Unrolled Optimization via Physics-assisted Convolutional Neural Network for MR-based Electrical Properties Tomography: a Numerical Investigation

Unrolled Optimization via Physics-assisted Convolutional Neural Network for MR-based Electrical Properties Tomography: a Numerical Investigation 150 150 IEEE Open Journal of Engineering in Medicine and Biology (OJEMB)

Abstract:

Magnetic Resonance imaging based Electrical Properties Tomography (MR-EPT) is a non-invasive technique that measures the electrical properties (EPs) of biological tissues. In this work, we present and numerically investigate the performance of an unrolled, physics-assisted method for 2D MR-EPT reconstructions, where a cascade of Convolutional Neural Networks is used to …

View on IEEE Xplore