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

Sökning: WFRF:(Tu Y) > A Sparse Model-Insp...

Wang, Z. (författare)

Guo, D. (författare)

Tu, Z. R. (författare)

Huang, Y. H. (författare)

Zhou, Y. R. (författare)

Wang, J. (författare)

Feng, L. B. (författare)

Lin, D. H. (författare)

You, Y. F. (författare)

Agback, T. (författare)

Orekhov, Vladislav, 1966 (författare): Gothenburg University,Göteborgs universitet,Institutionen för kemi och molekylärbiologi,Department of Chemistry and Molecular Biology

Qu, X. B. (författare)

(creator_code:org_t)

Institute of Electrical and Electronics Engineers (IEEE), 2022
2022
Engelska.
Ingår i: IEEE Transactions on Neural Networks and Learning Systems. - : Institute of Electrical and Electronics Engineers (IEEE). - 2162-237X .- 2162-2388. ; 34:10, s. 7578-92

Relaterad länk:: http://arxiv.org/pdf...; visa fler...; https://gup.ub.gu.se...; https://doi.org/10.1...; visa färre...

Abstract Ämnesord

Stäng

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.

TEKNIK OCH TEKNOLOGIER -- Medicinteknik -- Medicinsk bildbehandling (hsv//swe)
ENGINEERING AND TECHNOLOGY -- Medical Engineering -- Medical Image Processing (hsv//eng)
NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)

Av författaren/redakt...: Wang, Z.; Guo, D.; Tu, Z. R.; Huang, Y. H.; Zhou, Y. R.; Wang, J.; visa fler...; Feng, L. B.; Lin, D. H.; You, Y. F.; Agback, T.; Orekhov, Vladisl ...; Qu, X. B.; visa färre...

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Medicinteknik; och Medicinsk bildbe ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.