On the predictability of B0 maps at ultra-high fields using deep learning

UHF-MRI offers increased scanning sensitivity, but suffers from pronounced B₀ inhomogeneities. B₀ maps are essential for shimming and reconstruction at UHFs, but suffer from scanning overhead and low measurement confidence. Predicting B₀ maps from survey scans can effectively address these issues. We assessed predictability of brain B₀ maps at 7T and 11.7T using deep learning on a large synthetic B₀ map dataset created from 540 CT images. We found that deep learning can predict 1) spherical harmonics for shimming and 2) the complete B₀ maps. Our results indicate that B₀ predictions work as effectively as acquiring B₀ maps for shimming.