KIKI-net: cross-domain convolutional neural networks for reconstructing undersampled magnetic resonance images
KIKI-net: cross-domain convolutional neural networks for reconstructing undersampled magnetic resonance images
复制标题
DOI：
10.1002/mrm.27201
复制
发表时间：
2018-11-01
影响因子：
3.3
通讯作者：
Hwang, Dosik
中科院分区：
文献类型：
--
作者：
Eo, Taejoon;Jun, Yohan;Hwang, Dosik
目的：证明利用跨域卷积神经网络(CNN)从欠采样k空间数据中准确地重建MR图像。方法：跨域CNN由3部分组成：(1)k空间上的深层CNN(KCNN)；(2)图像域上的深层CNN(ICNN)；(3)交织数据一致性操作。这些分量被交替应用，并且每个CNN被训练以最小化重建的k空间和相应的完全采样的k空间之间的损失。结果：测试了K-Net(带反傅立叶变换的KCNN)、I-Net(带交织数据一致性的ICNN)以及两种不同网络的不同组合的性能。测试结果表明，K-Net和I-Net在组织结构修复方面各有优劣。因此，K-Net和I-Net的结合优于单域CNN。使用阿尔茨海默病神经成像计划的T-2液体衰减反转恢复(T-2 FLAIR)数据集和我所获得的2个数据集(T-2 FLAIR和T-1加权)来评估7种传统重建算法和所提出的跨域CNN(以下简称Kiki-Net)的性能。KIKI-Net在峰值信噪比和结构相似度上的平均改善分别为2.29dB和0.031。结论：KIKI-Net在恢复组织结构和去除混叠伪影方面表现出优于传统算法的性能。结果表明，基于变密度笛卡尔欠抽样，Kiki-Net的适用范围可达3~4的缩减因子。
Purpose: To demonstrate accurate MR image reconstruction from undersampled k-space data using cross-domain convolutional neural networks (CNNs)Methods: Cross-domain CNNs consist of 3 components: (1) a deep CNN operating on the k-space (KCNN), (2) a deep CNN operating on an image domain (ICNN), and (3) an interleaved data consistency operations. These components are alternately applied, and each CNN is trained to minimize the loss between the reconstructed and corresponding fully sampled k-spaces. The final reconstructed image is obtained by forward-propagating the undersampled k-space data through the entire network.Results: Performances of K-net (KCNN with inverse Fourier transform), I-net (ICNN with interleaved data consistency), and various combinations of the 2 different networks were tested. The test results indicated that K-net and I-net have different advantages/disadvantages in terms of tissue-structure restoration. Consequently, the combination of K-net and I-net is superior to single-domain CNNs. Three MR data sets, the T-2 fluid-attenuated inversion recovery (T-2 FLAIR) set from the Alzheimer's Disease Neuroimaging Initiative and 2 data sets acquired at our local institute (T-2 FLAIR and T-1 weighted), were used to evaluate the performance of 7 conventional reconstruction algorithms and the proposed cross-domain CNNs, which hereafter is referred to as KIKI-net. KIKI-net outperforms conventional algorithms with mean improvements of 2.29 dB in peak SNR and 0.031 in structure similarity.Conclusion: KIKI-net exhibits superior performance over state-of-the-art conventional algorithms in terms of restoring tissue structures and removing aliasing artifacts. The results demonstrate that KIKI-net is applicable up to a reduction factor of 3 to 4 based on variable-density Cartesian undersampling.