One of the more pleasant things we do at the RSNA meeting every year is conduct our annual editorial advisory board breakfast. We invite all members of the advisory board (listed below) and our columnists to a hot breakfast and a discussion about what's big, new, and important in radiology.
One of the more pleasant things we do at the RSNA meeting every year is conduct our annual editorial advisory board breakfast. We invite all members of the advisory board (listed below) and our columnists to a hot breakfast and a discussion about what's big, new, and important in radiology.
The hour is always early, 7 a.m., which prompts a bit of grousing from participants, but the discussion is always stimulating and productive. It gives our staff editors, the Diagnostic Imaging sales staff, and the editorial advisors themselves an inside look at some of the thinking that drives today's practicing radiologists.
This year, I prepared a summary of the meeting and sent it out to other advisors who were not able to attend. At this writing, I'm still getting responses.
For me and the other editors, this information is golden. We talk to radiologists all the time about specific topics, but there's nothing like a freewheeling discussion to open up new concepts and ideas. It allows us to pinpoint and refine ideas that make the magazine more relevant and topical. For those who participate, either in person or via replies to my summary, it's a chance to exchange views on important trends.
Among the observations: Pay for performance is gaining traction, radiology-specific search engines are replacing textbooks among residents, and advanced visualization is playing a bigger role in interpretation. Underlying all of these trends, the pace of change in radiology is increasing.
In the months ahead, we'll be writing about those changes and discussing their implications. Stay tuned.
John C. Hayes is editor of Diagnostic Imaging
Considering Breast- and Lesion-Level Assessments with Mammography AI: What New Research Reveals
June 27th 2025While there was a decline of AUC for mammography AI software from breast-level assessments to lesion-level evaluation, the authors of a new study, involving 1,200 women, found that AI offered over a seven percent higher AUC for lesion-level interpretation in comparison to unassisted expert readers.