While the most obvious application would be scanning bombs and other dangerous items and substances at airports, the findings described in Nature Communications Today, it is also possible to help detect cracks and rust in buildings, and ultimately identify tumors at an early stage.
A team of researchers from UCL hid small amounts of explosives, including Semtex and C4, inside electrical devices, such as laptops, hair dryers and cell phones. Items are placed inside the bag with a toothbrush, charger, paracetamol and other everyday items to replicate almost like a travel bag.
While standard X-ray machines hit objects with a uniform X-ray field, the team scanned the bags with a custom-built X-ray security scanner containing masks — metal sheets with holes are punched into them, which separates the beams into an array of smaller beams.
As the small beams pass through the bag and inside the bag, they are scattered at angles as small as one microradian (about 20,000 times smaller than a degree). angle change.
Lead author Sandro Olivo, from UCL Medical Physics & Biomedical Engineering, says AI is particularly good at picking up the textures of these materials, even when they’re hidden inside other objects. “Even if we hide a small amount of explosive somewhere, because there will be a bit of texture in the middle of a lot of other things, the algorithm will find it.”
The algorithm was able to accurately identify explosives in every test performed under experimental conditions, although the team admits that it would be unrealistic to expect such a high level of accuracy in large studies. future more closely resembling real-world conditions.
The team believes the technique could also be used in medical applications, particularly in cancer screening. Although Olivo and his team have yet to test whether the technique can successfully distinguish the texture of a tumor from the surrounding healthy breast tissue, he is excited by its ability to detect very subtle tumors. small that might have previously gone undetected behind the patient’s chest. .
“I’d love to do it someday,” he added. “If we get the same access rate for detecting textures in tumors, the potential for early diagnosis is huge.”
But the human body is a significantly more difficult environment to scan than static, air-filled objects like handbags, pointed out Kevin Wells, an associate professor at the University of Surrey who was not involved in the study. In addition, the researchers will need to reduce the size of the cumbersome device and ensure the cost of screening is comparable to existing techniques before it can be considered a potential screening method for humans.
“What’s presented here looks extremely promising. I think it has great potential for some types of threat detection and detection of cracks,” he said.
“For medical applications, cancer type, that’s a possibility, but there are a number of steps that must be taken before you can demonstrate efficacy in a clinical setting.”
