Detecting Escherichia coli Contamination on Plant Leaf Surfaces Using UV-C Fluorescence Imaging and Deep Learning

The transmission of <i>Escherichia coli</i> through contaminated fruits and vegetables poses serious public health risks and has led to several national outbreaks in the USA. To enhance food safety, rapid and reliable detection of <i>E. coli</i> on produce is essential. This study evaluated the performance of the CSI-D+ system combined with deep learning for detecting varying concentrations of <i>E. coli</i> on citrus and spinach leaves. Eight levels of <i>E. coli</i> contamination, ranging from 0 to 10⁸ colony-forming units (CFU)/mL, were inoculated onto the leaf surfaces. For each concentration level, 10 droplets were applied to 8 citrus and 12 spinach leaf samples (2 cm in diameter), and fluorescence images were captured. The images were then subdivided into quadrants, and several post-processing operations were applied to generate the final dataset, ensuring that each sample contained at least 2-3 droplets. Using this dataset, multiple deep learning (DL) models, including EfficientNetB7, ConvNeXtBase, and five YOLO11 variants (n, s, m, l, x), were trained to classify <i>E. coli</i> concentration levels. Additionally, Eigen-CAM heatmaps were used to visualize the spatial responses of the models to bacterial presence. All YOLO11 models outperformed EfficientNetB7 and ConvNeXtBase. In particular, YOLO11s-cls was identified as the best-performing model, achieving average validation accuracies of 88.43% (citrus) and 92.03% (spinach), and average test accuracies of 85.93% (citrus) and 92.00% (spinach) at a 0.5 confidence threshold. This model demonstrated an inference speed of 0.011 s per image with a size of 11 MB. These findings indicate that fluorescence-based imaging combined with deep learning for rapid <i>E. coli</i> detection could support timely interventions to prevent contaminated produce from reaching consumers.