Researchers at the University of Florida have developed a new AI system that can detect tiny specks of lung cancer in CT scans, which radiologists often have a difficult time identifying. The team said that the artificial intelligence system is about 95% accurate, compared to 65% when done by human eyes. “We used the brain as a model to create our system. Similar to the connections between neurons in the brain strengthen during development and learn, we used the same idea in developing a new system that can understand how to look for patterns in the CT scans and teach itself how to find these tiny tumors," Phys.org website cited Rodney LaLonde as saying. According to the German News Agency, the approach is similar to the algorithms that facial-recognition software uses, as it scans thousands of faces looking for a particular pattern to find its match. The group fed more than 1,000 CT scans provided by the National Institutes of Health through a collaboration with the Mayo Clinic, into the software they developed to help the computer learn to look for the tumors. LaLonde taught the computer how to ignore other tissue, nerves and other masses it encountered in the CT scans. Researcher Ulas Bagci says: “I believe this will have a very big impact,” as“lung cancer is the number one cancer killer in the United States and if detected in late stages, the survival rate is only 17%. By finding ways to help identify earlier, I think we can help increase survival rates.”