While the most obvious application would be to scan for bombs and other hazardous objects and substances at airports, the findings, detailed in: nature communication today, can also help detect cracks and rust in buildings and ultimately identify tumors at an early stage.
A team of researchers from UCL has hidden small amounts of explosives, including Semtex and C4, in electrical appliances such as laptops, hair dryers and cell phones. The items were placed in bags containing toothbrushes, chargers, acetaminophen and other everyday items to accurately mimic a traveler’s bag.
While standard X-ray machines hit objects with a uniform X-ray field, the team scanned the bags using a custom X-ray security scanner that contains masks — metal plates with holes in them, which separate the rays into a series of smaller beams.
As the streams passed through the bag and its contents, they were scattered at angles as small as a microradian (about 20,000 times smaller than a degree). The scattering was analyzed by AI trained to recognize the texture of specific materials based on a particular pattern of angular changes.
The AI is exceptionally good at picking up the textures of these materials, even if they are hidden in other objects, said lead author Sandro Olivo of UCL Medical Physics & Biomedical Engineering. “Even if we hide a small amount of explosive somewhere, because there will be a little bit of texture in the middle of many other things, the algorithm will find it.”
The algorithm was able to correctly identify explosives in every experiment conducted under test conditions, although the team acknowledged that it would be unrealistic to expect such a high degree of accuracy in future larger studies that are more similar to real-world conditions.
The technique could also be used in medical applications, especially cancer screening, the team believes. While 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, for example, he is excited about the ability to detect very small tumors that could previously go undetected behind a patient’s rib cage. .
“I’d love to do it sometime,” he adds. “If we get a similar hit rate in detecting texture 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 bags, emphasizes Kevin Wells, an associate professor at the University of Surrey, who was not involved in the study. In addition, the researchers would have to downsize the bulky equipment and ensure that the screening costs are equal to existing techniques before it can be considered a potential screening method for humans.
“What’s presented here looks promising. I think it has great potential for certain types of threat detection and crack detection,” he says.
“For the medical application of the cancer type, it’s a possibility, but there are still a few steps to go before you can demonstrate efficacy in a clinical context.”