Thesis etd-03302021-105400 |
Link copiato negli appunti
Thesis type
Tesi di laurea magistrale
URN
etd-03302021-105400
Thesis title
Graph Neural Networks as surrogate for thoracic aortic aneurysm wall shear stress estimation
Department
INGEGNERIA DELL'INFORMAZIONE
Course of study
INGEGNERIA BIOMEDICA
Supervisors
.
relatore Ing. Positano, Vincenzo
relatore Ing. Celi, Simona
relatore Dott. Scarpolini, Martino Andrea
relatore Ing. Celi, Simona
relatore Dott. Scarpolini, Martino Andrea
Keywords
- aorta
- artificial intelligence
- deep neural network
- graph neural network
- thoracic aortic aneurysm
- wall shear stress
Graduation session start date
23/04/2021
Availability
Full
Abstract (Inglese)
Abstract (Italiano)
By representing mesh as a graph, it is possible to apply graph convolution to extract features and preserving the spatial coherency. In our work, we focused in the prediction of wall shear stress distribution directly over 3D surfaces. Each surface represent a thoracic aorta affected by aneurysm. All the geometries used come from real segmentations.
File
| Nome file | Dimensione |
|---|---|
| Master_T...Longo.pdf | 10.02 Mb |
Contatta l’autore |
|