Grassmannian Kernels for Efficient and Effective Detection of Group Differences in fMRI Data

dc.contributor.authorHabib, Ashfia Binte
dc.contributor.authorGabrielson, Ben
dc.contributor.authorYang, Hanlu
dc.contributor.authorCalhoun, Vince D.
dc.contributor.authorAdali, Tulay
dc.date.accessioned2025-06-17T14:45:42Z
dc.date.available2025-06-17T14:45:42Z
dc.date.issued2025-03
dc.description2025 59th Annual Conference on Information Sciences and Systems (CISS), Baltimore, MD, 19-21 March 2025
dc.description.abstractUnderstanding group differences in multi-subject fMRI data is essential for advancing clinical and research applications. Factorizations such as independent component analysis (ICA) and independent vector analysis (IVA) are useful for extracting components revealing group differences among subject datasets; however, the complexity of factorizations can be intractable over many datasets. To efficiently quantify group differences among datasets, we propose a simple and effective measure of dataset similarity by measuring similarity between datasets’ linear subspaces – the set of all possible components within datasets – via the Grassmannian kernel (GK) between two datasets. By comparing component subspaces and not components themselves, the GK provides a useful summary of the overall group differences existing between two datasets’ components without requiring estimation of the components, resulting in a much more computationally friendly analysis useful as a foundational step for deeper analysis (e.g., assessing whether component-level group differences exist before estimating the components in a finer-grained analysis). We validate the GK’s abilities by showing it successfully identifies meaningful group differences in several functional magnetic resonance imaging (fMRI) datasets, quantified via statistical tests on distribution differences. We further observe that the degree of group separability identified by the GK aligns closely with a detailed analysis, functional network connectivity (FNC) differences derived following application of subject-wise ICA to the datasets. We further demonstrate that in addition to detecting group differences prior to an analysis like ICA or IVA, GK can be also used to guide order selection in fMRI data.
dc.description.sponsorshipThis work was supported in part by grants NSF 2316420, NIH R01MH118695, NIH R01MH123610, and NIH R01AG073949
dc.description.urihttps://ieeexplore.ieee.org/document/10944732
dc.format.extent6 pages
dc.genreconference papers and proceedings
dc.genrepreprints
dc.identifierdoi:10.13016/m2cb7c-beap
dc.identifier.urihttps://doi.org/10.1109/CISS64860.2025.10944732
dc.identifier.urihttp://hdl.handle.net/11603/38933
dc.language.isoen_US
dc.publisherCISS
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department
dc.relation.ispartofUMBC Student Collection
dc.relation.ispartofUMBC Faculty Collection
dc.rightsThis work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.
dc.subjectIVA
dc.subjectKernel
dc.subjectVectors
dc.subjectEstimation
dc.subjectIndependent component analysis
dc.subjectStatistical Testing
dc.subjectfMRI Analysis
dc.subjectICA
dc.subjectUMBC Ebiquity Research Group
dc.subjectUMBC Machine Learning for Signal Processing Lab
dc.subjectPCA
dc.subjectUMBC Machine Learning and Signal Processing Lab (MLSP-Lab)
dc.subjectGrassmannian Kernel
dc.subjectFunctional magnetic resonance imaging
dc.subjectPrincipal component analysis
dc.subjectComplexity theory
dc.subjectUMBC Machine Learning for Signal Processing Laboratory
dc.titleGrassmannian Kernels for Efficient and Effective Detection of Group Differences in fMRI Data
dc.typeText
dcterms.creatorhttps://orcid.org/0000-0001-9217-6641
dcterms.creatorhttps://orcid.org/0000-0001-7903-6257
dcterms.creatorhttps://orcid.org/0000-0003-0594-2796

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
CISS_GK_Plus_FNC_CameraReadyVersion.pdf
Size:
1.47 MB
Format:
Adobe Portable Document Format