Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning

Abstract

Raman optical spectroscopy promises label-free bacterial detection, identification, and antibiotic susceptibility testing in a single step. However, achieving clinically relevant speeds and accuracies remains challenging due to weak Raman signal from bacterial cells and numerous bacterial species and phenotypes. Here we generate an extensive dataset of bacterial Raman spectra and apply deep learning approaches to accurately identify 30 common bacterial pathogens. Even on low signal-to-noise spectra, we achieve average isolate-level accuracies exceeding 82% and antibiotic treatment identification accuracies of 97.0±0.3%. We also show that this approach distinguishes between methicillin-resistant and -susceptible isolates of Staphylococcus aureus (MRSA and MSSA) with 89±0.1% accuracy. We validate our results on clinical isolates from 50 patients. Using just 10 bacterial spectra from each patient isolate, we achieve treatment identification accuracies of 99.7%. Our approach has potential for culture-free pathogen identification and antibiotic susceptibility testing, and could be readily extended for diagnostics on blood, urine, and sputum.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 52

1. 1.

   Fleischmann C, et al. Assessment of global incidence and mortality of hospital-treated sepsis. current estimates and limitations. Am. J. Respir. Crit. Care Med. 2016;193:259-272.

   Not in our library10.1164/rccm.201504-0781oc

2. 2.

   DeAntonio R, Yarzabal J-P, Cruz JP, Schmidt JE, Kleijnen J. Epidemiology of community-acquired pneumonia and implications for vaccination of children living in developing and newly industrialized countries: A systematic literature review. Hum. Vaccin. Immunother. 2016;12:2422-2440.

   Not in our library10.1080/21645515.2016.1174356

3. 3.

   Torio, C.M. & Moore, B.J. National inpatient hospital costs: The most expensive conditions by payer, 2013. Tech. Rep. HCUP Statistical Brief #204., Agency for Healthcare Research and Quality (2016).

   Not in our library

4. 4.

   Dellinger, R. P. et al. Surviving sepsis campaign: international guidelines for management of severe sepsis and septic shock: 2012.

   Not in our library10.1007/s00134-012-2769-8

5. 5.

   Chaudhuri A, et al. EFNS guideline on the management of community-acquired bacterial meningitis: report of an EFNS task force on acute bacterial meningitis in older children and adults. Eur. J. Neurol. 2008;15:649-659.

   Not in our library10.1111/j.1468-1331.2008.02193.x

6. 6.

   American Thoracic Society. & Infectious Diseases Society of America. Guidelines for the management of adults with hospital-acquired, ventilator-associated, and healthcare-associated pneumonia. Am. J. Respir. Crit. Care Med. 2005;171:388-416.

   Not in our library10.1164/rccm.200405-644st

7. 7.

   Fleming-Dutra KE, et al. Prevalence of inappropriate antibiotic prescriptions among US ambulatory care visits, 2010-2011. JAMA. 2016;315:1864-1873.

   Not in our library10.1001/jama.2016.4151

8. 8.

   Butler HJ, et al. Using raman spectroscopy to characterize biological materials. Nat. Protoc. 2016;11:664-687.

   Not in our library10.1038/nprot.2016.036

9. 9.

   Stöckel S, Kirchhoff J, Neugebauer U, Rösch P, Popp J. The application of raman spectroscopy for the detection and identification of microorganisms. J. Raman Spectrosc. 2016;47:89-109.

   Not in our library10.1002/jrs.4844

10. 10.

    Kloss S, et al. Culture independent raman spectroscopic identification of urinary tract infection pathogens: a proof of principle study. Anal. Chem. 2013;85:9610-9616.

    Not in our library10.1021/ac401806f

11. 11.

    Boardman AK, et al. Rapid detection of bacteria from blood with Surface-Enhanced raman spectroscopy. Anal. Chem. 2016;88:8026-8035.

    Not in our library10.1021/acs.analchem.6b01273

12. 12.

    Schmid U, et al. Gaussian mixture discriminant analysis for the single-cell differentiation of bacteria using micro-raman spectroscopy. Chemometrics Intellig. Lab. Syst. 2009;96:159-171.

    Not in our library10.1016/j.chemolab.2009.01.008

13. 13.

    Münchberg U, Rösch P, Bauer M, Popp J. Raman spectroscopic identification of single bacterial cells under antibiotic influence. Anal. Bioanal. Chem. 2014;406:3041-3050.

    Not in our library10.1007/s00216-014-7747-2

14. 14.

    Novelli-Rousseau A, et al. Culture-free antibiotic-susceptibility determination from single-bacterium raman spectra. Sci. Rep. 2018;8:3957.

    Not in our library10.1038/s41598-018-22392-9

15. 15.

    Liu C-Y, et al. Rapid bacterial antibiotic susceptibility test based on simple surface-enhanced raman spectroscopic biomarkers. Sci. Rep. 2016;6:23375.

    Not in our library10.1038/srep23375

16. 16.

    Lu X, et al. Detecting and tracking nosocomial methicillin-resistant staphylococcus aureus using a microfluidic SERS biosensor. Anal. Chem. 2013;85:2320-2327.

    Not in our library10.1021/ac303279u

17. 17.

    Germond A, et al. Raman spectral signature reflects transcriptomic features of antibiotic resistance in escherichia coli. Communications Biology. 2018;1:85.

    Not in our library10.1038/s42003-018-0093-8

18. 18.

    Ayala OD, et al. Drug-Resistant staphylococcus aureus strains reveal distinct biochemical features with raman microspectroscopy. ACS Infect Dis. 2018;4:1197-1210.

    Not in our library10.1021/acsinfecdis.8b00029

19. 19.

    Kirchhoff J, et al. Simple ciprofloxacin resistance test and determination of minimal inhibitory concentration within 2 h using raman spectroscopy. Anal. Chem. 2018;90:1811-1818.

    Not in our library10.1021/acs.analchem.7b03800

20. 20.

    Vincent J-L, et al. International study of the prevalence and outcomes of infection in intensive care units. JAMA. 2009;302:2323-2329.

    Not in our library10.1001/jama.2009.1754

21. 21.

    Krizhevsky, A., Sutskever, I. & Hinton, G.E. ImageNet classification with deep convolutional neural networks. In Pereira, F., Burges, C. J. C., Bottou, L. & Weinberger, K. Q. (eds.) Advances in Neural Information Processing Systems 25, 1097-1105 (Curran Associates, Inc., 2012).

    Not in our library

22. 22.

    Mnih, V., Heess, N., Graves, A. & Kavukcuoglu, K. Recurrent models of visual attention. In Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N. D. & Weinberger, K. Q. (eds.) Advances in Neural Information Processing Systems 27, 2204–2212 (Curran Associates, Inc., 2014).

    Not in our library

23. 23.

    Karpathy, A. & Fei-Fei, L. In Proceedings of the IEEE conference on computer vision and pattern recognition, 3128–3137 (cv-foundation.org, 2015).

    Not in our library

24. 24.

    Zhang, R., Isola, P. & Efros, A.A. In Computer Vision – ECCV 2016, 649-666 (Springer International Publishing, 2016).

    Not in our library

25. 25.

    Dong, C., Loy, C.C., He, K. & Tang, X. In Computer Vision – ECCV 2014, 184–199 (Springer International Publishing, 2014).

    Not in our library

26. 26.

    Wang, L., Ouyang, W., Wang, X. & Lu, H. In Proceedings of the IEEE international conference on computer vision, 3119–3127 (cv-foundation.org, 2015).

    Not in our library

27. 27.

    Girshick, R., Donahue, J., Darrell, T. & Malik, J. In Proceedings of the IEEE conference on computer vision and pattern recognition, 580–587 (cv-foundation.org, 2014).

    Not in our library

28. 28.

    Girshick R, et al. Hierarchical deep convolutional neural networks combine spectral and spatial information for highly accurate raman microscopy based cytopathology. J. Biophotonics. 2018;11:e201800022.

    Not in our library10.1002/jbio.201800022

29. 29.

    Lotfollahi M, Berisha S, Daeinejad D, Mayerich D. Digital staining of High-Definition fourier transform infrared (FT-IR) images using deep learning. Appl. Spectrosc. 2019;73:556-564.

    Not in our library10.1177/0003702818819857

30. 30.

    Berisha S, et al. Deep learning for FTIR histology: leveraging spatial and spectral features with convolutional neural networks. Analyst. 2019;144:1642-1653.

    Not in our library10.1039/c8an01495g

31. 31.

    Kampe B, Kloß S, Bocklitz T, Rösch P, Popp J. Recursive feature elimination in raman spectra with support vector machines. Front. Optoelectron. 2017;10:273-279.

    Not in our library10.1007/s12200-017-0726-4

32. 32.

    Guo S, et al. Model transfer for raman-spectroscopy-based bacterial classification. J. Raman Spectrosc. 2018;49:627-637.

    Not in our library10.1002/jrs.5343

33. 33.

    Gurbani, S. S. et al. A convolutional neural network to filter artifacts in spectroscopic MRI. Magn. Reson. Med. 80, 1765–1775(2018).

    Not in our library10.1002/mrm.27166

34. 34.

    Malek S, Melgani F, Bazi Y. One-dimensional convolutional neural networks for spectroscopic signal regression: Feature extraction based on 1D-CNN is proposed and validated. J. Chemom. 2018;32:e2977.

    Not in our library10.1002/cem.2977

35. 35.

    Liu, J. et al. Deep convolutional neural networks for raman spectrum recognition: a unified solution. Analyst (2017).

    Not in our library10.1039/c7an01371j

36. 36.

    Zhang X, Lin T, Xu J, Luo X, Ying Y. DeepSpectra: An end-to-end deep learning approach for quantitative spectral analysis. Anal. Chim. Acta. 2019;1058:48-57.

    Not in our library10.1016/j.aca.2019.01.002

37. 37.

    He, K., Zhang, X., Ren, S. & Sun, J. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778 (2016).

    Not in our library

38. 38.

    Dumoulin, V. & Visin, F. A guide to convolution arithmetic for deep learning. Preprint at https://arxiv.org/abs/1603.07285(2016).

    Not in our library

39. 39.

    Banaei, N., Watz, N., Getsinger, D. & Ghafghaichi, L. SUH antibiogram data for bacterial and yeast isolates. Tech. Rep., Stanford Healthcare Clinical Microbiology Laboratory http://med.stanford.edu/bugsanddrugs/clinical-microbiology/_jcr_content/main/panel_builder/panel_0/download_748639600/file.res/SHC/%20antibiogram/202016.pdf (2016).

    Not in our library

40. 40.
    How to Optimize the Use of Blood Cultures for the Diagnosis of Bloodstream Infections? A State-of-the Art · 2016

    No notice

Cited by papers we hold 5

• A simple, low-cost, and highly efficient protocol for rapid isolation of pathogenic bacteria from human blood · 2025
  Not checked
• Rapid, label-free histopathological diagnosis of liver cancer based on Raman spectroscopy and deep learning · 2023
  No notice
• Discrimination between Carbapenem-Resistant and Carbapenem-Sensitive Klebsiella pneumoniae Strains through Computational Analysis of Surface-Enhanced Raman Spectra: a Pilot Study · 2022
  Not checked
• Drug-resistant Staphylococcus aureus bacteria detection by combining surface-enhanced Raman spectroscopy (SERS) and deep learning techniques · 2021
  Not checked
• Remote near infrared identification of pathogens with multiplexed nanosensors · 2020
  Not checked

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.