Learning Bloch Simulations for MR Fingerprinting by Invertible Neural Networks

Balsiger, Fabian; Jungo, Alain; Scheidegger, Olivier; Marty, Benjamin; Reyes, Mauricio (2020). Learning Bloch Simulations for MR Fingerprinting by Invertible Neural Networks. In: Deeba, Farah; Johnson, Patricia; Würfl, Tobias; Ye, Jong Chul (eds.) Machine Learning for Medical Image Reconstruction. Lecture Notes in Computer Science: Vol. 12450 (pp. 60-69). Cham: Springer 10.1007/978-3-030-61598-7_6

Text 978-3-030-61598-7_6.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (734kB)

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.

Interest & Impact

Downloads

1 since deposited on 20 Nov 2020
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item