Title: Development of classification models to detect salmonella enteritidis and salmonella typhimurium found in poultry carcass rinses by visible-near infrared hyperspectral imaging Authors
Submitted to: Proceedings of SPIE
Publication Type: Proceedings
Publication Acceptance Date: May 7, 2013
Publication Date: N/A
Interpretive Summary: Detection and enumeration of bacteria typically require the inoculation and incubation of microorganisms on agar plates before finding and picking up the presumptive positive colonies on agar plates, which is labor-intensive and time-consuming. In addition, growth of background microflora on agar plates along with target pathogens such as Salmonella and Campylobacter may also significantly affect the performance of visual screening of agar plates. In this study, visible near-infrared hyperspectral imaging measuring both spatial and spectral information in the wavelength range of 400-1,000 nm was used to detect Salmonella Enteritidis (SE) and Salmonella Typhimurium (ST) on brilliant green sulfa (BGS) and xylose lysine tergitol 4 (XLT4) agar plates and differentiate them from background microflora commonly found in chicken carcass rinses. Ten classification models for Salmonella detection in the presence of background microflora were developed with pure cultures of two Salmonella serotypes (SE and ST) and eight known background microflora. Ten multivariate analysis and classification methods were examined to develop the classification models. Salmonella Typhimurium was classified with over 99% accuracy on XLT4 agar. Salmonella detection accuracy on BGS agar was 98%. Validation of the Salmonella detection models with unknown microorganisms obtained from chicken carcass rinses spiked with Salmonella (SE and ST) showed the potential of the hyperspectral classification models for Salmonella detection. The expected outcome of the research is a rapid and accurate screening tool for the detection of Salmonella colonies on agar plates.
Technical Abstract: Salmonella is a major cause of foodborne disease outbreaks resulting from the consumption of contaminated food products in the United States. This paper reports the development of a hyperspectral imaging technique for detecting and differentiating two of the most common Salmonella serotypes, Salmonella Enteritidis (SE) and Salmonella Typhimurium (ST), from background microflora that are often found in poultry carcass rinse. Presumptive positive screening of colonies with a traditional direct plating method is a labor intensive and time consuming task. Thus, this paper is concerned with the detection of differences in spectral characteristics among the pure SE, ST, and background microflora grown on brilliant green sulfa (BGS) and xylose lysine tergitol 4 (XLT4) agar media with a spread plating technique. Visible near-infrared hyperspectral imaging, providing the spectral and spatial information unique to each microorganism, was utilized to differentiate SE and ST from the background microflora. A total of 10 classification models, including five machine learning algorithms, each without and with principal component analysis (PCA), were validated and compared to find the best model in classification accuracy. The five machine learning (classification) algorithms used in this study were Mahalanobis distance (MD), k-nearest neighbor (kNN), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and support vector machine (SVM). The average classification accuracy of all 10 models on a calibration (or training) set of the pure cultures on BGS agar plates was 98% (Kappa coefficient = 0.95) in determining the presence of SE and/or ST although it was difficult to differentiate between SE and ST. The average classification accuracy of all 10 models on a training set for ST detection on XLT4 agar was over 99% (Kappa coefficient = 0.99) although SE colonies on XLT4 agar were difficult to differentiate from background microflora. The average classification accuracy of all 10 models on a validation set of chicken carcass rinses spiked with SE or ST and incubated on BGS agar plates was 94.45% and 83.73%, without and with PCA for classification, respectively. The best-performing classification model on the validation set was QDA without PCA by achieving the classification accuracy of 98.65% (Kappa coefficient=0.98). The overall best performing classification model regardless of using PCA was MD with the classification accuracy of 94.84% (Kappa coefficient=0.88) on the validation set.