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/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Advances in computational science offer a principled pipeline for predictivemodeling of cardiovascular flows and aspire to provide a valuable tool formonitoring, diagnostics and surgical planning. Such models can be nowadaysdeployed on large patient-specific topologies of systemic arterial networks andreturn detailed predictions on flow patterns, wall shear stresses, and pulsewave propagation. However, their success heavily relies on tediouspre-processing and calibration procedures that typically induce a significantcomputational cost, thus hampering their clinical applicability. In this workwe put forth a machine learning framework that enables the seamless synthesisof non-invasive in-vivo measurement techniques and computational flow dynamicsmodels derived from first physical principles. We illustrate this new paradigmby showing how one-dimensional models of pulsatile flow can be used toconstrain the output of deep neural networks such that their predictionssatisfy the conservation of mass and momentum principles. Once trained on noisyand scattered clinical data of flow and wall displacement, these networks canreturn physically consistent predictions for velocity, pressure and walldisplacement pulse wave propagation, all without the need to employconventional simulators. A simple post-processing of these outputs can alsoprovide a cheap and effective way for estimating Windkessel model parametersthat are required for the calibration of traditional computational models. Theeffectiveness of the proposed techniques is demonstrated through a series ofprototype benchmarks, as well as a realistic clinical case involving in-vivomeasurements near the aorta/carotid bifurcation of a healthy human subject.

computer methods in applied mechanics and engineering

Machine learning in cardiovascular flows modeling: Predicting arterial  blood pressure from non-invasive 4D flow MRI data using physics-informed  neural networks