Predicting dynamic, motion-related changes in B 0 field in the brain at a 7T MRI using a subject-specific fine-trained U-net
Stanislav Motyka, Paul Weiser, Beata Bachrata, Lukas Hingerl, Bernhard Strasser, Gilbert Hangel, Eva Niess, Fabian Niess, Maxim Zaitsev, Simon Daniel Robinson, Georg Langs, Siegfried Trattnig, Wolfgang Bogner
Abstract
Purpose
Subject movement during the MR examination is inevitable and causes not only image artifacts but also deteriorates the homogeneity of the main magnetic field (B 0), which is a prerequisite for high quality data. Thus, characterization of changes to B 0, for example induced by patient movement, is important for MR applications that are prone to B 0 inhomogeneities.
Methods
We propose a deep learning based method to predict such changes within the brain from the change of the head position to facilitate retrospective or even real-time correction. A 3D U-net was trained on in vivo gradient-echo brain 7T MRI data. The input consisted of B 0 maps and anatomical images at an initial position, and anatomical images at a different head position (obtained by applying a rigid-body transformation on the initial anatomical image). The output consisted of B 0 maps at the new head positions. We further fine-trained the network weights to each subject by measuring a limited number of head positions of the given subject, and trained the U-net with these data.
Results
Our approach was compared to established dynamic B 0 field mapping via interleaved navigators, which suffer from limited spatial resolution and the need for undesirable sequence modifications. Qualitative and quantitative comparison showed similar performance between an interleaved navigator-equivalent method and proposed method.
Conclusion
It is feasible to predict B 0 maps from rigid subject movement and, when combined with external tracking hardware, this information could be used to improve the quality of MR acquisitions without the use of navigators.