Rapid identification of pathogens by using surface-enhanced Raman spectroscopy and multi-scale convolutional neural network

Ding, Jingyu; Lin, Qingqing; Zhang, Jiameng; Young, Glenn M.; Yao, Zhong; Zhang, Jianhua

doi:10.1007/s00216-021-03332-5

Cited by 33 publications

(22 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prepared gold nanoparticles and the developed CNN model showed detection accuracy higher than 97%. The given outcomes showed that the combination of SERS spectroscopy with multiscale CNN is feasible for Salmonella serotyping ( S. enteritidis , S. typhimurium , and S. Paratyphi) with bacterial concentration of 10 8 CFU/mL [ 36 ]. A stacked autoencoder-based deep neural networks algorithm was applied using SERS for the detection of methicillin-resistant Staphylococcus aureus and methicillin-sensitive S. aureus.…”

Section: Surface-enhanced Raman Spectroscopy (Sers)mentioning

confidence: 99%

Recent Progress in Spectroscopic Methods for the Detection of Foodborne Pathogenic Bacteria

et al. 2022

View full text Add to dashboard Cite

Detection of foodborne pathogens at an early stage is very important to control food quality and improve medical response. Rapid detection of foodborne pathogens with high sensitivity and specificity is becoming an urgent requirement in health safety, medical diagnostics, environmental safety, and controlling food quality. Despite the existing bacterial detection methods being reliable and widely used, these methods are time-consuming, expensive, and cumbersome. Therefore, researchers are trying to find new methods by integrating spectroscopy techniques with artificial intelligence and advanced materials. Within this progress report, advances in the detection of foodborne pathogens using spectroscopy techniques are discussed. This paper presents an overview of the progress and application of spectroscopy techniques for the detection of foodborne pathogens, particularly new trends in the past few years, including surface-enhanced Raman spectroscopy, surface plasmon resonance, fluorescence spectroscopy, multiangle laser light scattering, and imaging analysis. In addition, the applications of artificial intelligence, microfluidics, smartphone-based techniques, and advanced materials related to spectroscopy for the detection of bacterial pathogens are discussed. Finally, we conclude and discuss possible research prospects in aspects of spectroscopy techniques for the identification and classification of pathogens.

show abstract

Section: Surface-enhanced Raman Spectroscopy (Sers)mentioning

confidence: 99%

Recent Progress in Spectroscopic Methods for the Detection of Foodborne Pathogenic Bacteria

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For example, a convolutional neural network (CNN), which is one of the most popular deep learning architectures, has been widely used and has shown superior performance in analyzing spectroscopic signals including those from SERS spectroscopy of complex biological samples. [23][24][25] In this paper, the SERS spectra of eleven bacterial endotoxins have been measured based on silver nanorod array (AgNR) substrates. The characteristic SERS peaks from these endotoxins have been identified.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Differentiation and classification of bacterial endotoxins based on surface enhanced Raman scattering and advanced machine learning

Yang

Haverstick

et al. 2022

Nanoscale

View full text Add to dashboard Cite

show abstract

“…Raman spectroscopy is a label-free, rapid, and highly sensitive analytical technology [4][5][6][7], and in recent years, it has been used to identify bacteria [6,[8][9][10]. In various Raman technologies, surface-enhanced Raman spectroscopy (SERS) is a commonly used tool for bacterial analysis, which has been widely used in bacterial cell cycle monitoring [11], drug resistance [12], and identification [4,8,[13][14][15]. However, SERS requires complicated fabrication of the SERS substrate and is variable and difficult to reproduce, particularly in cell samples [6].…”

Section: Introductionmentioning

confidence: 99%

Rapid and accurate identification of pathogenic bacteria at the single‐cell level using laser tweezers Raman spectroscopy and deep learning

Sun

Fang

et al. 2022

Journal of Biophotonics

View full text Add to dashboard Cite

We report a new method for the rapid identification of pathogenic bacterial species at the single‐cell level that combines laser tweezers Raman spectroscopy (LTRS) with deep learning (DL). LTRS can accurately measure single‐cell Raman spectra (scRS) without destroying and labeling cells. Based on the scRS data, DL rapidly and accurately identifies pathogenic bacteria. We measured scRS of 15 species bacteria using homemade LTRS. For each species, approximately, 160 cells from three different patients were measured, one patient's data were used as test set, and the rest after being augmented was used as training set. A residual network (ResNet) model, trained on the augmented training set, achieved an accuracy of 94.53% on the test set. Moreover, we applied gradient‐weighted class activation mapping to visualize the proposed model. Finally, we demonstrated the advantages of ResNet over traditional machine‐learning algorithms.

show abstract

Rapid identification of pathogens by using surface-enhanced Raman spectroscopy and multi-scale convolutional neural network

Cited by 33 publications

References 53 publications

Recent Progress in Spectroscopic Methods for the Detection of Foodborne Pathogenic Bacteria

Recent Progress in Spectroscopic Methods for the Detection of Foodborne Pathogenic Bacteria

Differentiation and classification of bacterial endotoxins based on surface enhanced Raman scattering and advanced machine learning

Rapid and accurate identification of pathogenic bacteria at the single‐cell level using laser tweezers Raman spectroscopy and deep learning

Contact Info

Product

Resources

About