Fast reconstruction of non-uniform sampling multidimensional NMR spectroscopy via a deep neural network
Fast reconstruction of non-uniform sampling multidimensional NMR spectroscopy via a deep neural network
复制标题
通过深度神经网络快速重建非均匀采样多维核磁共振波谱
DOI：
10.1016/j.jmr.2020.106772
复制
发表时间：
2020-08-01
影响因子：
2.2
通讯作者：
Lin, Yanqin
中科院分区：
文献类型：
--
作者：
Luo, Jie;Zeng, Qing;Lin, Yanqin
多维核磁共振（NMR）光谱用于检查所研究系统的化学结构。不幸的是，核磁共振谱的应用因其较长的采集时间而受到限制，特别是对于 3D、4D 和更高维谱。非均匀采样 (NUS) 已被广泛认为是减少 NMR 实验时间的有力工具。但新加坡国立大学光谱的质量取决于适当的重建算法。深度学习作为一种有效的数据处理方法，近年来在多个领域得到广泛应用。在这项工作中，提出了一种基于深度学习的非均匀采样核磁共振谱快速重建策略。在我们的实验中，所提出的深度神经网络在去除伪影和保留弱峰方面比典型的 U-Net 和 DenseNet 卷积神经网络具有更好的性能。此外，利用一种生成训练数据的新方法来减少神经网络的计算负担，因此训练我们的网络比以前的基于深度学习的工作更容易、更快。与当前可用的两种方法 SMILE 和 hmsIST 相比，我们的策略可以在峰强度和峰形状保真度方面提供可比的重建质量。我们的方法的重建时间也与这两种方法相当或更快，特别是对于 3D 光谱。 (C) 2020 Elsevier Inc. 保留所有权利。
Multidimensional nuclear magnetic resonance (NMR) spectroscopy is used to examine the chemical structures of the studied systems. Unfortunately, the application of NMR spectra is limited by their long acquisition time, especially for 3D, 4D, and higher dimensional spectra. Non-uniform sampling (NUS) has been widely recognized as a powerful tool to reduce the NMR experimental time. But the quality of NUS spectra depends on appropriate reconstruction algorithms. As an effective data processing method, deep learning has been widely used in many fields in recent years. In this work, a deep learning-based strategy for fast reconstruction of non-uniform sampling NMR spectra is proposed. In our experiments, the pro-posed deep neural network has better performance in removing artifacts and preserving weak peaks than typical convolutional neural networks of U-Net and DenseNet. Besides, a novel approach of generating training data is utilized to reduce the computational burden of neural networks, and thus training our network can be easier and faster than previous deep learning-based works. Compared with the two currently available methods, SMILE and hmsIST, our strategy can provide comparable reconstruction quality in terms of peak intensities and the fidelity of peak shape. The reconstruction time of our methods is also comparable to or faster than the two methods, especially for 3D spectra. (C) 2020 Elsevier Inc. All rights reserved.