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

Abstract

Purpose To introduce a combined machine learning (ML)‐ and physics‐based image reconstruction framework that enables navigator‐free, highly accelerated multishot echo planar imaging (msEPI) and demonstrate its application in high‐resolution structural and diffusion imaging. Methods Single‐shot EPI is an efficient encoding technique, but does not lend itself well to high‐resolution imaging because of severe distortion artifacts and blurring. Although msEPI can mitigate these artifacts, high‐quality msEPI has been elusive because of phase mismatch arising from shot‐to‐shot variations which preclude the combination of the multiple‐shot data into a single image. We utilize deep learning to obtain an interim image with minimal artifacts, which permits estimation of image phase variations attributed to shot‐to‐shot changes. These variations are then included in a joint virtual coil sensitivity encoding (JVC‐SENSE) reconstruction to utilize data from all shots and improve upon the ML solution. Results Our combined ML + physics approach enabled Rinplane × multiband (MB) = 8‐ × 2‐fold acceleration using 2 EPI shots for multiecho imaging, so that whole‐brain T2 and T2* parameter maps could be derived from an 8.3‐second acquisition at 1 × 1 × 3‐mm3 resolution. This has also allowed high‐resolution diffusion imaging with high geometrical fidelity using 5 shots at Rinplane × MB = 9‐ × 2‐fold acceleration. To make these possible, we extended the state‐of‐the‐art MUSSELS reconstruction technique to simultaneous multislice encoding and used it as an input to our ML network. Conclusion Combination of ML and JVC‐SENSE enabled navigator‐free msEPI at higher accelerations than previously possible while using fewer shots, with reduced vulnerability to poor generalizability and poor acceptance of end‐to‐end ML approaches.

SMS MUSSELS: A navigator‐free reconstruction for simultaneous multi‐slice‐accelerated multi‐shot diffusion weighted imaging

“…Nevertheless, with the utilization of additional constraints, it might be possible to devise new reconstruction scheme that can exploit the better phase estimates for specific applications. A similar idea is pursed in Ref . where the phase estimate from a SMS MUSSELS reconstruction was used in a second step of reconstruction using JVC‐SENSE to further improve the under‐sampled reconstruction by imposing additional constraints.…”

“…The smoothness regularization incorporated in the SR SMS MUSSELS helps the recovery of the partial Fourier data by providing an additional constraint. Several studies have also showed the utility of a conjugate symmetry‐based regularization which can be extended to the SMS MUSSELS framework . Implementations similar to Ref .…”

Improved MUSSELS reconstruction for high‐resolution multi‐shot diffusion weighted imaging

“…Using piecewise smooth signal model, we have shown the recovery of 8‐shot data using SR‐MUSSELS in from a 32‐channel acquisition, which is also partial Fourier accelerated. The recovery of 9‐shot data from a 32‐channel acquisition using MUSSELS was recently shown in …”

“…In Figure of Supporting Information, we show the results of a shot‐accelerated reconstruction using IRLS MUSSELS with CS using three out of the four shots. The capability of MUSSELS to reconstruct highly (shot‐) accelerated msEPI was reported in also. Further, the extension of MUSSELS to incorporate slice acceleration was also demonstrated using real SMS‐accelerated scans in and simulations in .…”

“…The capability of MUSSELS to reconstruct highly (shot‐) accelerated msEPI was reported in also. Further, the extension of MUSSELS to incorporate slice acceleration was also demonstrated using real SMS‐accelerated scans in and simulations in . These reconstructions can also benefit from the IRLS formulation to reduce the computation time.…”