English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Subject movement during the magnetic resonance examination is inevitable andcauses not only image artefacts but also deteriorates the homogeneity of themain magnetic field (B0), which is a prerequisite for high quality data. Thus,characterization of changes to B0, e.g. induced by patient movement, isimportant for MR applications that are prone to B0 inhomogeneities. We proposea deep learning based method to predict such changes within the brain from thechange of the head position to facilitate retrospective or even real-timecorrection. A 3D U-net was trained on in vivo brain 7T MRI data. The inputconsisted of B0 maps and anatomical images at an initial position, andanatomical images at a different head position (obtained by applying arigid-body transformation on the initial anatomical image). The outputconsisted of B0 maps at the new head positions. We further fine-tuned thenetwork weights to each subject by measuring a limited number of head positionsof the given subject, and trained the U-net with these data. Our approach wascompared to established dynamic B0 field mapping via interleaved navigators,which suffer from limited spatial resolution and the need for undesirablesequence modifications. Qualitative and quantitative comparison showed similarperformance between an interleaved navigator-equivalent method and proposedmethod. We therefore conclude that it is feasible to predict B0 maps from rigidsubject movement and, when combined with external tracking hardware, thisinformation could be used to improve the quality of magnetic resonanceacquisitions without the use of navigators.

Predicting dynamic, motion-related changes in B0 field in the brain at a 7 T MRI using a subject-specific fine-tuned U-net