Academic journal

New AI-powered X-ray technique to detect explosives could identify cancer

“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 stuff, the algorithm will find it.”

The technique could be used in medical applications, including cancer screening, according to the research team.

Although the researchers have not yet tested whether the technique can successfully distinguish the texture of a tumor from the surrounding healthy breast tissue, they are excited about the possibility of detecting very small tumors that would not previously have been detected behind a patient’s rib cage.

“I would love to do it one day,” Olivo said. “If we achieve a similar success rate in detecting the texture of tumors, the potential for early diagnosis is huge.”

Explosives inside electronics

Explosives can be difficult to find using traditional X-ray techniques when they’re hidden inside electronics and other things. However, the researchers found that under test conditions, the new approach had a 100% accuracy rate for detecting explosives.

Small amounts of explosives, such as Semtex and C4, were concealed by the UCL team inside electrical devices such as computers, hair dryers and mobile phones to closely resemble the bag of a traveler. Products were placed in bags along with toothbrushes, chargers and other everyday items.

Sample images from the test.

The researchers used a specially built machine with masks – sheets of metal pierced with holes, which split the beams into an array of smaller beams – to scan the bags instead of using regular X-ray machines, which hit objects with a uniform field. of X-rays.