A microwave imaging approach based on artificial neural networks (ANNs) for the reconstruction of the properties of a cross section of the neck is proposed in this paper. The aim of this work is to retrieve the distribution maps of the neck dielectric properties starting from electromagnetic scattered fields. Possible applications include the diagnosis of cervical diseases. To this end, simplified neck phantoms were developed to test the feasibility of the proposed method. The developed network presents four fullyconnected layers with a last regression layer. Several numerical tests were performed to evaluate the performance of the ANN. The preliminary findings indicate a quite good reconstruction of dielectric properties and the possibility to evaluate the spinal canal dimension.
Microwave tomography of the neck with ANNs: Preliminary results with simplified numerical phantoms
Dachena, Chiara;Fedeli, Alessandro;Pastorino, Matteo;Randazzo, Andrea;
2021-01-01
Abstract
A microwave imaging approach based on artificial neural networks (ANNs) for the reconstruction of the properties of a cross section of the neck is proposed in this paper. The aim of this work is to retrieve the distribution maps of the neck dielectric properties starting from electromagnetic scattered fields. Possible applications include the diagnosis of cervical diseases. To this end, simplified neck phantoms were developed to test the feasibility of the proposed method. The developed network presents four fullyconnected layers with a last regression layer. Several numerical tests were performed to evaluate the performance of the ANN. The preliminary findings indicate a quite good reconstruction of dielectric properties and the possibility to evaluate the spinal canal dimension.File | Dimensione | Formato | |
---|---|---|---|
IST2021_NeckANN.pdf
accesso chiuso
Descrizione: Contributo in atti di convegno
Tipologia:
Documento in versione editoriale
Dimensione
1.41 MB
Formato
Adobe PDF
|
1.41 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.