Hyperspectral microscopy to identify foodborne bacteria with optimum lighting source

Authors: Eady, Matthew; Park, Bosoon; Yoon, Seung-Chul; Lawrence, Kurt; Gamble, Gary

Submitted to: American Society of Agricultural and Biological Engineers
Publication Type: Proceedings
Publication Acceptance Date: 6/15/2016
Publication Date: 7/20/2016
Citation: Eady, M.B., Park, B., Yoon, S.C., Lawrence, K.C., Gamble, G.R. 2016. Hyperspectral microscopy to identify foodborne bacteria with optimum lighting source. American Society of Agricultural and Biological Engineers. Paper No. 162462364.

Interpretive Summary: Optical methods have the potential to detect chemical or biological samples rapidly with the advantage of minimum or no sample preparation. Hyperspectral microscopy is an emerging technology for early and rapid detection of foodborne pathogenic bacteria. Spectral images of bacteria are captured from a microscope. Previously, these images have shown that the light scattering patterns of the bacteria are unique to the organisms on a species and serotype level. Here, the objective is to compare two microscope lamps, tungsten halogen (TH) and metal halide (MH) for determining an optimal lamp for better performance. Images were collected for five Salmonella serotypes with both TH and MH lamps. Light scattering patterns for the bacteria were collected in the visible light range. While light scattering patterns from the two lamps varied drastically, they both had 100 % Salmonella serotype classification accuracies with hyperspectral microscope imaging. Reduction of the spectral bands from MH lamp still showed classification accuracy of 99 %. These results were consistent across three experimental repetitions. MH lamps may be suitable for applications that require a data reduction method, due to the large storage necessary for spectral imaging files.

Technical Abstract: Hyperspectral microscopy is an emerging technology for rapid detection of foodborne pathogenic bacteria. Since scattering spectral signatures from hyperspectral microscopic images (HMI) vary with lighting sources, it is important to select optimal lights. The objective of this study is to compare tungsten halogen (TH) to metal-halide (MH) lighting source, assessing detection accuracies and robustness between the two light sources. HMI of live foodborne bacterial cells from five Salmonella serotypes were collected with both lighting sources. It was found that key spectral wavelengths in the visible ranges could be used for classification of the bacterial samples with MH. The experiments were repeated for validation of models with image subsets from images collected with MH and TH lighting sources. The spectra generated from HMI of five live Salmonella serotypes with two lighting sources, MH and TH were compared to assess classification accuracy and robustness with wavelength range of 450~800 nm. Ten key wavelengths between 594 and 630 nm were identified from MH HMI; however TH band reduction decreased classification accuracy. Multivariate data analysis methods were applied with the principal component-linear discriminate analysis (PC-LDA) algorithm for the classification of the five Salmonella serotypes. PC regression was applied to the second and third repetitions to assess the repeatability of the experiment. PC-LDA classified serotype subsets, reporting both MH and TH accuracies at 100%, while the reduced key MH bands achieved up to 99.3% accuracy. PC regression calculated the root mean squared error of cross–validation < 0.014 and a R2 > 0.948 for both full spectrum lights.