Dimensionality reduction of fMRI time series data using locally linear embedding.
(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:
https://lup.lub.lu.se/record/1582155
- author
- Mannfolk, Peter LU ; Wirestam, Ronnie LU ; Nilsson, Markus LU ; Ståhlberg, Freddy LU and Olsrud, Johan LU
- organization
- publishing date
- 2010
- 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
- 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
- 2016-04-01 13:22:44
- date last changed
- 2022-03-21 18:18:29
@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}}, doi = {{10.1007/s10334-010-0204-0}}, volume = {{23}}, year = {{2010}}, }