AI can help humans inspect chest X-rays for COVID-19, but the technology is unfit to serve as a standalone diagnostic tool for that purpose. 

If demography is indeed destiny, U.S. healthcare is headed for a major escalation in spending on medical imaging over the next three decades. 

The National Academies of Sciences, Engineering, and Medicine have released a report estimating $100 million will be needed for each of the next 15 years to learn how exposure to low doses of radiation affect human health.

Medical experts testifying in malpractice suits for the defense tend to have higher objective indicators of erudition than peers testifying for the plaintiff. Radiologists buck this pattern.

The FDA has OK’d software for planning and guiding image-based, computer-assisted surgery of the spine.

Comparing six dual-energy CT technologies marketed by three scanner manufacturers, radiology researchers have found all models helpful in determining the chemical composition of kidney stones even at substantially reduced radiation doses.

The Internet is an acceptable source of images for training algorithms to automatically triage patients with dislocated joints and similar orthopedic emergencies. 

As FDA-approved AI software continues to proliferate in radiology—well more than 150 products to date and rising—a trio of Yale radiologists has compiled a status report focused on AI applications available to, specifically, emergency radiology.