Library
local_library Home Repository

Recurrent inference machines as inverse problem solvers for MR relaxometry

Journal Article (2021)
Author(s)

E. R. Sabidussi (Erasmus MC)

S. Klein (Erasmus MC)

Matthan W.A. Caan (Amsterdam UMC)

S. Bazrafkan (Universiteit Antwerpen)

A. J. den Dekker (Universiteit Antwerpen)

J. Sijbers (Universiteit Antwerpen)

W.J. Niessen (Erasmus MC, TU Delft - ImPhys/Computational Imaging, TU Delft - ImPhys/Medical Imaging)

D. H J Poot (Erasmus MC, TU Delft - ImPhys/Computational Imaging)

Research Group
ImPhys/Computational Imaging
Copyright
© 2021 E. R. Sabidussi, S. Klein, M. W.A. Caan, S. Bazrafkan, A. J. den Dekker, J. Sijbers, W.J. Niessen, D.H.J. Poot
DOI related publication
https://doi.org/10.1016/j.media.2021.102220
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 E. R. Sabidussi, S. Klein, M. W.A. Caan, S. Bazrafkan, A. J. den Dekker, J. Sijbers, W.J. Niessen, D.H.J. Poot
Research Group
ImPhys/Computational Imaging
Volume number
74
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

In this paper, we propose the use of Recurrent Inference Machines (RIMs) to perform T1 and T2 mapping. The RIM is a neural network framework that learns an iterative inference process based on the signal model, similar to conventional statistical methods for quantitative MRI (QMRI), such as the Maximum Likelihood Estimator (MLE). This framework combines the advantages of both data-driven and model-based methods, and, we hypothesize, is a promising tool for QMRI. Previously, RIMs were used to solve linear inverse reconstruction problems. Here, we show that they can also be used to optimize non-linear problems and estimate relaxometry maps with high precision and accuracy. The developed RIM framework is evaluated in terms of accuracy and precision and compared to an MLE method and an implementation of the Residual Neural Network (ResNet). The results show that the RIM improves the quality of estimates compared to the other techniques in Monte Carlo experiments with simulated data, test-retest analysis of a system phantom, and in-vivo scans. Additionally, inference with the RIM is 150 times faster than the MLE, and robustness to (slight) variations of scanning parameters is demonstrated. Hence, the RIM is a promising and flexible method for QMRI. Coupled with an open-source training data generation tool, it presents a compelling alternative to previous methods.