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

Fast spin-echo (FSE) pulse sequences for Magnetic Resonance Imaging (MRI)offer important imaging contrast in clinically feasible scan times.T2-shuffling is widely used to resolve temporal signal dynamics in FSEacquisitions by exploiting temporal correlations via linear latent space and apredefined regularizer. However, predefined regularizers fail to exploit theincoherence especially for 2D acquisitions.Recent self-supervised learningmethods achieve high-fidelity reconstructions by learning a regularizer fromundersampled data without a standard supervised training data set. In thiswork, we propose a novel approach that utilizes a self supervised learningframework to learn a regularizer constrained on a linear latent space whichimproves time-resolved FSE images reconstruction quality. Additionally, inregimes without groundtruth sensitivity maps, we propose joint estimation ofcoil-sensitivity maps using an iterative reconstruction technique. Ourtechnique functions is in a zero-shot fashion, as it only utilizes data from asingle scan of highly undersampled time series images. We perform experimentson simulated and retrospective in-vivo data to evaluate the performance of theproposed zero-shot learning method for temporal FSE reconstruction. The resultsdemonstrate the success of our proposed method where NMSE and SSIM aresignificantly increased and the artifacts are reduced.

Zero-Shot Self-Supervised Joint Temporal Image and Sensitivity Map Reconstruction via Linear Latent Space