPlus fMRI data
This page contains data, software and documentation on the fMRI
data set for the StarPlus data. This data was originally
collected by Marcel Just and his colleagues in Carnegie Mellon
University's CCBI.
The
Experiment:
Timing: The experiment consists of a set of trials, and the
data is partitioned into trials. For some of these intervals, the
subject simply rested, or gazed at a fixation point on the
screen. For other trials, the subject was shown a picture and a
sentence, and instructed to press a button to indicate whether the
sentence correctly described the picture. For these trials, the
sentence and picture were presented in sequence, with the picture
presented first on half of the trials, and the sentence presented first
on the other half of the trials. Forty such trials are available
for each subject. The timing within each such trial is as
follows:
- The first stimulus (sentence or picture) was presented at the
begining of the trail (image=1).
- Four seconds later (image=9) the stimulus was removed, replaced
by a blank screen.
- Four seconds later (image=17) the second stimulus was presented.
This remained on the screen for four seconds, or until the subject
pressed the mouse button, whichever came first.
- A rest period of 15 seconds (30 images) was added after the
second stimulus was removed from the screen. Thus, each trial lasted a
total of approximately 27 seconds (approximately 54 images).
Imaging parameters: Images were collected every 500msec. Only a
fraction of the brain of each subject was imaged. The data is marked up
with 25-30 anatomically defined regions (called "Regions of Interest",
or ROIs).
Stimulus and behavioral data: A variety of information is
available for all three data sets, including the exact sentences and
pictures presented, and the subject response times.
The
Data:
The data consists of .mat files that can be directly loaded into
Matlab version 7. The data file for each human subject is
approximately 100Mbytes, so be sure you are on a high-speed line before
attempting to download these. You might want to begin by
downloading just the data for one of these subjects.
- data
for subject 04847
- data
for subject 04799
- data
for subject 05710
- data
for subject 04820
- data
for subject 05675
- data
for subject 05680
hint regarding ROI's: If you
plan to train a classifier to distinguish whether the subject is
viewing a picture or sentence, then you will probably find the best
accuracy if you restrict your program to consider only the following
Regions of Interest (ROI's): {'CALC'
'LIPL' 'LT' 'LTRIA' 'LOPER' 'LIPS' 'LDLPFC'};
The Software:
A zipped collection
of matlab functions is available to visualize and manipulate this
data. The software also includes a Gaussian Naive Bayes
classifier which can be used to train classifiers over this data.
The
Documentation:
The documentation includes a description
of available software routines and documentation
on the data structures used to represent the data.
The impulse response of fMRI activation to an impulse of neural
activity is modeled in "Detection versus Estimation in Event-Related
fMRI: Choosing the Optimal Stimulus Timing," R. Birn, R. Cox, and P.
Bandettini, NeuroImage 15, pp. 252-264 (2002). A matlab function
implementing this impulse response is available here.
Analyses of this data: are described in:
- Keller, T. A., Just, M. A., & Stenger, V. A. (2001). Reading
span and the time-course of cortical activation in sentence-picture
verification. Annual Convention of the Psychonomic Society, Orlando,
FL.
- Wang, X., Mitchell, T., Detecting
cognitive states using machine learning. Iterim working paper,
October 2002.
- Ramish, J., Learning
common features from fMRI data of multiple subjects. Summer project
report, August 2004.
- "Learning
to Identify Overlapping and Hidden Cognitive Processes from fMRI Data,"R.
Hutchinson, T.M. Mitchell, I. Rustandi, submitted to HBM 2005.
- "Learning
to Decode Cognitive States from Brain Images,"T.M. Mitchell, R.
Hutchinson, R.S. Niculescu, F.Pereira, X. Wang, M. Just, and S. Newman,
Machine Learning, Vol. 57, Issue 1-2, pp. 145-175. October
2004.
- "Training
fMRI Classifiers to Detect Cognitive States across Multiple Human
Subjects ," X. Wang, R. Hutchinson, and T. M. Mitchell, Neural
Information Processing Systems 2003. December 2003.
- "Classifying
Instantaneous Cognitive States from fMRI Data," T. Mitchell, R.
Hutchinson, M. Just, R.S. Niculescu, F. Pereira, X. Wang, American
Medical Informatics Association Symposium, October 2003.
- Using
machine learning to detect cognitive states across multiple subjects,
X. Wang, CALD KDD Project report, May, 2003.
Questions or comments: email Tom.Mitchell@cmu.edu or Wei.Wang@cs.cmu.edu