Dear AuntMinnie member,
A new study reporting on how AI-powered analysis of routine whole-body MRI scans on multiple myeloma patients could help predict treatment response was our top story of the week. After analyzing body composition, a deep-learning algorithm was able to tie greater abdominal muscle and subcutaneous fat reserves at baseline to better progression-free survival. Get all of the details by clicking here.
Some practices have begun to use large language models to generate patient-friendly imaging reports, but these efforts can also cause problems. Another group developed a rubric to evaluate the quality and safety of these AI-generated reports.
AuntMinnie members were also drawn to the latest podcast from MRI safety experts Toby Gilk and Josh Posh. Episode 3 of Season 3 of The Invisible Force focuses on deficiencies in MRI safety practices and corrective action plans.
We’ve also got a new Women’s Imaging MinnieCast for you. In episode 17, Associate Editor Amerigo Allegretto spoke with Meghana Konanur, MD, about the promise of cryoablation in breast care.
Please see below for our other top stories of the week.
Erik L. Ridley
Editor in Chief
AuntMinnie.com
1. MRI-based model shows changes over time in multiple myeloma patients
2. Rubric safeguards patient-friendly AI-generated imaging reports
3. Podcast: MRI safety experts shed light on wishy-washy leadership
4. Women’s Imaging MinnieCast, episode 17: Cryoablation promising for breast care
5. Ketamine offers better sedation option than fentanyl in IR
6. Radical radiotherapy use rising for treating lung cancer
7. MRI reveals brain patterns as music reduces stress
8. Super-resolution CEUS shows promise in Crohn’s disease assessment
9. AI model on par with experts in finding femoral-neck fracture
10. Thyroid nodule classification systems provide diagnostic equity
