Dear Women's Imaging Insider,
We've got the au courant news in breast imaging in this installment of the Women's Imaging Insider.
First, Dr. Wendie Berg, Ph.D., presents the latest results from the American College of Radiology Imaging Network (ACRIN) 6666 trial. Specifically, researchers put the ultrasound interpretation skills of 35 breast experts to the test and came up with some rather surprising results. To read more, click here.
A second breast ultrasound feature focuses on the modality's role in women with a genetic risk of cancer. Click here to read more on this presentation at the 2004 RSNA meeting in Chicago.
If breast MR is where your interest lies, then you'll want to check out two reports from the International Breast MRI Consortium (IBMC). While one group of IBMC researchers reiterates the value of MRI over mammography for identifying tumors in high-risk women, another team finds that the modality's specificity is still too low to make it a suitable replacement for biopsy.
Or if bones are more your bag, read up on how dental x-rays might double as an osteoporosis screening tool, or whether bone marrow fat can be used to judge bone mineral density.
For those of you who specialize in gynecologic imaging, we have an article on gel-enhanced MR for cervical cancer staging, as well as a patterns-of-care study on cervical cancer treatment.
Last but not least, I'd like to thank you for supporting the Women's Imaging Digital Community, and wish you all the best in 2005.















![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)


