TY - GEN
T1 - Advances in MRI based Electrical Properties Tomography
T2 - 21st Mediterranean Microwave Symposium, MMS 2021
AU - Zumbo, Sabrina
AU - Mandija, Stefano
AU - Meliado, Ettore Flavio
AU - Stijnman, Peter
AU - Meerbothe, Thierry
AU - Van Den Berg, Cornelis A.T.
AU - Isernia, Tommaso
AU - Bevacqua, Martina T.
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported by the European Commission, Fondo Sociale Europeo and Regione Calabria, POR-Calabria FSE 2014/2020. S.M. received funding from NWO, VENI grant n18078.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Magnetic resonance imaging (MRI) is widely used in several medical applications, which include the non-invasive and in-vivo investigation of the electrical properties of biological tissues. Such kind of inverse problem can be addressed by means of iterative methods, which are time and memory consuming and solution may converge to local minima. To accelerate the reconstructions and bypass the problem of local minima, we propose and compare two different learning methods to face the inverse problem underlying the MRI based electrical properties tomography, one based on supervised descent method and the other one on a cascade of multi-layers convolutional neural networks. Both methods are trained and tested using 2D simulated data of a human head model and show a good reconstruction capability. Better generalization ability can be achieved by using the CNN-based iterative approach.
AB - Magnetic resonance imaging (MRI) is widely used in several medical applications, which include the non-invasive and in-vivo investigation of the electrical properties of biological tissues. Such kind of inverse problem can be addressed by means of iterative methods, which are time and memory consuming and solution may converge to local minima. To accelerate the reconstructions and bypass the problem of local minima, we propose and compare two different learning methods to face the inverse problem underlying the MRI based electrical properties tomography, one based on supervised descent method and the other one on a cascade of multi-layers convolutional neural networks. Both methods are trained and tested using 2D simulated data of a human head model and show a good reconstruction capability. Better generalization ability can be achieved by using the CNN-based iterative approach.
KW - convolutional neural networks
KW - electrical properties
KW - electromagnetic inverse scattering
KW - image reconstruction
KW - learning methods
KW - magnetic resonance imaging
KW - supervised descent method
UR - http://www.scopus.com/inward/record.url?scp=85135181241&partnerID=8YFLogxK
U2 - 10.1109/MMS55062.2022.9825562
DO - 10.1109/MMS55062.2022.9825562
M3 - Conference contribution
AN - SCOPUS:85135181241
T3 - Mediterranean Microwave Symposium
BT - 2022 Microwave Mediterranean Symposium (MMS)
A2 - Boccia, Luigi
A2 - Catarinucci, Luca
A2 - Arnieri, Emilio
A2 - Colella, Riccardo
PB - IEEE Computer Society Press
Y2 - 9 May 2022 through 13 May 2022
ER -