Stefano Bergese
Estimating coronary endothelial shear stress with deep convolutional neural networks.
Rel. Maurizio Lodi Rizzini, Bianca Griffo. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Biomedica, 2026
Abstract
Coronary artery disease (CAD) represents the leading cause of global mortality, with acute myocardial infarction (MI) being the most severe clinical event. Atherosclerosis represents the main pathological process underlying CAD, and it is characterized by the development of atherosclerotic plaques that progressively reduce the lumen size. In clinical practice, lesion severity is typically assessed either on an anatomical level, with coronary angiography holding a central role, or on a functional level with pressure-based indices. However, in both cases the clinically adopted metrics have shown only a moderate predictive capacity for specific risks associated with non-obstructive lesions. In parallel, local hemodynamics, and in particular wall shear stress (WSS), is recognized as one of the key factors driving atherosclerosis, being associated with plaque progression, destabilization and ultimately MI.
Although computational fluid dynamics (CFD) enable the quantification of WSS in patient-specific models, its clinical translation is restricted mainly by the required high computational times
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Informazioni aggiuntive
Corso di laurea
Classe di laurea
Aziende collaboratrici
URI
![]() |
Modifica (riservato agli operatori) |
