Parcellation of fMRI datasets with ICA and PLS: a data driven approach
Inter-subject parcellation of functional Magnetic Resonance Imaging (fMRI) data based on a standard General Linear Model (GLM) and spectral clustering was recently proposed as a means to alleviate the issues associated with spatial normalization in fMRI. However, for all its appeal, a GLM-based par...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Book Section |
| Published: |
Springer
2009
|
| Online Access: | https://eprints.nottingham.ac.uk/1282/ |
| _version_ | 1848790576269361152 |
|---|---|
| author | Ji, Yongnan Hervé, Pierre-Yves Aickelin, Uwe Pitiot, Alain |
| author2 | Yang, Guang-Zhong |
| author_facet | Yang, Guang-Zhong Ji, Yongnan Hervé, Pierre-Yves Aickelin, Uwe Pitiot, Alain |
| author_sort | Ji, Yongnan |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Inter-subject parcellation of functional Magnetic Resonance
Imaging (fMRI) data based on a standard General Linear Model (GLM) and spectral clustering was recently proposed as a means to alleviate the issues associated with spatial normalization in fMRI. However, for all its appeal, a GLM-based parcellation approach introduces its own biases,
in the form of a priori knowledge about the shape of Hemodynamic Response Function (HRF) and task-related signal changes, or about the subject behaviour during the task.
In this paper, we introduce a data-driven version of the spectral clustering parcellation, based on Independent Component Analysis (ICA) and Partial Least Squares (PLS) instead of the GLM. First, a number of independent components are automatically selected. Seed voxels are then
obtained from the associated ICA maps and we compute the PLS latent variables between the fMRI signal of the seed voxels (which covers regional variations of the HRF) and the principal components of the signal across all voxels. Finally, we parcellate all subjects data with a spectral
clustering of the PLS latent variables. We present results of the application of the proposed method on both
single-subject and multi-subject fMRI datasets. Preliminary experimental results, evaluated with intra-parcel variance of GLM t-values and PLS derived t-values, indicate that this data-driven approach offers improvement in terms of parcellation accuracy over GLM based techniques. |
| first_indexed | 2025-11-14T18:14:48Z |
| format | Book Section |
| id | nottingham-1282 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T18:14:48Z |
| publishDate | 2009 |
| publisher | Springer |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-12822020-05-04T20:26:52Z https://eprints.nottingham.ac.uk/1282/ Parcellation of fMRI datasets with ICA and PLS: a data driven approach Ji, Yongnan Hervé, Pierre-Yves Aickelin, Uwe Pitiot, Alain Inter-subject parcellation of functional Magnetic Resonance Imaging (fMRI) data based on a standard General Linear Model (GLM) and spectral clustering was recently proposed as a means to alleviate the issues associated with spatial normalization in fMRI. However, for all its appeal, a GLM-based parcellation approach introduces its own biases, in the form of a priori knowledge about the shape of Hemodynamic Response Function (HRF) and task-related signal changes, or about the subject behaviour during the task. In this paper, we introduce a data-driven version of the spectral clustering parcellation, based on Independent Component Analysis (ICA) and Partial Least Squares (PLS) instead of the GLM. First, a number of independent components are automatically selected. Seed voxels are then obtained from the associated ICA maps and we compute the PLS latent variables between the fMRI signal of the seed voxels (which covers regional variations of the HRF) and the principal components of the signal across all voxels. Finally, we parcellate all subjects data with a spectral clustering of the PLS latent variables. We present results of the application of the proposed method on both single-subject and multi-subject fMRI datasets. Preliminary experimental results, evaluated with intra-parcel variance of GLM t-values and PLS derived t-values, indicate that this data-driven approach offers improvement in terms of parcellation accuracy over GLM based techniques. Springer Yang, Guang-Zhong 2009 Book Section PeerReviewed Ji, Yongnan, Hervé, Pierre-Yves, Aickelin, Uwe and Pitiot, Alain (2009) Parcellation of fMRI datasets with ICA and PLS: a data driven approach. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2009: 12th International Conference, London, UK, September 20-24, 2009: proceedings. Part 1. Lecture notes in computer science (5761). Springer, Berlin, pp. 984-991. ISBN 9783642042683 http://www.springer.com/computer/image+processing/book/978-3-642-04267-6 |
| spellingShingle | Ji, Yongnan Hervé, Pierre-Yves Aickelin, Uwe Pitiot, Alain Parcellation of fMRI datasets with ICA and PLS: a data driven approach |
| title | Parcellation of fMRI datasets with ICA and PLS: a data driven approach |
| title_full | Parcellation of fMRI datasets with ICA and PLS: a data driven approach |
| title_fullStr | Parcellation of fMRI datasets with ICA and PLS: a data driven approach |
| title_full_unstemmed | Parcellation of fMRI datasets with ICA and PLS: a data driven approach |
| title_short | Parcellation of fMRI datasets with ICA and PLS: a data driven approach |
| title_sort | parcellation of fmri datasets with ica and pls: a data driven approach |
| url | https://eprints.nottingham.ac.uk/1282/ https://eprints.nottingham.ac.uk/1282/ |