NPR

For Some Hard-To-Find Tumors, Doctors See Promise In Artificial Intelligence

Scientists are training computers to read CT scans and in the hopes they could catch pancreatic cancer early.
A team at Johns Hopkins Medicine in Baltimore is developing a tumor-detecting algorithm for detecting pancreatic cancer. But first, they have to train computers to distinguish between organs.

Artificial intelligence, which is bringing us everything from self-driving cars to personalized ads on the web, is also invading the world of medicine.

In radiology, this technology is increasingly helping doctors in their jobs. A computer program that assists doctors in diagnosing strokes garnered approval from the U.S. Food and Drug Administration earlier this year. Another that helps doctors diagnose broken wrists in x-ray images won FDA approval on May 24th.

One particularly intriguing line of research seeks to train computers to diagnose one of the deadliest of all malignancies, pancreatic cancer, when the disease is still readily treatable.

That's the vision of , a professor of radiology at Johns Hopkins Medicine in Baltimore.

You’re reading a preview, subscribe to read more.

More from NPR

NPR3 min readAmerican Government
In W. Va. Primary, Establishment Candidates For Governor Highlight Culture War Issues
Several Republicans with deep ties to state politics vye in the primary to face the Democrat in November
NPR3 min read
Justice Thomas Decries 'Nastiness' And 'Lies' Against Him
The Supreme Court justice told attendees at a judicial conference that he and his wife have faced "nastiness" and "lies" over the last several years and decried Washington as a "hideous place."
NPR4 min readWorld
In Gaza, A Hidden Threat Could Kill Palestinians Even After A Cease-fire
The United Nations says 7,500 metric tons of unexploded ordnance litter the Gaza Strip. The U.N. says it could take 14 years to dispose of these dangers.

Related Books & Audiobooks