Dual Objective Approach Using A Convolutional Neural Network for Magnetic Resonance Elastography
This work addresses computational inefficiencies in medical imaging for MRE, offering a faster alternative to traditional methods, though it appears incremental as it builds on existing CNN approaches with a secondary loss.
The authors tackled the problem of reconstructing images from Magnetic Resonance Elastography (MRE) displacement data by proposing a convolutional neural network (CNN) that maps data directly into elastograms, avoiding costly classical methods, and demonstrated its effectiveness in generating images comparable to those from nonlinear inversion.
Traditionally, nonlinear inversion, direct inversion, or wave estimation methods have been used for reconstructing images from MRE displacement data. In this work, we propose a convolutional neural network architecture that can map MRE displacement data directly into elastograms, circumventing the costly and computationally intensive classical approaches. In addition to the mean squared error reconstruction objective, we also introduce a secondary loss inspired by the MRE mechanical models for training the neural network. Our network is demonstrated to be effective for generating MRE images that compare well with equivalents from the nonlinear inversion method.