Sensitivity of hostile hemodynamics to aneurysm geometry via unsupervised shape interpolation

•A deep neural network can construct plausible cohorts of aneurysm geometries.•Sac-average wall shear stress may share too much mutual information with geometry.•Conversely, some metrics of complex flow may be too sensitive to geometry. Vessel geometry and hemodynamics are intrinsically linked, wher...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computer methods and programs in biomedicine 2023-11, Vol.241, p.107762-107762, Article 107762
Hauptverfasser:	MacDonald, Daniel E., Cancelliere, Nicole M., Pereira, Vitor M., Steinman, David A.
Format:	Artikel
Sprache:	eng
Schlagworte:	Computational fluid dynamics Geometry Intracranial aneurysm Machine learning Morphology Uncertainty quantification
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!