data analysis for fmri
DESCRIPTION
Data Analysis for fMRI. Computational Analyses of Brain Imaging CALD 10-731 and Psychology 85-735 Tom M. Mitchell and Marcel Just January 15, 2003. Ten Minutes of Activity for One Voxel. Indicates experimental condition. …. fMRI Data Visualization [from W. Schneider]. Slice View. - PowerPoint PPT PresentationTRANSCRIPT
1
Data Analysis for fMRI
Computational Analyses of Brain Imaging
CALD 10-731 and Psychology 85-735
Tom M. Mitchell and Marcel Just
January 15, 2003
2
Ten Minutes of Activity for One VoxelIndicates
experimental condition
3
4
…
5
fMRI Data Visualization[from W. Schneider]
Slice View
Time Series
3 D view
Rendered View
Inflated View
6
Many Types of Analysis
• Transformation from fourier space into spatial images, adjusting for head motion, noise, drift,... (FIASCO, SVM)
• Warping individual brains to canonical structure (Talairach, AIR, SPM)
• Identifying voxels activated during task (t-test, F-test,…)• Finding temporally correlated voxels (clustering)• Factoring signal into few components (PCA, ICA)• Modeling temporal evolution of activity (diffeqs, HMMs)• Learning classifiers to detect cognitive states (Bayes, SVM)• Modeling higher cognitive processes (4CAPS, ACT-R) • Combining fMRI with ERP, behavioral data, …
7
Identifying Voxels Activated During Task
For each voxel, vi, calculate t statistic comparing activity of vi during task versus rest condition.
Retain voxels with t-statistic above some threshold
8
Mental Rotation of Imagined Objects
Clock rotation
Shephard-Metz rotation
both
[Just, et al., 2001]
9
“Men listen with only one side of their brains, while women use both”
(IU School of Medicine Department of Radiology)
Men listening
Women listening
Study of Men and Women Listening
10
Identifying Voxels with Similar Time Courses
(functional connectivity)
11
The activation in two cortical areas (parietal/dorsal and inferior temporal/ventral) becomes more synchronized as the object recognition task becomes more difficult.
Easier
Harder
Increase in functional connectivity between parietal and inferior temporal areas with workload
(from Diwadkar, Carpenter, & Just, 2001)
12
Factoring fMRI Signals into Fewer Components
PCA, ICA, SVD, Hidden Units
13
Independent Component Analysis of fMRI time-series
• ICA discovers statistically independent components that combine to form the observed fMRI signal
• ICA is a data-driven approach, complementary to hypothesis-driven methods (e.g. GLM) for analyzing fMRI data
• Finds reduced dimensionality descriptions of poorly understood, high dimensional spaces
• Requires no a-priori knowledge about hemodynamics, noise models, time-courses of subject stimuli,…
14
(McKeown et al., 1998)
Independent Component Analysisof fMRI time-series: data-model
15
fMRI time-series
ICA
algorithm
.
.
. .......
IC #1
IC #2
IC #T
Independent Component Analysisof fMRI Time-series
[from W. Schneider]
16
ICA Solution
IC1
IC2
Independent Component Analysis of fMRI time-series
GLM Solution
Images Elia Formisano & Rainer Goebel 2001
17
Advantages of ICA
• Interpretation of non-explicit condition manipulation – Not just AB type designs– Applications driving, reading, problem solving
• Identify dimensions of poorly understood spaces– Reduce high dimension data to few components– Applications: structure of semantic memory, processes
underlying visual scene analysis in visual cortex
18
Learning Classifiers to Decode Cognitive States from fMRI
Bayes classifiers, SVM’s, kNN, …
19
Study 1: Word Categories
• Family members
• Occupations
• Tools
• Kitchen items
• Dwellings
• Building parts
• 4 legged animals• Fish• Trees• Flowers• Fruits• Vegetables
[Francisco Pereira et al.]
20
Training Classifier for Word CategoriesLearn fMRI(t) word-category(t)
– fMRI(t) = 8470 to 11,136 voxels, depending on subject
Feature selection: Select n voxels– Best single-voxel classifiers
– Strongest contrast between fixation and some word category
– Strongest contrast, spread equally over ROI’s
– Randomly
Training method:– train ten single-subect classifiers
– Gaussian Naïve Bayes P(fMRI(t) | word-category)
21
Results
Classifier outputs ranked list of classesEvaluate by the fraction of classes ranked ahead of true class
0=perfect, 0.5=random, 1.0 unbelievably poor
22
Impact of Feature Selection
23
24
Summary
• Able to classify instantaneous cognitive state– in contrast to describing average activity over time
• Significance– Virtual sensors for mental states– Step toward modeling sequential cognitive processes?– Potential clinical applications: diagnosis = classification
25
Modeling temporal evolution of activity
HMMs, Diffeqs, …
26
Challenge: learn process model -- HMM’s?
a=6,… 3x+a=2
recall correct
recall error
answer
transform correct
transform error
read problem
time
start
…
27
V1
V4
BA37
STG
BA39Perturbing inputs
Stimuli-bound u1(t){e.g. visual words}
DCM [Friston 2002]Aim: Functional integration and the modulation of specific pathways
y
y y
y
y
Contextual inputsStimulus-free -
u2(t){e.g. cognitive set/time}
28
yy
y
Hemodynamic model
},,{ CBA
The DCM and its bilinear approximation [Friston 02]
Inputu(t)
activityx1(t)
activityx3(t)
activityx2(t)
23b
12a
1c
The bilinear model
nnnnn
n
nnn
n
n c
c
u
x
x
bb
bb
u
aa
aa
x
x
11
1
111
1
1111
neuronalchanges
intrinsicconnectivity
inducedresponse
inducedconnectivity
CuxBuAxj
jj )(
))(()( txhty
29
Constraints on•Connections
•Hemodynamic parameters
Applications•Simulations
•Plasticity in single word processing•Attentional modulation of coupling
Models of•Hemodynamics in a single region
•Neuronal interactions
Overview[Friston, 2002]
Bayesian estimation
)(p
)()|()|( pypyp
)|( yp
30
Cognitive Models Grounded in fMRI Data
31
4CAPS Model of Language Processing[Just, et al., 2002]
32
The player was followed by the parent.
[Just, et al., 2002]
334
4CAPS Prediction of fMRI Activity
Figure 10
Model CU
transform
CU in 4CAPS comprehension model components
fMRI
data
Modelprediction
34
[Anderson, Qin,& Sohn, 2002]
35
Cognitive model:
Observed image
sequence:
See word
Recognize word
Understand statement
Answer question
Hypothesized intermediate
states, representations,
processes:
time
Understand question
What We’d Like
36
Machine Learning Problems
• Learn f: image(t) cognitiveState(t)
• Discover useful intermediate abstractions
• Learn process models
6
Cognitive model:
Observed image
sequence:
See word
Recognize word
Understand statement
Answer question
Hypothesized intermediate
states, representations,
processes:
time
Understand question
What We’d Like