Picture of radiographer dictating while reading a radiograph

Diagnostic Reading #19: Five “Must Read” Articles on HIT and Radiology

Artificial intelligence in radiology leads this week’s news.

This week’s Diagnostic Reading articles include: AI algorithms show promise in performing medical work; many radiologists prefer two monitors or more; AI’s most important application in radiology might be visualizing features on images that reflect genomic or diagnostic properties radiologists don’t see today; radiology residency is changing; and FDA warns natural health company about making marketing claims for a breast thermography system it has not approved.

AI in medicine: rise of the machines – ForbesPicture of radiographer dictating while reading a radiograph

A radiologist-authored blog discusses how new “deep learning” artificial intelligence (AI) algorithms are showing promise in performing medical work that was believed to only be capable of being done by physicians. For example, deep learning algorithms have been able to diagnose the presence or absence of tuberculosis in chest X-ray images with 96% accuracy.

Radiologist survey shows age-related preferences in workstation setup – Health Imaging

A survey of 336 radiologists showed a close split in the number of radiologists using one or two non-diagnostic monitors—46 percent vs. 51 percent, respectively—while a strong majority, 75 percent, use two diagnostic monitors. In addition, the authors found that more senior radiologists tended to find their current setup user-friendly more frequently than did younger radiologists, while the latter were more likely to believe additional monitors would help.

How will AI affect radiology? – Auntminnie

While the potential for AI to replace radiologists has received much attention, AI’s most important application in radiology will be visualizing features on images that reflect genomic or diagnostic properties that radiologists don’t see today. Dr. Bradley Erickson, PhD, of the Mayo Clinic (Rochester, Minn.) said researchers are showing that deep learning can predict genomic markers with high accuracy from routine CT and MR images, even when humans have seen little or nothing that reflects these properties. He notes that this is an area where increased attention needs to be focused.

Radiology residency: how it’s changing – Diagnostic Imaging

Radiology residency has a new look. One of the most significant changes is the elimination of the oral board certification exam conducted during the fourth year of residency. Instead today’s residents take a multiple-choice core exam at the end of their third year. Some in the industry feel the change has made the test easier, but many industry leaders contend it makes the final two years of residency stronger. Now residents spend their third year studying and mastering content—which leaves the fourth year open for targeted, sub-specialty learning that makes them more attractive to potential employers.

FDA hits firm with thermography warning letter – Auntminnie

A California provider of natural health products has been hit with a warning letter from the FDA for a variety of alleged infractions, including using marketing claims for a breast thermography system that the FDA said has not been approved by the agency.

Check back next Friday for a new issue of Diagnostic Reading. #healthIT  #radiology

 

POST A COMMENT