Advanced

Dimensionality reduction of fMRI time series data using locally linear embedding.

Mannfolk, Peter LU ; Wirestam, Ronnie LU ; Nilsson, Markus LU ; Ståhlberg, Freddy LU and Olsrud, Johan LU (2010) In Magma 23(5-6). p.327-338
Abstract
OBJECTIVE: Data-driven methods for fMRI analysis are useful, for example, when an a priori model of signal variations is unavailable. However, activation sources are typically assumed to be linearly mixed, although non-linear properties of fMRI data, including resting-state data, have been observed. In this work, the non-linear locally linear embedding (LLE) algorithm is introduced for dimensionality reduction of fMRI time series data. MATERIALS AND METHODS: LLE performance was optimised and tested using simulated and volunteer data for task-evoked responses. LLE was compared with principal component analysis (PCA) as a preprocessing step to independent component analysis (ICA). Using an example data set with known non-linear properties,... (More)
OBJECTIVE: Data-driven methods for fMRI analysis are useful, for example, when an a priori model of signal variations is unavailable. However, activation sources are typically assumed to be linearly mixed, although non-linear properties of fMRI data, including resting-state data, have been observed. In this work, the non-linear locally linear embedding (LLE) algorithm is introduced for dimensionality reduction of fMRI time series data. MATERIALS AND METHODS: LLE performance was optimised and tested using simulated and volunteer data for task-evoked responses. LLE was compared with principal component analysis (PCA) as a preprocessing step to independent component analysis (ICA). Using an example data set with known non-linear properties, LLE-ICA was compared with PCA-ICA and non-linear PCA-ICA. A resting-state data set was analysed to compare LLE-ICA and PCA-ICA with respect to identifying resting-state networks. RESULTS: LLE consistently found task-related components as well as known resting-state networks, and the algorithm compared well to PCA. The non-linear example data set demonstrated that LLE, unlike PCA, can separate non-linearly modulated sources in a low-dimensional subspace. Given the same target dimensionality, LLE also performed better than non-linear PCA. CONCLUSION: LLE is promising for fMRI data analysis and has potential advantages compared with PCA in terms of its ability to find non-linear relationships. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Magma
volume
23
issue
5-6
pages
327 - 338
publisher
Springer
external identifiers
  • wos:000285364200006
  • pmid:20229085
  • scopus:78651265609
ISSN
1352-8661
DOI
10.1007/s10334-010-0204-0
language
English
LU publication?
yes
id
817a798e-3bbf-4346-921b-74588df0d77b (old id 1582155)
alternative location
http://www.ncbi.nlm.nih.gov/pubmed/20229085?dopt=Abstract
date added to LUP
2010-04-07 16:38:53
date last changed
2018-06-17 04:11:15
@article{817a798e-3bbf-4346-921b-74588df0d77b,
  abstract     = {OBJECTIVE: Data-driven methods for fMRI analysis are useful, for example, when an a priori model of signal variations is unavailable. However, activation sources are typically assumed to be linearly mixed, although non-linear properties of fMRI data, including resting-state data, have been observed. In this work, the non-linear locally linear embedding (LLE) algorithm is introduced for dimensionality reduction of fMRI time series data. MATERIALS AND METHODS: LLE performance was optimised and tested using simulated and volunteer data for task-evoked responses. LLE was compared with principal component analysis (PCA) as a preprocessing step to independent component analysis (ICA). Using an example data set with known non-linear properties, LLE-ICA was compared with PCA-ICA and non-linear PCA-ICA. A resting-state data set was analysed to compare LLE-ICA and PCA-ICA with respect to identifying resting-state networks. RESULTS: LLE consistently found task-related components as well as known resting-state networks, and the algorithm compared well to PCA. The non-linear example data set demonstrated that LLE, unlike PCA, can separate non-linearly modulated sources in a low-dimensional subspace. Given the same target dimensionality, LLE also performed better than non-linear PCA. CONCLUSION: LLE is promising for fMRI data analysis and has potential advantages compared with PCA in terms of its ability to find non-linear relationships.},
  author       = {Mannfolk, Peter and Wirestam, Ronnie and Nilsson, Markus and Ståhlberg, Freddy and Olsrud, Johan},
  issn         = {1352-8661},
  language     = {eng},
  number       = {5-6},
  pages        = {327--338},
  publisher    = {Springer},
  series       = {Magma},
  title        = {Dimensionality reduction of fMRI time series data using locally linear embedding.},
  url          = {http://dx.doi.org/10.1007/s10334-010-0204-0},
  volume       = {23},
  year         = {2010},
}