A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction
A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction
复制标题
DOI：
10.1109/tmi.2017.2760978
复制
发表时间：
2018-02-01
影响因子：
10.6
通讯作者：
Rueckert, Daniel
中科院分区：
文献类型：
--
作者：
Schlemper, Jo;Caballero, Jose;Rueckert, Daniel
受深度学习的最新进展的启发，我们提出了一个框架，用于重建来自卷积神经网络（CNN）的深度级联数据的2-D心脏磁共振（MR）图像的动态序列，以加速数据采集过程。特别是，我们解决了使用积极的笛卡尔底采样获取数据的情况。首先，我们表明，当每个2-D图像框架都独立重建时，就重建错误和重建错误和重建速度。其次，当共同重建序列的框架时，我们证明CNN可以通过结合卷积和数据共享方法来有效地学习时空相关性。我们表明，所提出的方法始终胜过最先进的方法，并且能够更忠实地保存解剖结构，直至11倍。此外，重建非常快：每个完整的动态序列都可以在少于10 s中重建，并且对于2-D情况，可以在23 ms中重建每个图像帧，从而实现实时应用程序。
Inspired by recent advances in deep learning, we propose a framework for reconstructing dynamic sequences of 2-D cardiac magnetic resonance (MR) images from undersampled data using a deep cascade of convolutional neural networks (CNNs) to accelerate the data acquisition process. In particular, we address the case where data are acquired using aggressive Cartesian undersampling. First, we show that when each 2-D image frame is reconstructed independently, the proposed method outperforms state-of-the-art 2-D compressed sensing approaches, such as dictionary learning-based MR image reconstruction, in terms of reconstruction error and reconstruction speed. Second, when reconstructing the frames of the sequences jointly, we demonstrate that CNNs can learn spatio-temporal correlations efficiently by combining convolution and data sharing approaches. We show that the proposed method consistently outperforms state-of-the-art methods and is capable of preserving anatomical structure more faithfully up to 11-fold undersampling. Moreover, reconstruction is very fast: each complete dynamic sequence can be reconstructed in less than 10 s and, for the 2-D case, each image frame can be reconstructed in 23 ms, enabling real-time applications.