Functional Magnetic Resonance Imaging (fMRI) data of the brain includes activated parenchymal voxels, corresponding to the paradigm performed, non-activated parenchymal voxels and background voxels. Statistical tests, e.g. using the general linear model approach of SPM or the Kolmogorov-Smirnov (KS) non-parametric statistic, are common 'supervised' techniques to look for activation in functional brain MRI. Selection of voxel type by comparing the voxel time course with a model of the expected hemodynamic response function (HRF) from the task paradigm has proven to be difficult due to individual and spatial variance of the measured HRF. For the functional differentiation of brain voxels we introduce a method separating brain voxels based on their features in the time domain using a self-organizing map (SOM) neural network technique without modeling the HRF. Since activation measured by fMRI is related to magnetic susceptibility changes in venous blood which represents only 2 - 5% of brain matter, preprocessing is required to remove the majority of non- activated voxels which dominate learning instead of real activation patterns. Using the auto-correlation function one can select voxels which are candidates of being activated. Features of the time course of the selected voxels can be learned with the SOM. In the first step the SOM is trained by the voxels time course, fitting its neurons to the input. After learning, the neurons have adapted to the intrinsic features space of the voxel time courses. Using the trained SOM, voxel time courses are presented again, now labeled by the neuron having the smallest Euclidean distance to the presented voxel time course. The result of the labeling and the learned feature time course vectors are compared visually with the p-value map of the KS statistic. With the SOM map one can visually separate the voxels based on their features in the time domain into different functional task related classes.
[1]
Karl J. Friston,et al.
Exploring the temporal nature of hemodynamic responses of cortical motor areas using functional MRI
,
1998,
Neurology.
[2]
Karl J. Friston,et al.
Human Brain Function
,
1997
.
[3]
Karl J. Friston,et al.
Statistical parametric maps in functional imaging: A general linear approach
,
1994
.
[4]
Gwilym M. Jenkins,et al.
Time series analysis, forecasting and control
,
1972
.
[5]
Jorma Laaksonen,et al.
SOM_PAK: The Self-Organizing Map Program Package
,
1996
.
[6]
S. Ogawa,et al.
Magnetic resonance imaging of blood vessels at high fields: In vivo and in vitro measurements and image simulation
,
1990,
Magnetic resonance in medicine.
[7]
Karl J. Friston,et al.
Analysis of functional MRI time‐series
,
1994,
Human Brain Mapping.
[8]
Karl J. Friston,et al.
Analysis of fMRI Time-Series Revisited
,
1995,
NeuroImage.
[9]
E C Wong,et al.
Processing strategies for time‐course data sets in functional mri of the human brain
,
1993,
Magnetic resonance in medicine.
[10]
George E. P. Box,et al.
Time Series Analysis: Forecasting and Control
,
1977
.
[11]
Karl J. Friston,et al.
Spatial registration and normalization of images
,
1995
.
[12]
Teuvo Kohonen,et al.
Self-Organizing Maps
,
2010
.
[13]
D. Tank,et al.
Brain magnetic resonance imaging with contrast dependent on blood oxygenation.
,
1990,
Proceedings of the National Academy of Sciences of the United States of America.