ACE-Net: AutofoCus-Enhanced Convolutional Network for Field Imperfection Estimation with application to high b-value spiral Diffusion MRI
This work addresses image quality issues in diffusion MRI for medical imaging applications, but it is incremental as it combines existing autofocus metrics with deep learning.
The paper tackled the problem of spatiotemporal magnetic field variations causing artifacts in rapid MRI sequences by developing a data-driven method for automatic field imperfection estimation. The result was accurate estimation of B0 and eddy currents in high b-value spiral diffusion MRI, enabling high-quality image reconstruction without external calibrations.
Spatiotemporal magnetic field variations from B0-inhomogeneity and diffusion-encoding-induced eddy-currents can be detrimental to rapid image-encoding schemes such as spiral, EPI and 3D-cones, resulting in undesirable image artifacts. In this work, a data driven approach for automatic estimation of these field imperfections is developed by combining autofocus metrics with deep learning, and by leveraging a compact basis representation of the expected field imperfections. The method was applied to single-shot spiral diffusion MRI at high b-values where accurate estimation of B0 and eddy were obtained, resulting in high quality image reconstruction without need for additional external calibrations.