Deep learning for undersampled MRI reconstruction
Deep learning for undersampled MRI reconstruction
复制标题
DOI：
10.1088/1361-6560/aac71a
复制
发表时间：
2018-07-01
影响因子：
3.5
通讯作者：
Seo, Jin Keun
中科院分区：
文献类型：
--
作者：
Hyun, Chang Min;Kim, Hwa Pyung;Seo, Jin Keun
本文提出了一种深度学习方法，通过使用亚奈奎斯特采样策略减少k空间数据来实现更快的磁共振成像（MRI），并为所提出的方法的有效性提供了理论依据。在耗时的相位编码方向上使用均匀子采样来捕获高分辨率图像信息，同时允许由泊松求和公式决定的图像折叠问题。为了处理由于图像折叠而导致的定位不确定性，添加了少量的低频k空间数据。训练深度学习网络涉及输入和输出图像，这些图像是子采样和全采样k空间数据的傅立叶变换对。我们的实验表明，所提出的方法的显着性能，只有29%的k空间数据可以生成高质量的图像，有效地作为标准的MRI重建与完全采样的数据。
This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to capture high-resolution image information, while permitting the image-folding problem dictated by the Poisson summation formula. To deal with the localization uncertainty due to image folding, a small number of low-frequency k-space data are added. Training the deep learning net involves input and output images that are pairs of the Fourier transforms of the subsampled and fully sampled k-space data. Our experiments show the remarkable performance of the proposed method; only 29% of the k-space data can generate images of high quality as effectively as standard MRI reconstruction with the fully sampled data.