Deep Learning–Assisted Surface-Enhanced Raman Scattering for Rapid Bacterial Identification
ACS Applied Materials & Interfaces · 2023-06-07 · 15 (22) · 26398-26406
DOI: 10.1021/acsami.3c03212 ↗At a glance
Journal article in ACS Applied Materials & Interfaces, published online on 2023-05-22. Written by Yi-Ming Tseng and 4 co-authors. Institution: Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan, 106319. Major MEDLINE topics: Deep Learning, Methicillin-Resistant Staphylococcus aureus. Cited 97 times so far (Crossref); 45 references. Funded by: Ministry of Science and Technology, Taiwan.
Abstract (original language)
Bloodstream infection (BSI) is characterized by the presence of viable microorganisms in the bloodstream and may induce systemic immune responses. Early and appropriate antibiotic usage is crucial to effectively treating BSI. However, conventional culture-based microbiological diagnostics are time-consuming and cannot provide timely bacterial identification for subsequent antimicrobial susceptibility test (AST) and clinical decision-making. To address this issue, modern microbiological diagnostics have been developed, such as surface-enhanced Raman scattering (SERS), which is a sensitive, label-free, and quick bacterial detection method measuring specific bacterial metabolites. In this study, we aim to integrate a new deep learning (DL) method, Vision Transformer (ViT), with bacterial SERS spectral analysis to build the SERS-DL model for rapid identification of Gram type, species, and resistant strains. To demonstrate the feasibility of our approach, we used 11,774 SERS spectra obtained directly from eight common bacterial species in clinical blood samples without artificial introduction as the training dataset for the SERS-DL model. Our results showed that ViT achieved excellent identification accuracy of 99.30% for Gram type and 97.56% for species. Moreover, we employed transfer learning by using the Gram-positive species identifier as a pre-trained model to perform the antibiotic-resistant strain task. The identification accuracy of methicillin-resistant and -susceptible Staphylococcus aureus (MRSA and MSSA) can reach 98.5% with only 200-dataset requirement. In summary, our SERS-DL model has great potential to provide a quick clinical reference to determine the bacterial Gram type, species, and even resistant strains, which can guide early antibiotic usage in BSI.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan, 106319.
- Institute of Atomic and Molecular Sciences, Academia Sinica, Taipei, Taiwan, 106319.
- Department of Anesthesiology, National Taiwan University Hospital, Taipei, Taiwan, 100229.
- Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan, 106319.
ORCID profiles: Yi-Ming Tseng, Yin-Yi Han, Nien-Tsu Huang
Funding
- Ministry of Science and Technology, Taiwan
Cite
APA
Tseng, Y. M., Chen, K. L., Chao, P. H., Han, Y. Y., & Huang, N. T. (2023). Deep Learning–Assisted Surface-Enhanced Raman Scattering for Rapid Bacterial Identification. ACS Applied Materials & Interfaces, 15(22), 26398-26406. https://doi.org/10.1021/acsami.3c03212
Vancouver
Tseng YM, Chen KL, Chao PH, Han YY, Huang NT. Deep Learning–Assisted Surface-Enhanced Raman Scattering for Rapid Bacterial Identification. ACS Applied Materials & Interfaces. 2023;15(22):26398-26406. doi:10.1021/acsami.3c03212
BibTeX
@article{Tseng2023,
author = {Tseng, Yi-Ming and Chen, Ko-Lun and Chao, Po-Hsuan and Han, Yin-Yi and Huang, Nien-Tsu},
title = {Deep Learning–Assisted Surface-Enhanced Raman Scattering for Rapid Bacterial Identification},
journal = {ACS Applied Materials & Interfaces},
year = {2023},
volume = {15},
number = {22},
pages = {26398--26406},
doi = {10.1021/acsami.3c03212}
}
EUVIMED