Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

VECTOR: Very deep convolutional autoencoders for non-resonant background removal in broadband coherent anti-Stokes Raman scattering

Wang, Zhengwei orcid logoORCID: 0000-0001-7706-553X, O'Dwyer, Kevin orcid logoORCID: 0000-0001-7405-9679, Muddiman, Ryan orcid logoORCID: 0000-0001-9369-749X, Ward, Tomás E. orcid logoORCID: 0000-0002-6173-6607, Camp Jr., Charles H. orcid logoORCID: 0000-0002-5805-1842 and Hennelly, Bryan orcid logoORCID: 0000-0003-1326-9642 (2022) VECTOR: Very deep convolutional autoencoders for non-resonant background removal in broadband coherent anti-Stokes Raman scattering. Journal of Raman Spectroscopy, 53 (6). pp. 1081-1093. ISSN 0377-0486

Abstract
Abstract Rapid label-free spectroscopy of biological and chemical specimen via molecular vibration through means of broadband coherent anti-Stokes Raman scattering (B-CARS) could serve as a basis for a robust diagnostic platform for a wide range of applications. A limiting factor of CARS is the presence of a non-resonant background (NRB) signal, endemic to the technique. This background is multiplicative with the chemically resonant signal, meaning the perturbation it generates cannot be accounted for simply. Although several numerical approaches exist to account for and remove the NRB, they generally require some estimate of the NRB in the form of a separate measurement. In this paper, we propose a deep neural network architecture called Very dEep Convolutional auTOencodeRs (VECTOR), which retrieves the analytical Raman-like spectrum from CARS spectra through training of simulated noisy CARS spectra, without the need for an NRB reference measurement. VECTOR is composed of an encoder and a decoder. The encoder aims to compress the input to a lower dimensional latent representation without losing critical information. The decoder learns to reconstruct the input from the compressed representation. We also introduce skip connection that bypass from the encoder to the decoder, which benefits the reconstruction performance for deeper networks. We conduct abundant experiments to compare our proposed VECTOR to previous approaches in the literature, including the widely applied Kramers-Kronig method, as well as two another recently proposed methods that also use neural networks.
Metadata
Item Type:Article (Published)
Refereed:Yes
Uncontrolled Keywords:coherent anti-Stokes Raman scattering (CARS); coherent Raman spectroscopy; convolutional autoencoders; deep neural networks
Subjects:Biological Sciences > Biochemistry
Computer Science > Algorithms
Computer Science > Machine learning
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Publisher:John Wiley & Sons Ltd.
Official URL:https://doi.org/10.1002/jrs.6335
Copyright Information:© 2022 The Authors.
Funders:Science Foundation Ireland under Grant Numbers 15/CDA/3667, 19/FFP/7025, and 16/RI/3399.
ID Code:26858
Deposited On:29 Mar 2022 12:24 by Tomas Ward . Last Modified 17 Aug 2023 15:01
Documents

Full text available as:

[thumbnail of J Raman Spectroscopy - 2022 - Wang - VECTOR  Very deep convolutional autoencoders for non‐resonant background removal in.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution-Noncommercial-No Derivative Works 4.0
2MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record