University of Central Florida's computer vision research center has developed a computer that utilizes AI to detect tumors with 95% accuracy, according to the team.
Currently, humans are able to detect tumors with around 65% accuracy but using a computer to detect the often-missed tiny specks of lung cancer in CT scans radiologists will be able to improve detection levels.
"We used the brain as a model to create our system," said Rodney LaLonde, a doctoral candidate working on the project. "You know how connections between neurons in the brain strengthen during development and learn? We used that blueprint, if you will, to help our system understand how to look for patterns in the CT scans and teach itself how to find these tiny tumors."
Visit Innovation Enterprise's Big Data & Machine Learning for Pharma Summit Europe 2018 in Madrid on October 10, 2018
The team has revealed that the system was fed data from more than 1,000 CT scans provided by the National Institutes of Health in order to help the software detect abnormalities in scans.
"I believe this will have a very big impact," engineering assistant professor Ulad Bagci said. "Lung cancer is the number one cancer killer in the US 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."
The next step is to move the research project into hospital clinical trials and the team are currently trying to find partners to make this happen. Bagci has predicted that, once the project is in a hospital setting, the technology could be just one or two years from being market-ready.