|LADELY, SCOTT - Food Safety Inspection Service (FSIS)|
|Heitschmidt, Gerald - Jerry|
|Cray Jr, William|
Submitted to: Proceedings of SPIE
Publication Type: Proceedings
Publication Acceptance Date: 5/15/2012
Publication Date: 5/16/2012
Citation: Yoon, S.C., Windham, W.R., Ladely, S.R., Heitschmidt, G.W., Lawrence, K.C., Park, B., Narang, N., Cray Jr, W.C. 2012. Hyperspectral imaging for detection of non-O157 shiga-toxin producing escherichia coli(STEC) serogroups on spread plates of mixed cultures. Proceedings of SPIE. 8369-09.
Interpretive Summary: Culturing of microorganisms on solid agar media is the most widely used screening technique for foodborne pathogens although it is laborious and time-consuming and also involves manually selecting well-isolated colonies one-by-one for confirmatory testing. The USDA ARS scientists have been developing new non-contact optical imaging technology, based on hyperspectral imaging, for rapid presumptive positive screening of all colonies grown on agar plates. This study was part of ongoing research involving the optical detection and identification of non-O157 Shiga-toxin producing Escherichia coli (STEC) on agar plates. In 2011, USDA declared six STEC serogroups (O26, O45, O103, O111, O121, and O145) “adulterants” in raw ground beef and beef trim. Hyperspectral imaging is a non-destructive sensing technique appropriate for high-throughput screening of non-O157 STEC colonies on agar plates. In one of our previous studies, a hyperspectral imaging method was developed using 24 spread plates of pure cultures. In this study, the developed technique was tested with mixed cultures of six non-O157 STEC serogroups that were not used during method development. The independent test set was generated from six spread plates of mixed cultures. A total of 331 colonies were obtained from all six non-O157 STEC serogroups. The identity of each pixel and colony was predicted. The independent testing results showed 95% overall detection accuracy at pixel level and 97% at colony level. This study was an important first step for further research to test the imaging technique with contaminated ground beef samples. The study results implied the potential of the hyperspectral imaging technique for screening of any other pathogens on agar plates.
Technical Abstract: We investigated the feasibility of visible and near-infrared (VNIR) hyperspectral imaging for rapid presumptive-positive screening of six representative non-O157 Shiga-toxin producing Escherichia coli (STEC) serogroups (O26, O45, O103, O111, O121, and O145) on spread plates of mixed cultures. Although the traditional culture method is still the “gold standard” for presumptive-positive pathogen screening, it is time-consuming, labor-intensive, not effective in testing large amount of food samples, and cannot completely prevent unwanted background microflora from growing together with target microorganisms on agar media. A previous study was performed using the data obtained from pure cultures individually inoculated on spot and/or spread plates in order to develop multivariate classification models differentiating each colony of the six non-O157 STEC serogroups and to optimize the models in terms of parameters. This study dealt with the validation of the trained and optimized models with a test set of new independent samples obtained from colonies on spread plates of mixed cultures. A new validation protocol appropriate to a hyperspectral imaging study for mixed cultures was developed. One imaging experiment with colonies obtained from two serial dilutions was performed. A total of six agar plates were prepared, where O45, O111 and O121 serogroups were inoculated into all six plates and each of O45, O103 and O145 serogroups was added into the mixture of the three common bacterial cultures. The number of colonies grown after 24-h incubation was 331 and the number of pixels associated with the grown colonies was 16,379. The best model found from this validation study was based on pre-processing with standard normal variate and detrending (SNVD), first derivative, spectral smoothing, and k-nearest neighbor classification (kNN, k=3) of scores in the principal component subspace spanned by 6 principal components. The independent testing results showed 95% overall detection accuracy at pixel level and 97% at colony level. The developed model was proven to be still valid even for the independent samples although the size of a test set was small and only one experiment was performed. This study was an important first step in validating and updating multivariate classification models for rapid screening of ground beef samples contaminated by non-O157 STEC pathogens using hyperspectral imaging.