Usually a CT scanner takes many X-ray images from different angles and assembles a 3D picture. But sometimes doctors only scan a small area (say, one lung) and the data cuts off. It's like a chef given a single spoonful of soup and asked to name the exact recipe for the entire pot.
The new algorithm tackles this differently: it doesn't invent what's missing, but acts like a chef who starts with a rough recipe, adds ingredients, tastes, compares with the reference flavor of that original spoonful, and repeats until it matches. Unlike old approaches where edges got blurred and neural networks painted plausible but fake details, this method preserves sharpness and sticks strictly to real measurements.
The first commercial CT scanner appeared in 1971 and took several minutes to scan a head — today's machines are hundreds of times faster.
Medical scanners from 'Star Trek' instantly see the entire body: this new method brings us closer to that dream, even with only a fraction of the data available.