Dear AuntMinnie Member,
If they know what to look for, radiologists can play a key role in identifying cases of elder abuse, according to a group from Weill Cornell Medicine. Our top article for the week shares their tips when interpreting x-ray exams of fractures in elderly patients from the emergency department.
In another story in our Digital X-Ray Community, researchers reported that techniques that show how artificial intelligence algorithms arrive at their findings weren't that reliable when utilized on a database of chest x-rays.
Higher imaging costs
A new study we're spotlighting in our Imaging Leaders Community shares just how much patients are currently paying for imaging studies. Over the last two decades, medical imaging out-of-pocket costs for patients have nearly doubled, according to researchers from New Jersey.
In building relationships with patients, radiologists may find that a little humor can go a long way, according to researchers from Switzerland. Meanwhile, a troubling survey concluded that 1 in 4 clinicians are considering leaving healthcare entirely, largely due to feelings of burnout.
Cancer screening in older adults
Although most clinical guidelines suggest that older people no longer receive cancer screening exams at a certain age, knowing when to stop can be problematic. A recent study found that one-quarter of physicians believed that life expectancy wasn't a good enough reason to discontinue screening.
In other new coverage in our Women's Imaging Community, researchers reported that Black women have less access to new breast imaging technology. Also, surveillance MRI exams could detect brain metastases in women with inflammatory breast cancer.














![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)





