Advances in MRI based Electrical Properties Tomography: a Comparison between Physics-supported Learning Approaches

Sabrina Zumbo, Stefano Mandija, Ettore Flavio Meliado, Peter Stijnman, Thierry Meerbothe, Cornelis A.T. Van Den Berg, Tommaso Isernia, Martina T. Bevacqua

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

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.

Original languageEnglish
Title of host publication2022 Microwave Mediterranean Symposium (MMS)
EditorsLuigi Boccia, Luca Catarinucci, Emilio Arnieri, Riccardo Colella
PublisherIEEE Computer Society Press
ISBN (Electronic)9781665471107
DOIs
Publication statusPublished - 2022
Event21st Mediterranean Microwave Symposium, MMS 2021 - Pizzo Calabro, Italy
Duration: 9 May 202213 May 2022

Publication series

NameMediterranean Microwave Symposium
Volume2022-May
ISSN (Print)2157-9822
ISSN (Electronic)2157-9830

Conference

Conference21st Mediterranean Microwave Symposium, MMS 2021
Country/TerritoryItaly
CityPizzo Calabro
Period9/05/2213/05/22

Keywords

  • convolutional neural networks
  • electrical properties
  • electromagnetic inverse scattering
  • image reconstruction
  • learning methods
  • magnetic resonance imaging
  • supervised descent method

Fingerprint

Dive into the research topics of 'Advances in MRI based Electrical Properties Tomography: a Comparison between Physics-supported Learning Approaches'. Together they form a unique fingerprint.

Cite this