An end-to-end-trainable iterative network architecture for accelerated radial multi-coil 2D cine MR image reconstruction
An end-to-end-trainable iterative network architecture for accelerated radial multi-coil 2D cine MR image reconstruction
复制标题
DOI：
10.1002/mp.14809
复制
发表时间：
2021-04-01
期刊：
影响因子：
3.8
通讯作者：
Kolbitsch, Christoph
中科院分区：
文献类型：
--
作者：
Kofler, Andreas;Haltmeier, Markus;Kolbitsch, Christoph
迭代卷积神经网络（cnn）类似于展开学习迭代方案，已经证明可以在不同成像模式下始终如一地提供最先进的图像重建结果。然而，由于这些方法在体系结构中包含前向模型，它们的适用性通常局限于相对较小的重构问题或计算成本较低的算子问题。因此，到目前为止，它们还没有应用于动态非笛卡儿多线圈重建问题。方法在本研究中，我们提出了一种用于多接收线圈加速二维径向电影MRI图像重建的CNN架构。该网络基于计算轻的CNN分量和随后的共轭梯度（CG）方法，可以使用有效的训练策略进行端到端联合训练。我们研究了所提出的训练策略，并将我们的方法与其他已知的具有学习和非学习正则化方法的重构技术进行了比较。结果本文提出的方法优于其他基于非学习正则化的方法。此外，它的性能与使用3D U-Net的基于cnn的方法和使用自适应字典学习的方法相似或更好。此外，我们通过经验证明，即使仅通过迭代训练网络，也可以在测试时增加网络的长度并进一步改善结果。结论端到端训练可以大大减少重构网络可训练参数的数量，稳定重构网络。此外，由于可以在测试时改变网络的长度，因此在cnn块的复杂性和每个cg块的迭代次数之间找到折衷的需要变得无关紧要。
Purpose Iterative convolutional neural networks (CNNs) which resemble unrolled learned iterative schemes have shown to consistently deliver state-of-the-art results for image reconstruction problems across different imaging modalities. However, because these methods include the forward model in the architecture, their applicability is often restricted to either relatively small reconstruction problems or to problems with operators which are computationally cheap to compute. As a consequence, they have not been applied to dynamic non-Cartesian multi-coil reconstruction problems so far.Methods In this work, we propose a CNN architecture for image reconstruction of accelerated 2D radial cine MRI with multiple receiver coils. The network is based on a computationally light CNN component and a subsequent conjugate gradient (CG) method which can be jointly trained end-to-end using an efficient training strategy. We investigate the proposed training strategy and compare our method with other well-known reconstruction techniques with learned and non-learned regularization methods.Results Our proposed method outperforms all other methods based on non-learned regularization. Further, it performs similar or better than a CNN-based method employing a 3D U-Net and a method using adaptive dictionary learning. In addition, we empirically demonstrate that even by training the network with only iteration, it is possible to increase the length of the network at test time and further improve the results.Conclusions End-to-end training allows to highly reduce the number of trainable parameters of and stabilize the reconstruction network. Further, because it is possible to change the length of the network at the test time, the need to find a compromise between the complexity of the CNN-block and the number of iterations in each CG-block becomes irrelevant.