Dear AuntMinnie Member,
This week comes more confirmation of the connection between hormone replacement therapy (HRT) and breast cancer, according to a new study published on Wednesday in the Journal of the American Medical Association.
The link between the two was established in 2002, but at the time it was believed that cancers related to HRT were less aggressive. That may not be the case, according to this week's study: Women on HRT tended to have more advanced breast cancer and were more likely to die from it than women in a control group.
The researchers believe that theirs is the first research to show higher death rates among women on HRT. Get the rest of the story by clicking here, or visit our Women's Imaging Digital Community at women.auntminnie.com.
Study validates remote VC
In other news, researchers from the University of Arizona in Tucson this week are reporting on their work in setting up a teleradiology service to perform virtual colonoscopy studies at remote health centers that serve Native American populations.
Native Americans are seeing rising incidence of colorectal cancer, but have screening compliance rates that are lower than the general U.S. population. Optical colonoscopy can be difficult to offer due to its requirement to have a gastroenterologist either onsite or within reasonable traveling distance.
Instead, the U of A researchers trained radiologic technologists at the local health centers to perform VC studies, which were transmitted to university radiologists for interpretation. Find out how well the service performed by clicking here, or visit our Virtual Colonoscopy Digital Community at vc.auntminnie.com.



![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=100&q=70&w=100)



![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)







