A Spatially Robust ICA Algorithm for Multiple fMRI Data Sets

Ana S. Lukic; Miles N. Wernick; Lars Kai Hansen; Stephen C. Strother

doi:10.1109/ISBI.2002.1029390

A Spatially Robust ICA Algorithm for Multiple fMRI Data Sets

Ana S. Lukic
, Miles N. Wernick
, Lars Kai Hansen
, Stephen C. Strother

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

169 Downloads (Orbit)

Abstract

In this paper we derive an independent-component analysis (ICA) method for analyzing two or more data sets simultaneously. Our model extracts independent components common to all data sets and independent data-set-specific components. We use time-delayed autocorrelations to obtain independent signal components and base our algorithm on prediction analysis. We applied this method to functional brain mapping using functional magnetic resonance imaging (fMRI). The results of our 3-subject analysis demonstrate the robustness of the algoritltm to the spatial misalignment intrinsic in multiple-subject fMRI data sets.

Original language	English
Title of host publication	Proceedings IEEE International Symposium on Biomedical Imaging
Publisher	IEEE
Publication date	2002
Pages	839-842
Article number	1029390
ISBN (Print)	078037584X
DOIs	https://doi.org/10.1109/ISBI.2002.1029390
Publication status	Published - 2002
Event	2002 IEEE International Symposium on Biomedical Imaging - Washington, United States Duration: 7 Jul 2002 → 10 Jul 2002

Conference

Conference	2002 IEEE International Symposium on Biomedical Imaging
Country/Territory	United States
City	Washington
Period	07/07/2002 → 10/07/2002

Access to Document

10.1109/ISBI.2002.1029390

FulltextSubmitted manuscript, 105 KB

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{b1e46e590eba4fb481c43ea3f7a1d57e,

title = "A Spatially Robust ICA Algorithm for Multiple fMRI Data Sets",

abstract = "In this paper we derive an independent-component analysis (ICA) method for analyzing two or more data sets simultaneously. Our model extracts independent components common to all data sets and independent data-set-specific components. We use time-delayed autocorrelations to obtain independent signal components and base our algorithm on prediction analysis. We applied this method to functional brain mapping using functional magnetic resonance imaging (fMRI). The results of our 3-subject analysis demonstrate the robustness of the algoritltm to the spatial misalignment intrinsic in multiple-subject fMRI data sets. ",

author = "Lukic, \{Ana S.\} and Wernick, \{Miles N.\} and Hansen, \{Lars Kai\} and Strother, \{Stephen C.\}",

year = "2002",

doi = "10.1109/ISBI.2002.1029390",

language = "English",

isbn = "078037584X",

pages = "839--842",

booktitle = "Proceedings IEEE International Symposium on Biomedical Imaging",

publisher = "IEEE",

address = "United States",

note = "2002 IEEE International Symposium on Biomedical Imaging, IEEE International Symposium on Biomedical Imaging ; Conference date: 07-07-2002 Through 10-07-2002",

}

Lukic, AS, Wernick, MN, Hansen, LK & Strother, SC 2002, A Spatially Robust ICA Algorithm for Multiple fMRI Data Sets. in Proceedings IEEE International Symposium on Biomedical Imaging., 1029390, IEEE, pp. 839-842, 2002 IEEE International Symposium on Biomedical Imaging, Washington, District of Columbia, United States, 07/07/2002. https://doi.org/10.1109/ISBI.2002.1029390

TY - GEN

T1 - A Spatially Robust ICA Algorithm for Multiple fMRI Data Sets

AU - Lukic, Ana S.

AU - Wernick, Miles N.

AU - Hansen, Lars Kai

AU - Strother, Stephen C.

PY - 2002

Y1 - 2002

N2 - In this paper we derive an independent-component analysis (ICA) method for analyzing two or more data sets simultaneously. Our model extracts independent components common to all data sets and independent data-set-specific components. We use time-delayed autocorrelations to obtain independent signal components and base our algorithm on prediction analysis. We applied this method to functional brain mapping using functional magnetic resonance imaging (fMRI). The results of our 3-subject analysis demonstrate the robustness of the algoritltm to the spatial misalignment intrinsic in multiple-subject fMRI data sets.

AB - In this paper we derive an independent-component analysis (ICA) method for analyzing two or more data sets simultaneously. Our model extracts independent components common to all data sets and independent data-set-specific components. We use time-delayed autocorrelations to obtain independent signal components and base our algorithm on prediction analysis. We applied this method to functional brain mapping using functional magnetic resonance imaging (fMRI). The results of our 3-subject analysis demonstrate the robustness of the algoritltm to the spatial misalignment intrinsic in multiple-subject fMRI data sets.

U2 - 10.1109/ISBI.2002.1029390

DO - 10.1109/ISBI.2002.1029390

M3 - Article in proceedings

SN - 078037584X

SP - 839

EP - 842

BT - Proceedings IEEE International Symposium on Biomedical Imaging

PB - IEEE

T2 - 2002 IEEE International Symposium on Biomedical Imaging

Y2 - 7 July 2002 through 10 July 2002

ER -

A Spatially Robust ICA Algorithm for Multiple fMRI Data Sets

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this