Meeting Banner
Abstract #0663

Accelerated MRI Using Residual RAKI: Scan-specific Learning of Reconstruction Artifacts

Chi Zhang1,2, Steen Moeller2, Sebastian Weingärtner1,2,3, Kâmil Uǧurbil2, and Mehmet Akçakaya1,2

1Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, United States, 2Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, United States, 3Computer Assisted Clinical Medicine, University Medical Center Mannheim, Heidelberg University, Mannheim, Germany

Recently, there has been an interest in machine learning reconstruction techniques for accelerated MRI, where the focus has been on training regularizers on large databases. Another line of work, called Robust Artificial-neural-networks for k-space Interpolation (RAKI) explored the use of CNNs, trained on subject-specific ACS data for improving parallel imaging. In this work, we propose a ResNet architecture, called Residual RAKI (rRAKI) for training a subject-specific CNN that simultaneously approximates a linear convolutional operator and a nonlinear component that compensates for noise amplification artifacts that arise from coil geometry. Brain data shows improved noise resilience at high acceleration rates.

This abstract and the presentation materials are available to members only; a login is required.

Join Here