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

Myocardial motion and deformation are rich descriptors that characterizecardiac function. Image registration, as the most commonly used technique formyocardial motion tracking, is an ill-posed inverse problem which oftenrequires prior assumptions on the solution space. In contrast to most existingapproaches which impose explicit generic regularization such as smoothness, inthis work we propose a novel method that can implicitly learn anapplication-specific biomechanics-informed prior and embed it into a neuralnetwork-parameterized transformation model. Particularly, the proposed methodleverages a variational autoencoder-based generative model to learn a manifoldfor biomechanically plausible deformations. The motion tracking then can beperformed via traversing the learnt manifold to search for the optimaltransformations while considering the sequence information. The proposed methodis validated on three public cardiac cine MRI datasets with comprehensiveevaluations. The results demonstrate that the proposed method can outperformother approaches, yielding higher motion tracking accuracy with reasonablevolume preservation and better generalizability to varying data distributions.It also enables better estimates of myocardial strains, which indicates thepotential of the method in characterizing spatiotemporal signatures forunderstanding cardiovascular diseases.

Generative Myocardial Motion Tracking via Latent Space Exploration with Biomechanics-informed Prior