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) provides high spatial resolution andexcellent soft-tissue contrast without using harmful ionising radiation.Dynamic MRI is an essential tool for interventions to visualise movements orchanges of the target organ. However, such MRI acquisition with high temporalresolution suffers from limited spatial resolution - also known as thespatio-temporal trade-off of dynamic MRI. Several approaches, including deeplearning based super-resolution approaches, have been proposed to mitigate thistrade-off. Nevertheless, such an approach typically aims to super-resolve eachtime-point separately, treating them as individual volumes. This researchaddresses the problem by creating a deep learning model which attempts to learnboth spatial and temporal relationships. A modified 3D UNet model, DDoS-UNet,is proposed - which takes the low-resolution volume of the current time-pointalong with a prior image volume. Initially, the network is supplied with astatic high-resolution planning scan as the prior image along with thelow-resolution input to super-resolve the first time-point. Then it continuesstep-wise by using the super-resolved time-points as the prior image whilesuper-resolving the subsequent time-points. The model performance was testedwith 3D dynamic data that was undersampled to different in-plane levels. Theproposed network achieved an average SSIM value of 0.951$\pm$0.017 whilereconstructing the lowest resolution data (i.e. only 4\% of the k-spaceacquired) - which could result in a theoretical acceleration factor of 25. Theproposed approach can be used to reduce the required scan-time while achievinghigh spatial resolution.

DDoS-UNet: Incorporating temporal information using Dynamic Dual-channel UNet for enhancing super-resolution of dynamic MRI