Activation detection in event-related fMRI through clustering ofwavelet distributions
- Resource Type
- Conference
- Authors
- Verdoolaege, Geert; Rosseel, Yves
- Source
- 2010 IEEE International Conference on Image Processing Image Processing (ICIP), 2010 17th IEEE International Conference on. :4393-4396 Sep, 2010
- Subject
- Signal Processing and Analysis
Computing and Processing
Time series analysis
Clustering algorithms
Noise
Gaussian distribution
Hemodynamics
Discrete wavelet transforms
fMRI
k-means clustering
generalized Gaussian distribution
Kullback-Leibler divergence
- Language
- ISSN
- 1522-4880
2381-8549
We propose a new method for the detection of activated voxels in event-related BOLD fMRI data. We model the statistics of the wavelet histograms derived from each voxel time series independently through a generalized Gaussian distribution (GGD). We perform k-means clustering of the GGDs characterizing the voxel data in a synthetic data set, using the symmetrized Kullback-Leibler divergence (KLD) as a similarity measure. We compare our technique with GLM modeling and with another clustering method for activation detection that directly uses the wavelet coefficients as features. Our method is shown to be considerably more stable against realistic hemodynamic variability.