ARS | Publication request: Hyperspectral imaging of shiga toxin-producing escherichia coli serogroups O26, O45, O103, O111, O121, and O145 on Rainbow Agar

Submitted to: Journal of Food Protection
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: March 7, 2013
Publication Date: N/A

Interpretive Summary: Hyperspectral imaging was used to detect and classify non-O157 Shiga-toxin producing Escherichia coli (STEC) serogroups O26, O45, O103, O111, O121, and O145 on Rainbow Agra (RBA) O157 plates. Detection of non-O157 STEC colonies for conformational testing is challenging due to the lack of distinct color variation among serogroups grown RBA. Hyperspectral imaging is an optical imaging technique that combines aspects of conventional imaging and vibrational spectroscopy so that data can provide two-dimensional spatial information on colony shapes and one-dimensional spectral information at every pixel in each colony under test. Spectral libraries of pure pathogen cultures were built, classification models developed and tested on non-O157 STEC serogroups artificially inoculated into ground beef. Results showed the potential of the hyperspectral imaging technique for rapid presumptive positive screening of non-O157 STEC in meat products.

Technical Abstract: The U.S. Department of Agriculture, Food Safety Inspection Service has determined that six non-O157 Shiga toxin-producing Escherichia coli (STEC) serogroups (O26, O45, O103, O111, O121, and O145) are adulterants in raw beef. Isolate and phenotypic discrimination of non-O157 STEC is problematic due to the lack of suitable agar media. The lack of distinct phenotypic color variation among non-O157serogroups cultured on chromagenic agar poses a challenge in picking colonies for confirmation. In this study, visible and near-infrared (VNIR) hyperspectral imaging (HIS) and chemometrics were used to detect and classify non-O157 STEC serogroups grown on Rainbow Agar O157. The method was first developed by building a spectral libraries were built for each serogroup obtained from ground-truth regions-of-interest (ROIs) representing the true identity of each pixel and thus each pure culture colony in the agar plate image. The spectral library for the pure culture non-O157 STEC consisted of 2,171 colonies and 124,347 of pixel spectra. Classification models for each serogroup were developed with k nearest neighbour classifier. The overall classification training accuracy at the colony level was 99%. The classifier was validated using ground beef broth artificially inoculated with 10 and 100 CFU/ml. The validation ground-truth ROIs of the STEC target colonies consisted of 606 colonies and 3,030 of pixel spectra. The overall classification accuracy was 98%. The average specificity of the method was 98% due to the low false positive rate of 1.2%. The sensitivity ranged from 78% to 100% due to the false negative rates of 22%, 7%, and 8% for O145, O45, and O26, respectively. This study showed a potential of VNIR hyperspectral imaging for detecting and classifying colonies of the six non-O157 STEC serogroups. The technique needs to be validated with bacterial cultures directly extracted from meat products and positive identification of colonies using confirmatory tests such as latex agglutination tests or polymerase chain reaction.