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

<jats:sec><jats:title>Purpose</jats:title><jats:p>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.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>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.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>Our combined ML + physics approach enabled R<jats:sub>inplane</jats:sub> × multiband (MB) = 8‐ × 2‐fold acceleration using 2 EPI shots for multiecho imaging, so that whole‐brain T<jats:sub>2</jats:sub> and T<jats:sub>2</jats:sub>* parameter maps could be derived from an 8.3‐second acquisition at 1 × 1 × 3‐mm<jats:sup>3</jats:sup> resolution. This has also allowed high‐resolution diffusion imaging with high geometrical fidelity using 5 shots at R<jats:sub>inplane</jats:sub> × 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.</jats:p></jats:sec><jats:sec><jats:title>Conclusion</jats:title><jats:p>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.</jats:p></jats:sec>