The Orthogonal Analysis of Tensor Decomposition forMultisubject FMRI Analysis

DOI

10.2991/978-94-6463-108-1_79How to use a DOI?

Keywords

fMRI; tensor decomposition; functional network; component; multi subject

Abstract

As neuroimaging technology matures, high-dimensional biomedical data is gradually applied to research. Location of activated regions from multi subject fMRI data is the foundation for exploring functional brain tissue in neuroscience. However, most of the methods ignore the multi-way nature of the data and the crosstalk or overlap in the spatiotemporal representation of the located components. To this end, we propose an orthogonal analysis method based on sparse decomposition of tensors. Specifically, a novel sparse tensor decomposition with orthogonality is designed to decompose the tensor into three matrices (subject, space and time), which can extract common components across subjects and reduce components. To verify the effectiveness of the proposed model, our model is compared with CANDECOMP/PARAFAC decomposition (CPD), tensor independent component analysis (Tensor ICA), independent component analysis, group independent component analysis (GICA), and method based on nonnegative matrix decomposition using simulated data. The experimental results show that our proposed model can effectively locate the activation area and activation time as well as improve the calculation speed of decomposition. Moreover, the components decomposed by our model simply and efficiently represent multi-subject fMRI data which facilitates interpretation and optimization of group fMRI studies.

Copyright

© 2022 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Biao Wang
AU  - Bingjing Cui
AU  - Yipu Zhang
PY  - 2022
DA  - 2022/12/30
TI  - The Orthogonal Analysis of Tensor Decomposition forMultisubject FMRI Analysis
BT  - Proceedings of the 2022 International Conference on Computer Science, Information Engineering and Digital Economy (CSIEDE 2022)
PB  - Atlantis Press
SP  - 711
EP  - 720
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-108-1_79
DO  - 10.2991/978-94-6463-108-1_79
ID  - Wang2022
ER  -