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

Magnetic resonance imaging (MRI) is a potent diagnostic tool, but suffersfrom long examination times. To accelerate the process, modern MRI machinestypically utilize multiple coils that acquire sub-sampled data in parallel.Data-driven reconstruction approaches, in particular diffusion models, recentlyachieved remarkable success in reconstructing these data, but typically rely onestimating the coil sensitivities in an off-line step. This suffers frompotential movement and misalignment artifacts and limits the application toCartesian sampling trajectories. To obviate the need for off-line sensitivityestimation, we propose to jointly estimate the sensitivity maps with the image.In particular, we utilize a diffusion model -- trained on magnitude images only-- to generate high-fidelity images while imposing spatial smoothness of thesensitivity maps in the reverse diffusion. The proposed approach demonstratesconsistent qualitative and quantitative performance across differentsub-sampling patterns. In addition, experiments indicate a good fit of theestimated coil sensitivities.

Joint Non-Linear MRI Inversion with Diffusion Priors