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

Thoracic aortic aneurysm (TAA) is a localized dilatation of the aortaresulting from compromised wall composition, structure, and function, which canlead to life-threatening dissection or rupture. Several genetic mutations andpredisposing factors that contribute to TAA have been studied in mouse modelsto characterize specific changes in aortic microstructure and materialproperties that result from a wide range of mechanobiological insults.Assessments of TAA progression in vivo is largely limited to measurements ofaneurysm size and growth rate. It has been shown that aortic geometry alone isnot sufficient to predict the patient-specific progression of TAA butcomputational modeling of the evolving biomechanics of the aorta could predictfuture geometry and properties from initiating insults. In this work, wepresent an integrated framework to train a deep operator network(DeepONet)-based surrogate model to identify contributing factors for TAA byusing FE-based datasets of aortic growth and remodeling resulting fromprescribed insults. For training data, we investigate multiple types of TAArisk factors and spatial distributions within a constrained mixture model togenerate axial--azimuthal maps of aortic dilatation and distensibility. Thetrained network is then capable of predicting the initial distribution andextent of the insult from a given set of dilatation and distensibilityinformation. Two DeepONet frameworks are proposed, one trained on sparseinformation and one on full-field grayscale images, to gain insight into apreferred neural operator-based approach. Performance of the surrogate modelsis evaluated through multiple simulations carried out on insult distributionsvarying from fusiform to complex. We show that the proposed approach canpredict patient-specific mechanobiological insult profile with a high accuracy,particularly when based on full-field images.

Neural operator learning of heterogeneous mechanobiological insults contributing to aortic aneurysms