Why can it be used in rapid detection of pathogenic microorganisms by Raman spectroscopy?

   Bacterial infections are a leading cause of death in both developed and developing nations:

   Bacterial infections taking >6.7 million lives each year. These infections are also costly to treat, accounting for 8.7% of annual healthcare spending, or $33 billion, in the United States alone. Current diagnostic methods require sample culturing to detect and identify the bacteria and its antibiotic susceptibility, a slow process that can take days even in state-of-the-art labs. Broad spectrum antibiotics are often prescribed while waiting for culture results, and according to the Centers for Disease Control and Prevention, over 30% of patients are treated unnecessarily. New methods for rapid, culture-free diagnosis of bacterial infections are needed to enable earlier prescription of targeted antibiotics and help mitigate antimicrobial resistance.

    Raman spectroscopy has the potential to identify the species and antibiotic resistance of bacteria:

  when combined with confocal spectroscopy, can interrogate individual bacterial cells (Fig.1). Different bacterial phenotypes are characterized by unique molecular compositions, leading to subtle differences in their corresponding Raman spectra. However, because Raman scattering efficiency is low (~10⁻⁸ scattering probability), these subtle spectral differences are easily masked by background noise. High signal-to-noise ratios (SNRs) are thus needed to reach high identification accuracies, typically requiring long measurement times that prohibit high-throughput single-cell techniques. Additionally, the large number of clinically relevant species, strains, and antibiotic resistance patterns require comprehensive datasets that are not gathered in studies that focus on differentiating between species, isolates (typically referred to as strains in the literature), or antibiotic susceptibilities In this work, we address this challenge by training a convolutional neural network (CNN) to classify noisy bacterial spectra by isolate, empiric treatment, and antibiotic resistance.

    A convolutional neural network (CNN) can be used to identify bacteria from Raman spectra:

•    To build a training dataset of Raman spectra, we deposit bacterial cells onto gold-coated silica substrates and collect spectra from 2000 bacteria over monolayer regions for each strain. An SEM cross section of the sample is shown (gold coated to allow for visualization of bacteria under electron beam illumination). Scale bar is 1 µm. 
•   Conceptual measurement schematic: by focusing the excitation laser source to a diffraction-limited spot size, Raman signal from single cells can be acquired. 
•   Using a one-dimensional residual network with 25 total convolutional layers (see Methods for details), low-signal Raman spectra are classified as one of 30 isolates, which are then grouped by empiric antibiotic treatment. 
•   Raman spectra of bacterial species can be difficult to distinguish, and short integration times (1 s) lead to noisy spectra (SNR = 4.1). Averages of 2000 spectra from 30 isolates are shown in bold and overlaid on representative examples of noisy single spectra for each isolate. Spectra are color-grouped according to antibiotic treatment. These reference isolates represent over 94% of the most common infections seen at Stanford Hospital in the years