Australian scientists use AI to spot toxicants in food

(MENAFN) An international study led by Australian scientists has found that artificial intelligence can detect contaminated food before it reaches the market, a breakthrough that could help prevent millions of deaths globally each year.

The research, conducted by the University of South Australia (UniSA) and partners, demonstrated that combining hyperspectral imaging (HSI) with machine learning can quickly and accurately identify mycotoxins — poisonous substances produced by fungi — in cereal grains and nuts during growth, harvest, and storage.

Mycotoxins have been linked to cancer, weakened immune systems, and hormonal disorders. According to the World Health Organization, foodborne contamination, including mycotoxins, results in 600 million illnesses and 4.2 million deaths annually worldwide.

Researchers noted that current detection methods are often slow, expensive, and destructive, making them unsuitable for large-scale real-time food processing. Lead author and UniSA PhD candidate Ahasan Kabir explained that “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.”

MENAFN12082025000045017281ID1109917047