qModeL: A plug-and-play model-based reconstruction for highly accelerated multi-shot diffusion MRI using learned priors.
qModeL: A plug-and-play model-based reconstruction for highly accelerated multi-shot diffusion MRI using learned priors.
复制标题
DOI：
10.1002/mrm.28756
复制
发表时间：
2021-08
影响因子：
3.3
通讯作者：
Jacob M
中科院分区：
文献类型：
--
作者：
Mani M;Magnotta VA;Jacob M
介绍一种用于高度欠采样多激发扩散加权（msDW）扫描的联合重建方法。多激发EPI方法使扩散MRI具有更高的空间分辨率，但以长扫描时间为代价。需要高度加速的msDW扫描，以使其在先进的微观结构研究中的利用，这需要高Q空间覆盖。以前，联合k-q欠采样方法与压缩感知相结合，显示出能够实现非常高的加速因子。然而，使用稀疏先验的数据的重建是具有挑战性的，并且不适合于多壳数据。我们提出了一种新的重建，恢复图像的组合k-q数据联合。所提出的qModeL重建结合了基于模型的迭代重建和机器学习的优点，扩展了即插即用算法的思想。具体而言，qModeL通过使用深度学习预先学习与扩散测量空间对应的信号流形来工作。预先学习的流形先验被合并到基于模型的重建中，以在联合恢复期间沿着沿着q维度提供逐体素正则化。值得注意的是，学习不需要体内训练数据，并且完全来自生物物理建模。此外，即插即用的总变差去噪提供了沿空间维度的正则化沿着。在不同的加速因子下，对所提出的框架进行了k-q欠采样单壳和多壳msDW采集测试。qModeL联合重建显示可从8倍加速msDW采集中恢复DWI，单壳和多壳数据的误差均小于5%。使用欠采样重建进行的高级微观结构分析也报告了合理的准确性。qModeL能够利用基于学习的先验知识联合恢复高度加速的多次激发dMRI。生物物理驱动的方法使得能够使用加速的多次拍摄成像进行多壳取样和先进的微观结构研究。
To introduce a joint reconstruction method for highly under-sampled multi-shot diffusion weighted (msDW) scans. Multi-shot EPI methods enable higher spatial resolution for diffusion MRI, but at the expense of long scan-time. Highly accelerated msDW scans are needed to enable their utilization in advanced microstructure studies, which require high q-space coverage. Previously, joint k-q under-sampling methods coupled with compressed sensing were shown to enable very high acceleration factors. However, the reconstruction of this data using sparsity priors is challenging and is not suited for multi-shell data. We propose a new reconstruction that recovers images from the combined k-q data jointly. The proposed qModeL reconstruction brings together the advantages of model-based iterative reconstruction and machine learning, extending the idea of plug-and-play algorithms. Specifically, qModeL works by pre-learning the signal manifold corresponding to the diffusion measurement space using deep learning. The pre-learned manifold prior is incorporated into a model-based reconstruction to provide a voxel-wise regularization along the q-dimension during the joint recovery. Notably, the learning does not require in-vivo training data and is derived exclusively from biophysical modeling. Additionally, a plug-and-play total variation denoising provides regularization along the spatial dimension. The proposed framework is tested on k-q under-sampled single-shell and multi-shell msDW acquisition at various acceleration factors. The qModeL joint reconstruction is shown to recover DWIs from 8-fold accelerated msDW acquisitions with error less than 5% for both single-shell and multi-shell data. Advanced microstructural analysis performed using the under-sampled reconstruction also report reasonable accuracy. qModeL enables the joint recovery of highly accelerated multi-shot dMRI utilizing learning-based priors. The bio-physically driven approach enables the use of accelerated multi-shot imaging for multi-shell sampling and advanced microstructure studies.
登录
查看更多内容
微观结构生物物理建模的挑战。
影响因子：
3
作者：
Jelescu, Ileana O.;Palombo, Marco;Bagnato, Francesca;Schilling, Kurt G.
通讯作者：
Schilling, Kurt G.
影响因子：
5.7
作者：
Daducci, Alessandro;Canales-Rodriguez, Erick J.;Thiran, Jean-Philippe
通讯作者：
Thiran, Jean-Philippe
影响因子：
5.7
作者：
Landman, Bennett A.;Bogovic, John A.;Wan, Hanlin;ElShahaby, Fatma El Zahraa;Bazin, Pierre-Louis;Prince, Jerry L.
通讯作者：
Prince, Jerry L.
影响因子：
14.9
作者：
Ahmad R;Bouman CA;Buzzard GT;Chan S;Liu S;Reehorst ET;Schniter P
通讯作者：
Schniter P
影响因子：
3.3
作者：
Barth M;Breuer F;Koopmans PJ;Norris DG;Poser BA
通讯作者：
Poser BA