Rapid Classification of Single Bacterium Based on Backscattering Microscopic Spectrum—A Pilot Study

Abstract

Rapid detection of foodborne pathogens is one of the most effective ways to solve food safety problems. To achieve rapid and noninvasive detection and classification of foodborne pathogens, we modified a fiber confocal backscattering micro-spectral system to suit an extremely small biological sample, that is, a bacterium. This system offers single-bacterium level, label-free, convenient, and environmentally friendly characterization. Three categories of common foodborne pathogens (Salmonella typhimurium, Escherichia coli, and Staphylococcus aureus) were measured. The scattering spectrum ranging from 450 to 900 nm was selected, and by the model of principal component analysis (PCA) and error back propagation algorithm of back propagation neural network (BPNN), the backscattering microscopic spectra of three categories of pathogens were dimensionally reduced, identified, and classified. The results showed that the identification accuracy of three categories of pathogens was above 90%, under neutral, acidic, and alkaline culturing conditions, respectively. The preliminary results demonstrated the feasibility of using confocal backscattering microscopic spectra combined with PCA and BPNN algorithm to identify and classify single bacterium in a rapid, noninvasive, and label-free manner.