Highly accelerated multishot echo planar imaging through synergistic machine learning and joint reconstruction
Highly accelerated multishot echo planar imaging through synergistic machine learning and joint reconstruction
复制标题
DOI：
10.1002/mrm.27813
复制
发表时间：
2019-10-01
影响因子：
3.3
通讯作者：
Setsompop, Kawin
中科院分区：
文献类型：
--
作者：
Bilgic, Berkin;Chatnuntawech, Itthi;Setsompop, Kawin
目的：介绍一种组合的机器学习（ML）和基于物理的图像重建框架，使导航器免费，高度加速的多激发回波平面成像（msEPI），并展示其在高分辨率结构和扩散imaging. Methods的应用：单激发EPI是一种有效的编码技术，但并不适合高分辨率成像，因为严重的失真伪影和模糊。虽然msEPI可以减轻这些伪影，但由于拍摄间变化引起的相位失配，高质量的msEPI一直难以实现，这妨碍了将多个拍摄数据组合成单个图像。我们利用深度学习来获得具有最小伪影的临时图像，这允许估计归因于镜头间变化的图像相位变化。这些变化然后被包括在联合虚拟线圈灵敏度编码中（JVC-SENSE）重建，以利用来自所有镜头的数据并改进ML解决方案。我们的ML+物理组合方法使R-平面内x多波段（MB）= 8-x 2倍加速，使用2次EPI激发进行多回波成像，因此，全脑T-2和T-2 * 参数图可以从8.3秒的采集中以1 × 1 × 3毫米（3）的分辨率得出。这也允许在Rinplane x MB = 9-x 2倍加速度下使用5次发射进行具有高几何保真度的高分辨率扩散成像。为了使这些成为可能，我们将最先进的MUSSELS重建技术扩展到同步多切片编码，并将其用作ML network.Conclusion的输入：ML和JVC-SENSE的组合使无导航器的msEPI能够以比以前更高的加速度使用更少的镜头，减少易受端到端ML方法的可推广性差和接受度差的影响。
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-vresolution 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 R-inplane x multiband (MB) = 8-x 2-fold acceleration using 2 EPI shots for multiecho imaging, so that whole-brain T-2 and T-2* parameter maps could be derived from an 8.3-second acquisition at 1 x 1 x 3-mm(3) resolution. This has also allowed high-resolution diffusion imaging with high geometrical fidelity using 5 shots at Rinplane x MB = 9- x 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.