Dear AuntMinnie Member,
Large language models such as OpenAI’s ChatGPT and Google’s Gemini are vulnerable to cybersecurity threats, an international team recently noted. Thus, the group has offered a report that lays out security measures needed to prevent them from being used maliciously in the healthcare system. Click here for more details.
In other AI research, a group in South Korea recently validated a commercially available generative AI model that may reduce reading times and increase chest x-ray reporting accuracy. Similarly, a team from Brigham & Women’s Hospital in Boston developed a generative AI model that achieved high diagnostic accuracy and showed clinical value in preliminary reporting of chest x-ray images
In still more AI work, researchers suggested that convolutional neural network algorithms may be useful for identifying gastrointestinal obstructions on pediatric x-rays.
A large part of our digital x-ray coverage recently focused on a SpaceX mission that included the first x-ray taken in space. Here are the stories, which include interviews with key players on the mission:
- Part I: What will we learn from x-rays in space?
- Part II: ‘Spectral x-ray’ technology key in space mission
- Part III: From space to the world’s deepest mine
In addition, we posted a story about dynamic chest radiography, with the emerging technology showing potential as a tool to investigate lung health in people with cystic fibrosis.
Finally, we featured research published in JAMA Network Open suggesting that three screening tools recommended by the U.S. Preventive Services Task Force are suboptimal for identifying women who may be at risk for osteoporosis.
For more x-ray news, be sure to check in regularly with our Digital X-Ray content area. And as always, if you have x-ray topics you'd like us to consider, please contact me.
Will Morton
Editor
AuntMinnie.com
