Multiset FMRI Data Analysis with Subject Group Information using Structured Dictionary Learning

A dictionary learning (DL)-based method for analyzing multiple functional magnetic resonance imaging (fMRI) data sets is developed. The algorithm can incorporate subject group information to extract neural activation maps indicative of the group differences and the maps shared across groups. Further...

Full description

Saved in:
Bibliographic Details
Published inProceedings (International Symposium on Biomedical Imaging) pp. 1 - 4
Main Authors Xu, Shuai, Jin, Rui, Kim, Seung-Jun, Calhoun, Vince D., Adali, Tulay
Format Conference Proceeding
LanguageEnglish
Published IEEE 14.04.2025
Subjects
Accuracy
Biomedical imaging
Data analysis
Data mining
Dictionary learning
Estimation
fMRI data analysis
Functional magnetic resonance imaging
group sparsity
Image color analysis
Machine learning
multiset analysis
Online AccessGet full text

Cover

More Information
Summary:A dictionary learning (DL)-based method for analyzing multiple functional magnetic resonance imaging (fMRI) data sets is developed. The algorithm can incorporate subject group information to extract neural activation maps indicative of the group differences and the maps shared across groups. Furthermore, multiple data sets are jointly analyzed to obtain the maps common across data sets and those unique to individual data sets. For this, a novel structured supervised DL problem is formulated. Numerical tests on synthetic and real fMRI data sets verify the effectiveness of the proposed method
ISSN:1945-8452
DOI:10.1109/ISBI60581.2025.10980867