Network Accelerated Motion Estimation and Reduction (NAMER): Convolutional neural network guided retrospective motion correction using a separable motion model
Network Accelerated Motion Estimation and Reduction (NAMER): Convolutional neural network guided retrospective motion correction using a separable motion model
复制标题
DOI：
10.1002/mrm.27771
复制
发表时间：
2019-10-01
影响因子：
3.3
通讯作者：
Wald, Lawrence L.
中科院分区：
文献类型：
--
作者：
Haskell, Melissa W.;Cauley, Stephen F.;Wald, Lawrence L.
目的：提出并验证了一种可扩展的脑成像回溯式运动校正技术，该技术在基于模型的运动最小化中加入了机器学习组件。方法：将卷积神经网络(CNN)引入基于模型的数据一致性优化中，以联合搜索2D运动参数和未被破坏的图像。我们的可分离运动模型允许对严重损坏的镜头进行有效的焦内(逐行)运动校正，而不是以前的方法，这些方法不能很好地扩展到这种运动模型的改进。最终图像生成将运动参数合并到基于模型的图像重建中。结果：虽然卷积神经网络单独提供了一定的运动抑制(以引入模糊为代价)，但它可以指导迭代联合优化，既提高了搜索的收敛速度，又使联合优化可分离。这使得除了在快照之间之外，还可以在快照内快速缓解。对于二维平面内运动校正实验，仿真结果显著降低了图像空间均方根误差，在活体运动测试中运动伪影也明显减少。结论：卷积神经网络+基于模型的组合方法在可分离性和收敛方面的改进显示了在临床MRI中有意义的采集后运动缓解的潜力。
Purpose: We introduce and validate a scalable retrospective motion correction technique for brain imaging that incorporates a machine learning component into a model-based motion minimization.Methods: A convolutional neural network (CNN) trained to remove motion artifacts from 2D T2-weighted rapid acquisition with refocused echoes (RARE) images is introduced into a model-based data-consistency optimization to jointly search for 2D motion parameters and the uncorrupted image. Our separable motion model allows for efficient intrashot (line-by-line) motion correction of highly corrupted shots, as opposed to previous methods which do not scale well with this refinement of the motion model. Final image generation incorporates the motion parameters within a model-based image reconstruction. The method is tested in simulations and in vivo motion experiments of in-plane motion corruption.Results: While the convolutional neural network alone provides some motion mitigation (at the expense of introduced blurring), allowing it to guide the iterative joint-optimization both improves the search convergence and renders the joint-optimization separable. This enables rapid mitigation within shots in addition to between shots. For 2D in-plane motion correction experiments, the result is a significant reduction of both image space root mean square error in simulations, and a reduction of motion artifacts in the in vivo motion tests.Conclusion: The separability and convergence improvements afforded by the combined convolutional neural network+model-based method shows the potential for meaningful postacquisition motion mitigation in clinical MRI.