Location: Quality & Safety Assessment ResearchTitle: Classification of Salmonella serotypes with hyperspectral microscope imagery Author
|Seo, Youngwook - US Department Of Agriculture (USDA)|
|Hinton, Jr, Arthur|
Submitted to: Annals of Clinical Pathology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 2/27/2017
Publication Date: 3/7/2017
Citation: Park, B., Seo, Y., Eady, M.B., Yoon, S.C., Hinton Jr, A., Lawrence, K.C., Gamble, G.R. 2017. Classification of Salmonella serotypes with hyperspectral microscope imagery. Annals of Clinical Pathology. 5(2):1108-1116.
Interpretive Summary: During past decade numerous foodborne outbreaks have occurred, resulted in about 48 million incidences of foodborne illness, 128,000 hospitalizations and 3,000 deaths in the United States. Among serious foodborne outbreaks, Salmonella had the most infections and incidence cases. Specifically, each year more than million people are sickened by Salmonella in the United States and approximately 200,000 cases from poultry alone and the average national cost of foodborne illness was estimated as over $93 billion. Thus there is a need to reduce foodborne illnesses, especially in poultry products. To reduce the risk, real-time and deployable microbial detection and identification of source has become increasingly important. Nondestructive advanced optical method such as hyperspectral microscope imaging (HMI) to evaluate foodborne pathogens can enhance the presumptive-positive screening method by reducing labor and increasing speed for sample analysis. In this study, we developed HMI methods to classify five Salmonella serotypes with their spectral signatures from the live cells using classification methods. Combining with traditional culture protocols, HMI techniques can be used for identifying Salmonella serotypes rapidly at the cell level and further employed at the poultry industry.
Technical Abstract: Previous research has demonstrated an optical method with acousto-optic tunable filter (AOTF) based hyperspectral microscope imaging (HMI) had potential for classifying gram-negative from gram-positive foodborne pathogenic bacteria rapidly and nondestructively with a minimum sample preparation. In this research, we continued developing HMI methods to identify serotypes of Salmonella, most typical gram-negative bacteria at a cell level. We successfully validated the protocol for live-cell immobilization on glass slide to acquire 89 contiguous quality spectral images from five S. serotype bacterial cells within 45 sec using 250 ms exposure time and approximately 3.5% gain of an electron multiplying charge coupled device (EMCCD) camera. Among the spectral imagery from visible/near-infrared range, the scattering intensity at the wavelengths of 454, 542, 550, 582, 630, 690, 710, and 722 nm were distinct for Salmonella. The average classification accuracy of five Salmonella serotypes was 84%. However, S. Typhimurium and S. Enteritidis were classified with 93.2% and 93.9% accuracy using a support vector machine (SVM) algorithm.