Deep learning using a biophysical model for robust and accelerated reconstruction of quantitative, artifact-free and denoisedR2*images

Purpose To introduce a novel deep learning method for Robust and Accelerated Reconstruction (RoAR) of quantitative andB0-inhomogeneity-correctedR2*maps from multi-gradient recalled echo (mGRE) MRI data. Methods RoARtrainsa convolutional neural network (CNN) to generate quantitativeR2*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 macroscopicB0 field inhomogeneities. Importantly, no ground-truthR2*images are required and F-function is only needed during RoAR training but not application. Results We show that RoAR preserves all features ofR2*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 producedR2*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 onR2*measurements. RoAR training is based on the biophysical model and does not require ground-truthR2*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 ofR2*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.