English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Single-subject mapping of resting-state brain functional activity tonon-imaging phenotypes is a major goal of neuroimaging. The large majority oflearning approaches applied today rely either on static representations or onshort-term temporal correlations. This is at odds with the nature of brainactivity which is dynamic and exhibit both short- and long-range dependencies.Further, new sophisticated deep learning approaches have been developed andvalidated on single tasks/datasets. The application of these models for thestudy of a different targets typically require exhaustive hyperparametersearch, model engineering and trial and error to obtain competitive resultswith simpler linear models. This in turn limit their adoption and hinder fairbenchmarking in a rapidly developing area of research. To this end, we proposefMRI-S4; a versatile deep learning model for the classification of phenotypesand psychiatric disorders from the timecourses of resting-state functionalmagnetic resonance imaging scans. fMRI-S4 capture short- and long- rangetemporal dependencies in the signal using 1D convolutions and the recentlyintroduced state-space models S4. The proposed architecture is lightweight,sample-efficient and robust across tasks/datasets. We validate fMRI-S4 on thetasks of diagnosing major depressive disorder (MDD), autism spectrum disorder(ASD) and sex classifcation on three multi-site rs-fMRI datasets. We show thatfMRI-S4 can outperform existing methods on all three tasks and can be trainedas a plug&play model without special hyperpararameter tuning for each setting

fMRI-S4: learning short- and long-range dynamic fMRI dependencies using 1D Convolutions and State Space Models