Multi-Task fMRI Data Fusion Using IVA and PARAFAC2

Data fusion-the joint analysis of multiple datasets-through coupled factorizations has the promise to enable enhanced knowledge discovery, and hence is an active area. Various formulations of coupled matrix factorizations have been proposed, each with its own modeling assumptions. In this paper, we...

Full description

Saved in:
Bibliographic Details
Main Authors: Lehmann, Isabell, Acar, Evrim, Hasija, Tanuj, Akhonda, M.A.B.S., Calhoun, Vince D., Schreier, Peter J., Adali, Tulay
Format: Conference Proceeding
Language:English
Subjects:
data fusion
Functional magnetic resonance imaging
Independent component analysis
independent vector analysis
Knowledge discovery
multi-task fMRI
Multitasking
PARAFAC2
Reliability
Signal processing
tensor decompositions
Tensors
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Data fusion-the joint analysis of multiple datasets-through coupled factorizations has the promise to enable enhanced knowledge discovery, and hence is an active area. Various formulations of coupled matrix factorizations have been proposed, each with its own modeling assumptions. In this paper, we study two such methods, namely Independent Vector Analysis (IVA), i.e., extension of Independent Component Analysis (ICA) to multiple datasets, and PARAFAC2, a tensor factorization approach. We demonstrate the modeling assumptions of IVA and PARAFAC2 using simulations, revealing that both methods can accurately capture the latent components, albeit with certain differences in capturing the corresponding subject scores. By making use of a rich multi-task functional Magnetic Resonance Imaging (fMRI) dataset, we show how the two methods can be used for achieving two important goals at once, namely capturing group differences between patients with schizophrenia and healthy controls with interpretable components, as well as understanding the relationship across multiple tasks. This is achieved through the definition of source component vectors across datasets.
ISSN:2379-190X
DOI:10.1109/ICASSP43922.2022.9747662