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

The key to dynamic or multi-contrast magnetic resonance imaging (MRI)reconstruction lies in exploring inter-frame or inter-contrast information.Currently, the unrolled model, an approach combining iterative MRIreconstruction steps with learnable neural network layers, stands as thebest-performing method for MRI reconstruction. However, there are two mainlimitations to overcome: firstly, the unrolled model structure and GPU memoryconstraints restrict the capacity of each denoising block in the network,impeding the effective extraction of detailed features for reconstruction;secondly, the existing model lacks the flexibility to adapt to variations inthe input, such as different contrasts, resolutions or views, necessitating thetraining of separate models for each input type, which is inefficient and maylead to insufficient reconstruction. In this paper, we propose a two-stage MRIreconstruction pipeline to address these limitations. The first stage involvesfilling the missing k-space data, which we approach as a physics-basedreconstruction problem. We first propose a simple yet efficient baseline model,which utilizes adjacent frames/contrasts and channel attention to capture theinherent inter-frame/-contrast correlation. Then, we extend the baseline modelto a prompt-based learning approach, PromptMR, for all-in-one MRIreconstruction from different views, contrasts, adjacent types, andacceleration factors. The second stage is to refine the reconstruction from thefirst stage, which we treat as a general video restoration problem to furtherfuse features from neighboring frames/contrasts in the image domain. Extensiveexperiments show that our proposed method significantly outperforms previousstate-of-the-art accelerated MRI reconstruction methods.

Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction