Learning Bloch Simulations for MR Fingerprinting by Invertible Neural Networks

08/10/2020
by   Fabian Balsiger, et al.
0

Magnetic resonance fingerprinting (MRF) enables fast and multiparametric MR imaging. Despite fast acquisition, the state-of-the-art reconstruction of MRF based on dictionary matching is slow and lacks scalability. To overcome these limitations, neural network (NN) approaches estimating MR parameters from fingerprints have been proposed recently. Here, we revisit NN-based MRF reconstruction to jointly learn the forward process from MR parameters to fingerprints and the backward process from fingerprints to MR parameters by leveraging invertible neural networks (INNs). As a proof-of-concept, we perform various experiments showing the benefit of learning the forward process, i.e., the Bloch simulations, for improved MR parameter estimation. The benefit especially accentuates when MR parameter estimation is difficult due to MR physical restrictions. Therefore, INNs might be a feasible alternative to the current solely backward-based NNs for MRF reconstruction.

READ FULL TEXT

page 3

page 7

research
11/09/2019

Spatially Regularized Parametric Map Reconstruction for Fast Magnetic Resonance Fingerprinting

Magnetic resonance fingerprinting (MRF) provides a unique concept for si...
research
03/01/2017

A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction

The acquisition of Magnetic Resonance Imaging (MRI) is inherently slow. ...
research
12/07/2021

Accurate parameter estimation using scan-specific unsupervised deep learning for relaxometry and MR fingerprinting

We propose an unsupervised convolutional neural network (CNN) for relaxa...
research
02/26/2019

Deep MR Fingerprinting with total-variation and low-rank subspace priors

Deep learning (DL) has recently emerged to address the heavy storage and...
research
10/15/2017

Deep Learning for Rapid Sparse MR Fingerprinting Reconstruction

PURPOSE: Demonstrate a novel fast method for reconstruction of multi-dim...
research
09/19/2022

Magnetic Resonance Fingerprinting with compressed sensing and distance metric learning

Magnetic Resonance Fingerprinting (MRF) is a novel technique that simult...
research
11/30/2022

Generalized Deep Learning-based Proximal Gradient Descent for MR Reconstruction

The data consistency for the physical forward model is crucial in invers...

Please sign up or login with your details

Forgot password? Click here to reset