HMN 2026: How Deep learning detects foodborne bacteria within three hours by eliminating debris misclassifications

Researchers have significantly enhanced an artificial intelligence tool used to rapidly detect bacterial contamination in food by eliminating misclassifications of food debris that looks like bacteria. Current methods to detect contamination of foods such as leafy greens, meat and cheese, which typically involve cultivating bacteria, often require specialized expertise and are time-consuming—taking several days to a week.

Luyao Ma, an assistant professor at Oregon State University, and her collaborators from the University of California, Davis, Korea University and Florida State University, have developed a deep learning-based model for rapid detection and classification of live bacteria using digital images of bacteria microcolonies. The method enables reliable detection within three hours. The findings are published in the journal npj Science of Food.

Their latest breakthrough involves 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.

Bacterial contamination can arise throughout food production from farms to processing facilities and occur via sources such as animals, irrigation water, soil and air. The U.S. Food & Drug Administration estimates 48 million cases of foodborne illness annually, leading to 128,000 hospitalizations and 3,000 deaths.

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

The study tested the deep learning model on three bacterial strains—E. coli, listeria and Bacillus subtilis—and food debris from chicken, spinach and Cotija cheese. Researchers are now working to optimize the AI system for industry adoption.

Co-authors of the paper are Hyeon Work Park, Korea University; Zhengao Li, Florida State; and Nitin Nitin, UC Davis. Ma is affiliated with Oregon State’s Department of Food Science and Technology and Department of Biological & Ecological Engineering.

The content is provided for information purposes only.