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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Determining brain hemodynamics plays a critical role in the diagnosis andtreatment of various cerebrovascular diseases. In this work, we put forth aphysics-informed deep learning framework that augments sparse clinicalmeasurements with fast computational fluid dynamics (CFD) simulations togenerate physically consistent and high spatiotemporal resolution of brainhemodynamic parameters. Transcranial Doppler (TCD) ultrasound is one of themost common techniques in the current clinical workflow that enablesnoninvasive and instantaneous evaluation of blood flow velocity within thecerebral arteries. However, it is spatially limited to only a handful oflocations across the cerebrovasculature due to the constrained accessibilitythrough the skull's acoustic windows. Our deep learning framework employsin-vivo real-time TCD velocity measurements at several locations in the brainand the baseline vessel cross-sectional areas acquired from 3D angiographyimages, and provides high-resolution maps of velocity, area, and pressure inthe entire vasculature. We validated the predictions of our model againstin-vivo velocity measurements obtained via 4D flow MRI scans. We then showcasedthe clinical significance of this technique in diagnosing the cerebralvasospasm (CVS) by successfully predicting the changes in vasospastic localvessel diameters based on corresponding sparse velocities measurements. The keyfinding here is that the combined effects of uncertainties in outlet boundarycondition subscription and modeling physics deficiencies render theconventional purely physics-based computational models unsuccessful inrecovering accurate brain hemodynamics. Nonetheless, fusing these models withclinical measurements through a data-driven approach ameliorates predictions ofbrain hemodynamic variables.

Physics-informed neural networks for improving cerebral hemodynamics predictions