Numerous deep learning models can detect and classify imaging findings with a performance that rivals human radiologists. However, according to a new study published in the Journal of the American College of Radiology, many of these AI models aren’t nearly as impressive when applied to external data sets.

The U.S Food and Drug Administration gave the go-ahead for two additional molybdenum-99 filling lines at the company's Columbia, Missouri, facility.

Exams of patients who require a translator appeared to be of “significantly worse” quality, underlining the need to strengthen communication, according to new research in Abdominal Imaging. 

University College London researchers harnessed this new tool to quickly analyze cardiovascular magnetic resonance images and determine the risk of other adverse events such as stroke.

AI promises to make a titanic impact on radiology, but most of the attention tends to focus on its ability to identify important findings in medical images. What about the technology’s non-interpretive qualities?

Connecticut-based Hyperfine Research said its new point-of-care imaging tool carries a fraction of the cost and weight of a traditional magnetic resonance machine. 

Emory University recently devised a detailed process to ensure that such tests are delivered in a uniform fashion across its vast clinical enterprise.

Idaho-based International Isotopes has received U.S. Food and Drug Administration approval for its radioactive therapeutic agent used to treat thyroid cancers.