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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Mapping from functional connectivity (FC) to structural connectivity (SC) canfacilitate multimodal brain network fusion and discover potential biomarkersfor clinical implications. However, it is challenging to directly bridge thereliable non-linear mapping relations between SC and functional magneticresonance imaging (fMRI). In this paper, a novel diffusision generativeadversarial network-based fMRI-to-SC (DiffGAN-F2S) model is proposed to predictSC from brain fMRI in an end-to-end manner. To be specific, the proposedDiffGAN-F2S leverages denoising diffusion probabilistic models (DDPMs) andadversarial learning to efficiently generate high-fidelity SC through a fewsteps from fMRI. By designing the dual-channel multi-head spatial attention(DMSA) and graph convolutional modules, the symmetric graph generator firstcaptures global relations among direct and indirect connected brain regions,then models the local brain region interactions. It can uncover the complexmapping relations between fMRI and structural connectivity. Furthermore, thespatially connected consistency loss is devised to constrain the generator topreserve global-local topological information for accurate intrinsic SCprediction. Testing on the public Alzheimer's Disease Neuroimaging Initiative(ADNI) dataset, the proposed model can effectively generate empiricalSC-preserved connectivity from four-dimensional imaging data and shows superiorperformance in SC prediction compared with other related models. Furthermore,the proposed model can identify the vast majority of important brain regionsand connections derived from the empirical method, providing an alternative wayto fuse multimodal brain networks and analyze clinical disease.

DiffGAN-F2S: Symmetric and Efficient Denoising Diffusion GANs for Structural Connectivity Prediction from Brain fMRI