Conference paper
A Spatially Robust ICA Algorithm for Multiple fMRI Data Sets
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 algorithm to the spatial misalignment intrinsic in multiple-subject fMRI data sets.
Language: | English |
---|---|
Year: | 2002 |
Pages: | 839,840,841,842 |
Proceedings: | 2002 IEEE International Symposium on Biomedical Imaging |
ISBN: | 078037584X , 078037584x and 9780780375840 |
Types: | Conference paper |
DOI: | 10.1109/ISBI.2002.1029390 |
ORCIDs: | Hansen, Lars Kai |
3-subject analysis Algorithm design and analysis Autocorrelation Brain mapping Data mining Independent component analysis Magnetic analysis Magnetic resonance imaging Prediction algorithms Robustness Signal analysis algorithm robustness biomedical MRI brain functional brain mapping functional magnetic resonance imaging independent component analysis independent data-set-specific components independent signal components intrinsic spatial misalignment medical diagnostic imaging medical image processing modelling prediction analysis time-delayed autocorrelations