Researchers from the University of South Australia are using artificial intelligence (AI) to detect contaminated food in fields and factories before reaching consumers, and potentially saving lives.

To accomplish this, the team used advanced hyperspectral imaging (HSI) in combination with machine learning (ML) to identify mycotoxins, which are dangerous compounds produced by fungi that can contaminate food at the growth, harvest and storage stages.

An advanced hyperspectral imaging system scans almonds on a conveyor belt, capturing an optical footprint of mycotoxins. Source: University of South Australia

Additionally, mycotoxins can reportedly cause health issues, like cancer, compromised immunity and hormone-related disorders.

Experts suggest that traditional mycotoxin detection approaches are time-consuming, expensive and destructive, thus making them inappropriate for large-scale real-time food processing.

“In contrast, hyperspectral imaging — a technique that captures images with detailed spectral information — allows us to quickly detect and quantify contamination across entire food samples without destroying them.”

The team determined the effectiveness of HSI in how it detects toxic compounds in cereal grains and nuts — which are both highly susceptible to fungi and mycotoxin contamination in warm, humid environments — from cultivation to storage.

“HSI captures an optical footprint of mycotoxins and when paired with machine learning algorithms it rapidly classifies contaminated grains and nuts based on subtle spectral variations,” the researchers explained.

The researchers found that ML-integrated HSI systems outperformed traditional methods for detecting mycotoxins. Specifically, the technology proved particularly effective at identifying aflatoxin B1, which is one of the most carcinogenic substances found in food, according to experts.

The team envisions that in the future, HSI and ML could potentially be deployed on processing lines or handheld devices, thereby reducing health risks and trade losses by ensuring that only safe, uncontaminated produce reaches store shelves.

An article detailing the technology, "Detection of Mycotoxins in Cereal Grains and Nuts Using Machine Learning Integrated Hyperspectral Imaging: A Review," appears in the journal Toxins.