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 cardiac magnetic resonance (CMR) imaging, a 3D high-resolutionsegmentation of the heart is essential for detailed description of itsanatomical structures. However, due to the limit of acquisition duration andrespiratory/cardiac motion, stacks of multi-slice 2D images are acquired inclinical routine. The segmentation of these images provides a low-resolutionrepresentation of cardiac anatomy, which may contain artefacts caused bymotion. Here we propose a novel latent optimisation framework that jointlyperforms motion correction and super resolution for cardiac imagesegmentations. Given a low-resolution segmentation as input, the frameworkaccounts for inter-slice motion in cardiac MR imaging and super-resolves theinput into a high-resolution segmentation consistent with input. A multi-viewloss is incorporated to leverage information from both short-axis view andlong-axis view of cardiac imaging. To solve the inverse problem, iterativeoptimisation is performed in a latent space, which ensures the anatomicalplausibility. This alleviates the need of paired low-resolution andhigh-resolution images for supervised learning. Experiments on two cardiac MRdatasets show that the proposed framework achieves high performance, comparableto state-of-the-art super-resolution approaches and with better cross-domaingeneralisability and anatomical plausibility.

Joint Motion Correction and Super Resolution for Cardiac Segmentation via Latent Optimisation