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

In dynamic Magnetic Resonance Imaging (MRI), k-space is typicallyundersampled due to limited scan time, resulting in aliasing artifacts in theimage domain. Hence, dynamic MR reconstruction requires not only modelingspatial frequency components in the x and y directions of k-space but alsoconsidering temporal redundancy. Most previous works rely on image-domainregularizers (priors) to conduct MR reconstruction. In contrast, we focus oninterpolating the undersampled k-space before obtaining images with Fouriertransform. In this work, we connect masked image modeling with k-spaceinterpolation and propose a novel Transformer-based k-space GlobalInterpolation Network, termed k-GIN. Our k-GIN learns global dependencies amonglow- and high-frequency components of 2D+t k-space and uses it to interpolateunsampled data. Further, we propose a novel k-space Iterative Refinement Module(k-IRM) to enhance the high-frequency components learning. We evaluate ourapproach on 92 in-house 2D+t cardiac MR subjects and compare it to MRreconstruction methods with image-domain regularizers. Experiments show thatour proposed k-space interpolation method quantitatively and qualitativelyoutperforms baseline methods. Importantly, the proposed approach achievessubstantially higher robustness and generalizability in cases ofhighly-undersampled MR data. For video presentation, poster, GIF results andcode please check our project page:https://jzpeterpan.github.io/k-gin.github.io/.

Global k-Space Interpolation for Dynamic MRI Reconstruction using Masked Image Modeling