Fuente: Food Processing Researchers have enhanced an artificial intelligence tool used to rapidly detect bacterial contamination in food by eliminating misclassifications of food debris that looks like bacteria.

Bacterial contamination of food can occur throughout the entire production process, from pre-harvest on farms to post-harvest handling, processing and the finished product.

While conventional methods used to detect contamination of foods such as leafy greens, meat and cheese can take nearly a week, the new rapid detection method is designed to accurately detect within three hours.

Luyao Ma, an assistant professor at Oregon State University, and her collaborators from the University of California, Davis, Korea University and Florida State University, developed a deep learning-based model for rapid detection and classification of live bacteria using digital images of bacteria microcolonies.

It involved training the model to distinguish bacteria from microscopic food debris to improve its accuracy. A model trained only on bacteria misclassified debris as bacteria more than 24% of the time. The enhanced model, trained on both bacteria and debris, eliminated misclassifications.



Representative images of bacterial microcolonies and food debris captured using a phase-contrast microscope during research by Luyao Ma at Oregon State University. Image credit: Luyao Ma [Click on image for a clearer view.]

The study, published in npj Science of Food, tested the deep learning model on three bacterial strains — E. coli, Listeria monocytogenes and Bacillus subtilis — and food debris from chicken, spinach and Cotija cheese.

“Early detection of foodborne pathogens before products reach the market is essential to prevent outbreaks, protect consumer health and reduce costly recalls,” Ma said.

Researchers are now working to optimise the AI system for food industry applications.

Top image credit: iStock.com/wildpixel