Researchers at the University of Central Florida in the US have taught a computer to detect tiny lung cancer spots in computed tomography (CT) scans, which are often difficult to identify for radiologists.
The Artificial Intelligence (AI) system is about 95 percent accurate, compared to 65 percent when done by human eyes, the team said.
"We used the brain as a model to build our system," said one of the researchers, Rodney LaLonde, in a statement from the university.
The approach is similar to the algorithms used by the face recognition software. It scans thousands of faces looking for a specific pattern to find a match.
The group fed more than 1
"I believe this will have a very big impact," Assistant Professor Ulas Bagci said.
"Lung cancer is the largest cancer killer in the US and when it is discovered late stages, the survival rate is only 17 percent." By finding ways to help earlier, we can help to increase the survival rate, "added Bagci ,
The next step is to move the research project to a hospital. After that, the technology could be a year or two off the market, said Bagci
gb / sed
(This story was not edited by Business Standard staff members and is automatically generated from a shared feed.)