Andres Felipe Medina Ospina
Cycle-GAN-Based Calibration for a Microwave Brain Stroke Imaging System.
Rel. Francesca Vipiana, David Orlando Rodriguez Duarte, Matteo Luciano Maria Savazzi. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Biomedica, 2026
|
|
PDF (Tesi_di_laurea)
- Tesi
Accesso limitato a: Solo utenti staff fino al 28 Settembre 2029 (data di embargo). Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (45MB) |
Abstract
Stroke is one of the leading causes of death and disability worldwide. Early diagnosis relies on computed tomography (CT) and magnetic resonance imaging (MRI), which, although effective, have significant limitations in cost, portability, and accessibility in emergency settings. Microwave imaging (MWI) emerges as a promising alternative, offering a safe, low-cost, portable technology for stroke detection. MWI reconstructs a map of dielectric permittivity from measured scattered-field data (S-parameters). Its accuracy depends strongly on how closely the input data matches the simplified computational models used for reconstruction, which do not fully capture real experimental conditions, producing errors and artifacts in the reconstructed images.
Proper calibration is therefore essential, since experimental S-parameters exist on a different scale and units than the simulated fields used by the reconstruction algorithm
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
URI
![]() |
Modifica (riservato agli operatori) |
