Evaluating the Robustness of the Recurrent Inference Machine Based on MRI Lesion Data from Multiple Sclerosis Patients

Master thesis (2021)

Authors

K. Pancras Mechanical Engineering

Contributors

F.M. Vos ImPhys/Computational Imaging - AS (supervisor 2)
Q. Tao ImPhys/Medical Imaging - AS (supervisor 2)
MWA Caan Amsterdam UMC (supervisor 1)
D. Karkalousos Amsterdam UMC (supervisor 1)
Faculty
Mechanical Engineering
Copyright: © 2021 Kevin Pancras
Deep learning MRI Compressed sensing MS patient RIM Multiple sclerosis FLAIR
More Info
expand_more

Published Date

05-07-2021

Language

English

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.

Faculty

Mechanical Engineering

Abstract

The Recurrent Inference Machine (RIM) has been developed as an alternative to the clinically used Compressed Sensing (CS) algorithm, using Deep Learning (DL). A common issue with DL networks is the generalization of the network to features that have not been trained for. In this study we evaluate the robustness of the RIM to white matter lesions in FLuid Attenuated Inversion Recovery (FLAIR) brain MRI data. We are evaluating two pre-trained RIM networks, one trained on T1 brain data and another trained on T2 knee data. This evaluation was done by comparing the two networks to CS in terms of the average relative Signal-to-Noise Ratio (SNR) and Contrast Resolution (CR) that is achieved on 15 datasets acquired from Multiple Sclerosis patients. From these comparisons it shows that the network trained on T2 knee data performs similar to CS in terms of the relative SNR, while having a higher CR. The network trained on T1 brain data has both a lower relative SNR and CR, compared to CS. The data suggest that the RIM trained on T2 knee data is robust to the inclusion of lesions in an area that the network was not trained on.