While the most obvious application would be to search airports for bombs and other dangerous items and substances, the findings, described today in Nature Communications, could also help detect cracks and rust in buildings, and eventually it can be used to identify early stages tumors.
The team of researchers, from UCL in London, hid small amounts of explosives, including Semtex and C4, inside electrical items such as laptops, hairdryers and mobile phones. The items were placed in pockets with toothbrushes, chargers and other everyday objects to closely replicate a traveler’s bag.
While standard x-ray machines hit objects with a uniform field of x-rays, the team scanned the bags with a custom-made machine that contains masks—metal sheets with holes punched in them, which separate the beams into a series of smaller beams.
As the rays passed through the bag and its contents, they were scattered at angles as small as a microradian (about one 20,000th the size of a degree). The scattering was analyzed by AI trained to recognize the texture of specific materials of a specific material. pattern of angle changes.
The AI is exceptionally good at picking up this material, even when it is hidden in other objects, says lead author Sandro Olivo, from UCL’s Department of Medical Physics and Biomedical Engineering. “Even if we hide a small amount of explosives somewhere, because there will be some texture in the middle of a lot of 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 admitted that it would be unrealistic to expect such a high level of accuracy in larger studies that more closely resemble real-world conditions.
The technique can also be used in medical applications, especially cancer screening, the team believes. Although the researchers have yet to test whether the technique can successfully distinguish the texture of a tumor from, for example, surrounding healthy breast tissue, he is excited about the possibility of detecting very small tumors that could previously have gone unnoticed behind a patient’s rib cage.
“I’d love to do that one day,” 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 challenging environment to scan than static, air-filled objects like bags, says Kevin Wells, associate professor at the University of Surrey, who was not involved in the study. In addition, the researchers will need to reduce the bulky equipment and ensure that the cost is equivalent to that of existing techniques before it can be considered as a potential screening method for humans.
“What is on offer here looks extremely promising. I think it has great potential for certain types of threat detection, and detecting cracks,” he says.
“For the medical, cancer-type application, this is a possibility, but there are some steps to go before you can demonstrate efficacy in a clinical context.”