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

Abstract

RoAR is trained to recognize the macroscopic magnetic field inhomogeneities directly from the input magnitude-only mGRE data and eliminate their effect on <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msubsup><mml:mi>R</mml:mi><mml:mn>2</mml:mn><mml:mo>∗</mml:mo></mml:msubsup></mml:math> measurements. RoAR training is based on the biophysical model and does not require ground-truth <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msubsup><mml:mi>R</mml:mi><mml:mn>2</mml:mn><mml:mo>*</mml:mo></mml:msubsup></mml:math> 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 <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msubsup><mml:mi>R</mml:mi><mml:mn>2</mml:mn><mml:mo>*</mml:mo></mml:msubsup></mml:math> 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.