2018
DOI: 10.1016/j.neuroimage.2018.04.070
|View full text |Cite
|
Sign up to set email alerts
|

Extracting orthogonal subject- and condition-specific signatures from fMRI data using whole-brain effective connectivity

Abstract: The study of brain communication based on fMRI data is often limited because such measurements are a mixture of session-to-session variability with subject- and condition-related information. Disentangling these contributions is crucial for real-life applications, in particular when only a few recording sessions are available. The present study aims to define a reliable standard for the extraction of multiple signatures from fMRI data, while verifying that they do not mix information about the different modali… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

5
54
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 44 publications
(59 citation statements)
references
References 64 publications
(146 reference statements)
5
54
0
Order By: Relevance
“…First, the MLR and LDA perform much better than the 1NN for the 4-task discrimination, both with MOU-EC and FC; this does not change when using kNN instead of 1NN. This agrees with 410 previous results on subject identification [112] that are transposed to the present dataset in Fig. 4E.…”
Section: Remark On Cross-validation Schemessupporting
confidence: 92%
See 4 more Smart Citations
“…First, the MLR and LDA perform much better than the 1NN for the 4-task discrimination, both with MOU-EC and FC; this does not change when using kNN instead of 1NN. This agrees with 410 previous results on subject identification [112] that are transposed to the present dataset in Fig. 4E.…”
Section: Remark On Cross-validation Schemessupporting
confidence: 92%
“…For subject identification, MOU-EC performs better than FC in Fig. 4E, in line with previous results [112]. Taken together, these results show that the dynamic model used for MOU-EC is a representation of the BOLD signals that extracts relevant information for both cognitive conditions and individual traits.…”
Section: Remark On Cross-validation Schemessupporting
confidence: 90%
See 3 more Smart Citations