Hyperspectral imaging of common foodborne pathogens for rapid identification and differentiation

Abstract

Hyperspectral imaging (HSI) provides both spatial and spectral information of a sample by combining imaging with spectroscopy. The objective of this study was to generate hyperspectral graphs of common foodborne pathogens and to develop and validate prediction models for the classification of these pathogens. Four strains of Cronobacter sakazakii , five strains of Salmonella spp., eight strains of Escherichia coli , and one strain each of Listeria monocytogenes and Staphylococcus aureus were used in the study. Principal component analysis and k NN ( k ‐nearest neighbor) classifier model were used for the classification of hyperspectra of various bacterial cells, which were then validated using the cross‐validation technique. Classification accuracy of various strains within genera including C. sakazakii , Salmonella spp., and E. coli , respectively, was 100%; except within C. sakazakii , strain BAA‐894, and E. coli , strains O26, O45, and O121 had 66.67% accuracy. When all strains were studied together (irrespective of their genus) for the classification, only C. sakazakii P1, E. coli O104, O111, and O145, S . Montevideo, and L. monocytogenes had 100% classification accuracy, whereas E. coli O45 and S . Tennessee were not classified (classification accuracy of 0%). Lauric arginate treatment of C. sakazakii BAA‐894, E. coli O157, S . Senftenberg, L. monocytogenes , and S. aureus significantly affected their hyperspectral signatures, and treated cells could be differentiated from the healthy, nontreated cells.

Developing an affordable hyperspectral imaging system for rapid identification of Escherichia coli O157:H7 and Listeria monocytogenes in dairy products

“…Using HSI, Michael et al. (2019) were able to identify foodborne pathogens at a cellular level (various strains of Cronobacter sakazakii , Salmonella spp., Shiga toxin producing Escherichia coli (STEC), and Listeria monocytogenes ) with accuracy ranging from 66.66% to 100% within the respective genera. Michael et al.…”

“…identification and differentiation of four strains of Cronobacter sakazakii, five strains of Salmonella, eight strains of Escherichia coli, and a single strain of Listeria monocytogenes and Staphylococcus aureus at a cellular level using a commercial CytoViva HSI microscope setup.The author used principal component analysis and kNN classifiers to classify the hyperspectral signatures Michael et al (2019). reported 100% classification accuracy in all but four strains when analyzed within their respective genera.…”

Recent Advances and Applications of Rapid Microbial Assessment from a Food Safety Perspective

“…The developed model was cross-validated, and the results were satisfactory for some strains, while the model’s performance was poor in some others. The authors proposed the use of the method for testing the presumptive presence of foodborne pathogens, but it was mentioned that it cannot yet replace conventional microbiology methods [ 73 ].…”

Advancement in Salmonella Detection Methods: From Conventional to Electrochemical-Based Sensing Detection

“…Thus, HSI will provide more specific detection and identification compared to a single source of modality. This non-destructive method is usually being used in foodborne pathogen detection and the development of a complete hyperspectral graph of common foodborne pathogens is still under development [ 135 ]. Seo Y. N. et al reported on the development of an HSI method for automated screening of S .…”

“…On the other hand, sample preparation is also a crucial part of the Salmonella detection process as the sample might be isolated in variety of forms (solid/liquid). Most of the Salmonella detection methods discussed require an input sample in a liquid form except for MALDI-TOF MS, NIR spectroscopy, HSI spectroscopy, and optical phenotyping (BARDOT) as they require bacterial colonies grown on an agar plate [ 18 , 127 , 132 , 135 ]. Most of the immunological and molecular-based methods also require sample pre-treatment or pre-enrichment, while other methods such as mass spectrometry, spectroscopy and electrochemical biosensor can be perform in a mixed sample with minimal pre-treatment.…”