Deep learning using a biophysical model for robust and accelerated reconstruction of quantitative, artifact-free and denoised R2* images

Abstract

Purpose: To introduce a novel deep learning method for Robust and Accelerated Reconstruction (RoAR) of quantitative and B0-inhomogeneity-corrected $R_2^{*}$ maps from multi-gradient recalled echo (mGRE) MRI data.

Methods: RoAR trains a convolutional neural network (CNN) to generate quantitative $R_2^{\ast }$ maps free from field inhomogeneity artifacts by adopting a self-supervised learning strategy given (a) mGRE magnitude images, (b) the biophysical model describing mGRE signal decay, and (c) preliminary-evaluated F-function accounting for contribution of macroscopic B0 field inhomogeneities. Importantly, no ground-truth $R_2^{*}$ images are required and F-function is only needed during RoAR training but not application.

Results: We show that RoAR preserves all features of $R_2^{*}$ maps while offering significant improvements over existing methods in computation speed (seconds vs. hours) and reduced sensitivity to noise. Even for data with SNR = 5 RoAR produced $R_2^{*}$ maps with accuracy of 22% while voxel-wise analysis accuracy was 47%. For SNR = 10 the RoAR accuracy increased to 17% vs. 24% for direct voxel-wise analysis.

Conclusions: RoAR is trained to recognize the macroscopic magnetic field inhomogeneities directly from the input magnitude-only mGRE data and eliminate their effect on $R_2^{\ast }$ measurements. RoAR training is based on the biophysical model and does not require ground-truth $R_2^{*}$ maps. Since RoAR utilizes signal information not just from individual voxels but also accounts for spatial patterns of the signals in the images, it reduces the sensitivity of $R_2^{*}$ maps to the noise in the data. These features plus high computational speed provide significant benefits for the potential usage of RoAR in clinical settings.

Keywords: $R_2^{*}$ mapping; MRI; gradient recalled echo; self-supervised deep learning.