Rapid Detection of Salmonella in Fresh Meat Using Computer Vision and Digital Imaging

Abstract

The rapid detection of foodborne pathogens is critical for improving food safety and reducing the risk of contamination in meat products. This study evaluated the detection and survival of Salmonella Typhimurium in ground chicken meat using advanced digital imaging and computer vision approaches alongside conventional microbiological analysis. Four treatment groups were investigated: Salmonella Typhimurium culture only (control), ground chicken inoculated with Salmonella Typhimurium, inoculated ground chicken treated with 1% vinegar solution, and inoculated ground chicken treated with sterile Buffered Peptone Water (BPW). Samples were prepared under sterile conditions, serially diluted, and plated on Tryptic Soy Agar (TSA) and Xylose Lysine Deoxycholate (XLD) agar for microbial enumeration. Fluorescence-based digital imaging was employed to visualize microbial presence and assess cellular morphology within the meat matrix. Statistical analyses were conducted using the Kruskal–Wallis nonparametric test followed by Dunn’s pairwise comparisons at a significance level of p < 0.05. Results demonstrated significant differences in microbial counts among treatment groups in the primary analysis (Kruskal–Wallis χ² = 9.684, p = 0.0215). Dunn’s post-hoc test revealed significant differences between the control culture and all meat treatment groups, indicating that the meat matrix and antimicrobial intervention influenced bacterial survival. The robustness median test further confirmed significant differences among groups (Pearson χ² = 11.0769, p = 0.011). However, a secondary analysis showed no significant differences among selected treatment groups (Kruskal–Wallis χ² = 2.604, p = 0.272), suggesting variability in treatment effects under certain conditions. Digital imaging successfully visualized microbial distribution and morphological characteristics, supporting rapid and non-destructive assessment of contamination. The findings demonstrate the potential of integrating computer vision, digital imaging, and conventional microbiological techniques for enhanced detection of Salmonella Typhimurium in fresh meat. This combined approach offers a promising tool for real-time monitoring, quality assurance, and improved food safety management in meat processing systems.