Illegal and dangerous items, akin to explosives, could possibly be detected with 100% efficiency, using artificial intelligence (AI) and a recent X-ray approach by UK academics.
Some explosives could be difficult to identify with a traditional X-ray alone, and the brand new method could revolutionise how illicit products akin to drugs, illegal wildlife and explosives are detected.
Researchers say their findings can have significant implications for the safety sector, and now have the potential to support healthcare and industry.
It is a radically different way of inspecting materials and objects by analysing textures, and allows us a recent way of detecting illicit materials
Professor Sandro Olivo, UCL
Senior creator Professor Sandro Olivo (UCL Medical Physics & Biomedical Engineering), said: “It is a radically different way of inspecting materials and objects by analysing textures, and allows us a recent way of detecting illicit materials.
“The tiny bends in X-rays have all the time been there, but they’re invisible to traditional X-ray systems, so this permits us to access an enormous amount of previously untapped information.
“To this point, we’ve got shown it really works extremely well for detecting explosives, however it could possibly be utilized in any application that relies on X-rays, akin to medical imaging or detecting weaknesses in industrial structures.”
Within the study, the team, led by UCL researchers, combined a recent X-ray measuring technique with AI machine learning, and tested it in a custom-developed X-ray security scanner, using objects containing hidden explosive material in addition to protected objects.
Through earlier research, Prof Olivo had discovered that microscopic changes or irregularities in objects cause X-ray beams to bend as they go through them.
The brand new method relies on measuring these tiny bends because the beam moves through objects of various textures.
The bend occurs at angles as small as a microradian, which is about 20,000 times smaller than a level.
The team combined the measurement of those angles, often called microradian scatter, with AI to accurately discover objects and materials through their texture.
In accordance with the study, when tested on explosives, the detection rate was 100%.
Co-author Tristram Riley-Smith, XPCI Technology founder and UKRI Champion for Conflict, Crime & Security, said: “This research has demonstrated the potential to remodel the detection of covert threats around the globe, in addition to such varied contraband as narcotics and illicit wildlife commodities.”
Co-author David Bate, UCL Medical Physics & Biomedical Engineering, said: “By training the AI on ‘perfect’ components, we predict that the technique could be used to discover defects in industrial components akin to cracks, rust or gaps before they’re visible to the naked eye.”
The findings are published in Nature Communications.