Title :
Hybrid multivariate morphology using lattice auto-associative memories for resting-state fMRI network discovery
Author :
Grana, Manuel ; Chyzhyk, D.
Author_Institution :
Dept. CCIA, UPV/EHU, San Sebastian, Spain
Abstract :
Analysis of fMRI data, specifically resting-state fMRI data, is performed here from the point of view of a hybrid Multivariate Mathematical Morphology induced by a supervised h-ordering defined on the fMRI time series by the response of Lattice Auto-associative Memories built from specific fMRI voxels. The supervised h-ordering values and the results of morphological filters, i.e. a morphological top-hat, allow to identify some brain networks depending on the seed voxel value. Results on a set of resting state fMRI images of schizophrenia patients and healthy controls show that these networks can be dependent on the subject class, thus providing discriminant findings that may be useful for machine learning approaches.
Keywords :
biomedical MRI; content-addressable storage; learning (artificial intelligence); medical image processing; time series; fMRI time series; fMRI voxels; healthy controls; hybrid multivariate morphology; lattice auto-associative memories; machine learning approaches; morphological filters; resting-state fMRI network discovery; schizophrenia patients; supervised h-ordering values; Diseases; Independent component analysis; Lattices; Machine learning; Morphology; Vectors; Lattice Computing; Multivariate Mathematical Morphology; Resting state; fMRI;
Conference_Titel :
Hybrid Intelligent Systems (HIS), 2012 12th International Conference on
Conference_Location :
Pune
Print_ISBN :
978-1-4673-5114-0
DOI :
10.1109/HIS.2012.6421391