TY - JOUR
T1 - A review of multivariate methods for multimodal fusion of brain imaging data
AU - Sui, Jing
AU - Adali, Tülay
AU - Yu, Qingbao
AU - Chen, Jiayu
AU - Calhoun, Vince D.
N1 - Funding Information:
This work was supported by the National Institutes of Health grants R01EB 006841 and R01EB 005846 (to Calhoun VD), and by the National Sciences Foundation grants 1017718 (to Adali T) and 1016619 (to Calhoun VD).
PY - 2012/2/15
Y1 - 2012/2/15
N2 - The development of various neuroimaging techniques is rapidly improving the measurements of brain function/structure. However, despite improvements in individual modalities, it is becoming increasingly clear that the most effective research approaches will utilize multi-modal fusion, which takes advantage of the fact that each modality provides a limited view of the brain. The goal of multi-modal fusion is to capitalize on the strength of each modality in a joint analysis, rather than a separate analysis of each. This is a more complicated endeavor that must be approached more carefully and efficient methods should be developed to draw generalized and valid conclusions from high dimensional data with a limited number of subjects. Numerous research efforts have been reported in the field based on various statistical approaches, e.g. independent component analysis (ICA), canonical correlation analysis (CCA) and partial least squares (PLS). In this review paper, we survey a number of multivariate methods appearing in previous multimodal fusion reports, mostly fMRI with other modality, which were performed with or without prior information. A table for comparing optimization assumptions, purpose of the analysis, the need of priors, dimension reduction strategies and input data types is provided, which may serve as a valuable reference that helps readers understand the trade-offs of the 7 methods comprehensively. Finally, we evaluate 3 representative methods via simulation and give some suggestions on how to select an appropriate method based on a given research.
AB - The development of various neuroimaging techniques is rapidly improving the measurements of brain function/structure. However, despite improvements in individual modalities, it is becoming increasingly clear that the most effective research approaches will utilize multi-modal fusion, which takes advantage of the fact that each modality provides a limited view of the brain. The goal of multi-modal fusion is to capitalize on the strength of each modality in a joint analysis, rather than a separate analysis of each. This is a more complicated endeavor that must be approached more carefully and efficient methods should be developed to draw generalized and valid conclusions from high dimensional data with a limited number of subjects. Numerous research efforts have been reported in the field based on various statistical approaches, e.g. independent component analysis (ICA), canonical correlation analysis (CCA) and partial least squares (PLS). In this review paper, we survey a number of multivariate methods appearing in previous multimodal fusion reports, mostly fMRI with other modality, which were performed with or without prior information. A table for comparing optimization assumptions, purpose of the analysis, the need of priors, dimension reduction strategies and input data types is provided, which may serve as a valuable reference that helps readers understand the trade-offs of the 7 methods comprehensively. Finally, we evaluate 3 representative methods via simulation and give some suggestions on how to select an appropriate method based on a given research.
KW - CCA
KW - ICA
KW - MRI
KW - Multimodal fusion
KW - Multivariate methods
KW - PLS
UR - http://www.scopus.com/inward/record.url?scp=84855185464&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84855185464&partnerID=8YFLogxK
U2 - 10.1016/j.jneumeth.2011.10.031
DO - 10.1016/j.jneumeth.2011.10.031
M3 - Review article
C2 - 22108139
AN - SCOPUS:84855185464
SN - 0165-0270
VL - 204
SP - 68
EP - 81
JO - Journal of Neuroscience Methods
JF - Journal of Neuroscience Methods
IS - 1
ER -