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

Generating virtual populations of anatomy that capture sufficient variabilitywhile remaining plausible is essential for conducting in-silico trials ofmedical devices. However, not all anatomical shapes of interest are alwaysavailable for each individual in a population. Hence,missing/partially-overlapping anatomical information is often available acrossindividuals in a population. We introduce a generative shape model for complexanatomical structures, learnable from datasets of unpaired datasets. Theproposed generative model can synthesise complete whole complex shapeassemblies coined virtual chimaeras, as opposed to natural human chimaeras. Weapplied this framework to build virtual chimaeras from databases of whole-heartshape assemblies that each contribute samples for heart substructures.Specifically, we propose a generative shape compositional framework whichcomprises two components - a part-aware generative shape model which capturesthe variability in shape observed for each structure of interest in thetraining population; and a spatial composition network which assembles/composesthe structures synthesised by the former into multi-part shape assemblies (viz.virtual chimaeras). We also propose a novel self supervised learning schemethat enables the spatial composition network to be trained with partiallyoverlapping data and weak labels. We trained and validated our approach usingshapes of cardiac structures derived from cardiac magnetic resonance imagesavailable in the UK Biobank. Our approach significantly outperforms a PCA-basedshape model (trained with complete data) in terms of generalisability andspecificity. This demonstrates the superiority of the proposed approach as thesynthesised cardiac virtual populations are more plausible and capture agreater degree of variability in shape than those generated by the PCA-basedshape model.

A Generative Shape Compositional Framework: Towards Representative Populations of Virtual Heart Chimaeras