Skip to main content
SLU publication database (SLUpub)

Research article2023Peer reviewedOpen access

A Sparse Model-Inspired Deep Thresholding Network for Exponential Signal Reconstruction--Application in Fast Biological Spectroscopy

Wang, Zi; Guo, Di; Tu, Zhangren; Huang, Yihui; Zhou, Yirong; Wang, Jian; Feng, Liubin; Lin, Donghai; You, Yongfu; Agback, Tatiana; Orekhov, Vladislav; Qu, Xiaobo


The nonuniform sampling (NUS) is a powerful approach to enable fast acquisition but requires sophisticated reconstruction algorithms. Faithful reconstruction from partially sampled exponentials is highly expected in general signal processing and many applications. Deep learning (DL) has shown astonishing potential in this field, but many existing problems, such as lack of robustness and explainability, greatly limit its applications. In this work, by combining the merits of the sparse model-based optimization method and data-driven DL, we propose a DL architecture for spectra reconstruction from undersampled data, called MoDern. It follows the iterative reconstruction in solving a sparse model to build the neural network, and we elaborately design a learnable soft-thresholding to adaptively eliminate the spectrum artifacts introduced by undersampling. Extensive results on both synthetic and biological data show that MoDern enables more robust, high-fidelity, and ultrafast reconstruction than the state-of-the-art methods. Remarkably, MoDern has a small number of network parameters and is trained on solely synthetic data while generalizing well to biological data in various scenarios. Furthermore, we extend it to an open-access and easy-to-use cloud computing platform (XCloud-MoDern), contributing a promising strategy for further development of biological applications.


Nuclear magnetic resonance; Spectroscopy; Image reconstruction; Biological system modeling; Time-domain analysis; Computer architecture; Data models; Cloud computing; deep learning (DL); exponential signal; fast sampling; optimization

Published in

IEEE transactions on neural networks and learning systems
2023, Volume: 34, number: 10, pages: 7578-7592

    UKÄ Subject classification

    Bioinformatics (Computational Biology)

    Publication identifier


    Permanent link to this page (URI)