Any technology that can help us fighting cancer better is a great achievement. That’s precisely what a research team made of engineers and doctors from the University of Central Florida (UCF) developed. Namely, they came up with a new AI system, designed to spot undetected tumors in lung cancer patients.
According to the researchers involved in this project, the Artificial Intelligence developed by the UCF has a 95% accuracy rate in spotting small tumors in CT scans, which is significantly higher in comparison with the only 65% accuracy of human radiologists.
“We used the brain as a model to create our [AI system]. 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,” explained Rodney LaLonde, one of the researchers involved in the project.
New AI system designed to detect tumors in cancer patients, developed with facial-recognition algorithms like those on iPhone X
Researchers at the UCF Computer Vision Research Center, along with Rodney LaLonde and Engineering Assistant Professor Ulas Bagci, took parts of the famous facial recognition algorithms, such as the one on iPhone X, which are specifically designed to match faces by scanning for particular patterns. Teaming up with the National Institute of Health and the Mayo Clinic, the UCF scientists taught their new AI system about tumor size and shape, as well as other particular traits, using thousands of CT scans of cancer patients.
“I believe this [AI system] will have a very big impact. Lung cancer is the number one cancer killer in the United States, and if detected in late stages, the survival rate is only 17 percent. By finding ways to help identify earlier, I think we can help increase survival rates,” explained Engineering Assistant Professor Ulas Bagci.
In conclusion, researchers at the UCF developed a new AI system to spot undetected tumors in cancer patients, a technological breakthrough that indeed can benefit hundreds of thousands of people with lung cancer.