Offset Sampling Improves Deep Learning based Accelerated MRI Reconstructions by Exploiting Symmetry
This work addresses image quality issues in accelerated MRI for medical imaging applications, presenting an incremental improvement over existing sampling methods.
The paper tackled the problem of improving deep learning-based accelerated MRI reconstructions by optimizing the sampling offset to better exploit k-space symmetries, resulting in higher quality reconstructions compared to standard equally-spaced or randomized compressed sensing samples.
Deep learning approaches to accelerated MRI take a matrix of sampled Fourier-space lines as input and produce a spatial image as output. In this work we show that by careful choice of the offset used in the sampling procedure, the symmetries in k-space can be better exploited, producing higher quality reconstructions than given by standard equally-spaced samples or randomized samples motivated by compressed sensing.