journal article·2025-09Open access

RADAR: Raman Spectral Analysis Using Deep Learning for Artifact Removal

Joel Sjöberg, Nicoleta Siminea, Andrei Păun, Adrian Lita, Mioara Larion, Ion Petre

Advanced Optical Materials· Volume 13· Issue 25

Abstract

Abstract Raman spectroscopy is a non‐destructive analytical technique that reveals molecular vibrations, enabling precise identification of chemical compounds and material properties. Its spatial resolution and compatibility with microscopic imaging allow for high‐resolution chemical mapping of heterogeneous samples. However, spectral artifacts such as baseline drift, cosmic rays, and instrumental noise complicate data interpretation, necessitating correction. RADAR is introduced, two lightweight deep learning models for artifact removal, capable of simultaneous denoising and correction of Raman spectra, significantly accelerating high‐quality data acquisition. The models help reduce the data acquisition time by 90% while preserving signal integrity, as demonstrated on noisy spectra from a diversity of samples, biological and non‐biological. These models are versatile and can be readily applied to novel Raman datasets, offering an order‐of‐magnitude improvement in acquisition efficiency. This work advances Raman spectroscopy as a faster, more reliable tool for chemical analysis, with broad applications in materials science, biomedical research, and beyond.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Spectroscopy Techniques in Biomedical and Chemical Research · Spectroscopy and Chemometric Analyses · Fault Detection and Control Systems

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Mathematics and Statistics University Of Turku Turku 20014 Finland

Faculty of Mathematics and Computer Science University of Bucharest Bucharest 010014 Romania

Departament of Bioinformatics National Institute for Research and Development in Biological Sciences Bucharest 060031 Romania

Research Institute for Artificial Intelligence (ICIA) Romanian Academy Bucharest 060031 Romania

Neuro‐Oncology Branch, National Cancer Institute National Institutes of Health Bethesda 20892 USA

Funding

Turun Yliopistosäätiö · Svenska Kulturfonden · Ministerul Cercetării, Inovării şi Digitalizării

References (41)

Show source-provided references
1. P. R.Griffiths inHandbook of Vibrational Spectroscopy(Eds:P.Griffiths J. M.Chalmers) John Wiley & Sons Ltd New York2006 pp.1–50.
2. G.Keresztury inHandbook of Vibrational Spectroscopy(Eds:P.Griffiths J. M.Chalmers) John Wiley & Sons Ltd New York2006 pp.1–50.
3. Han X. X. · Nat. Rev. Methods Primers · 2021 · 1
4. 10.1007/s00340-007-2630-x10.1007/s00340-007-2630-x ↗
5. 10.1038/s41592-019-0538-010.1038/s41592-019-0538-0 ↗
6. 10.1016/j.trac.2024.11757810.1016/j.trac.2024.117578 ↗
7. 10.1002/978111944059810.1002/9781119440598 ↗
8. 10.1177/0003702822109407010.1177/00037028221094070 ↗
9. 10.1366/00037020332255451810.1366/000370203322554518 ↗
10. 10.1366/00037020778259700310.1366/000370207782597003 ↗
11. 10.1117/1.JBO.28.2.02500210.1117/1.JBO.28.2.025002 ↗
12. 10.1039/b922045c10.1039/b922045c ↗
13. 10.1016/j.chemolab.2018.06.00910.1016/j.chemolab.2018.06.009 ↗
14. 10.3390/s2114462310.3390/s21144623 ↗
15. 10.1021/ac60214a04710.1021/ac60214a047 ↗
16. 10.1021/acs.analchem.2c0308210.1021/acs.analchem.2c03082 ↗
17. J.Wahl Multimodal applications in medical technology that utilize Raman spectroscopy Ph.D. thesis Luleå University of Technology2022.
18. 10.1016/j.chemolab.2023.10477910.1016/j.chemolab.2023.104779 ↗
19. 10.3390/s2410316110.3390/s24103161 ↗
20. 10.1109/ICASSP.2019.868231110.1109/ICASSP.2019.8682311 ↗
21. 10.1177/000370281988894910.1177/0003702819888949 ↗
22. 10.1039/D2AN00868H10.1039/D2AN00868H ↗
23. 10.1016/j.chemolab.2021.10431710.1016/j.chemolab.2021.104317 ↗
24. 10.1038/s41467-024-44864-510.1038/s41467-024-44864-5 ↗
25. 10.1038/s41377-024-01394-510.1038/s41377-024-01394-5 ↗
26. 10.1364/BOE.10.00386010.1364/BOE.10.003860 ↗
27. 10.1364/BOE.47650710.1364/BOE.476507 ↗
28. 10.1039/b922045c10.1039/b922045c ↗
29. 10.3390/s2410316110.3390/s24103161 ↗
30. 10.1038/s41598-023-34457-510.1038/s41598-023-34457-5 ↗
31. G.Berlanga Q.Williams N.Temiquel Machine Learning Raman Open Dataset (MLROD) 2022.
32. 10.1029/2021EA00212510.1029/2021EA002125 ↗
33. 10.1016/j.trac.2024.11757810.1016/j.trac.2024.117578 ↗
34. 10.1117/1.JBO.25.5.05090110.1117/1.JBO.25.5.050901 ↗
35. 10.1093/neuonc/noae10110.1093/neuonc/noae101 ↗
36. 10.1038/s41598-023-42946-w10.1038/s41598-023-42946-w ↗
37. 10.1038/s41598-021-90157-y10.1038/s41598-021-90157-y ↗
38. K.Simonyan A.Vedaldi A.Zisserman Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps2014 arXiv:1312.6034 [cs].
39. 10.1007/978-3-319-10590-1_5310.1007/978-3-319-10590-1_53 ↗
40. 10.1021/acssensors.4c0326010.1021/acssensors.4c03260 ↗
41. Liu Y. · AIP Adv. · 2022 · 12