k‐Space deep learning for reference‐free EPI ghost correction

Abstract

Purpose Nyquist ghost artifacts in echo planar imaging (EPI) are originated from phase mismatch between the even and odd echoes. However, conventional correction methods using reference scans often produce erroneous results especially in high‐field MRI due to the nonlinear and time‐varying local magnetic field changes. Recently, it was shown that the problem of ghost correction can be reformulated as k‐space interpolation problem that can be solved using structured low‐rank Hankel matrix approaches. Another recent work showed that data driven Hankel matrix decomposition can be reformulated to exhibit similar structures as deep convolutional neural network. By synergistically combining these findings, we propose a k‐space deep learning approach that immediately corrects the phase mismatch without a reference scan in both accelerated and non‐accelerated EPI acquisitions. Theory and Methods To take advantage of the even and odd‐phase directional redundancy, the k‐space data are divided into 2 channels configured with even and odd phase encodings. The redundancies between coils are also exploited by stacking the multi‐coil k‐space data into additional input channels. Then, our k‐space ghost correction network is trained to learn the interpolation kernel to estimate the missing virtual k‐space data. For the accelerated EPI data, the same neural network is trained to directly estimate the interpolation kernels for missing k‐space data from both ghost and subsampling. Results Reconstruction results using 3T and 7T in vivo data showed that the proposed method outperformed the image quality compared to the existing methods, and the computing time is much faster. Conclusions The proposed k‐space deep learning for EPI ghost correction is highly robust and fast, and can be combined with acceleration, so that it can be used as a promising correction tool for high‐field MRI without changing the current acquisition protocol.

Highly accelerated multishot echo planar imaging through synergistic machine learning and joint reconstruction

“…A conventional BM3D denoiser also proved to be effective in jumpstarting SMS‐NEATR, but the performance was consistently better using a learned denoiser tailored for the specific application (Figure and Supporting Information Figures S3 and S4). We anticipate further gains from advanced models that could simultaneously enforce data consistency and perform learned filtering . This would also streamline the SMS‐NEATR pipeline and reduce the number of steps.…”

“…We anticipate further gains from advanced models that could simultaneously enforce data consistency and perform learned filtering. [54][55][56] This would also streamline the SMS-NEATR pipeline and reduce the number of steps.…”

Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction

“…Under these frame conditions, we showed in [26] that (17) satisfies the perfect reconstruction condition, i.e…”

“…This leads to the same expression in (17) except that b i and b i are the i-th column of the following augmented matrices B skp andB skp , respectively [26]:…”

“…In addition to the potential increase of the piecewise linear regions, the nonlinear combination model (44) increases the redundancy of the representations in each piecewise linear region. Specifically, using the representation in (17) for each neural network, we have…”