Dear Women's Imaging Insider,
There's an intrinsic challenge to mammography: How do you image a 3D structure with 2D technology? Researchers have been seeking a solution to this challenge for years, and with the advent of breast tomosynthesis -- which produces a volumetric dataset, a sequence of 2D slices that represents an entire volume -- they may be getting closer.
But perhaps there is an even simpler solution. Dr. Carl D'Orsi and Dr. Mary Newell, both at Emory University Hospital's Breast Imaging Center in Atlanta, and partner BBN Technologies of Cambridge, MA, have been working to develop a stereo mammography device that takes advantage of the natural human capacity to fuse multiple 2D images into one 3D image. This month's Women's Imaging Insider brings you more information about this device, as well as results from a clinical trial that point to a reduction in false positives. Click here to read more. As a Women's Imaging Insider, you have access to the article well before the rest of our members.
As for other news in the Women's Imaging Digital Community, read what researchers have to say about why the craniocaudal view on mammography is important for breast cancer risk assessment. Find out how US-guided core-needle breast biopsy offers an alternative to surgery. And check out the latest information on an easy fix for mammogram pain.
As always, if you have a comment, report, or article idea to share about any aspect of women's imaging, please feel free to contact me at [email protected].













![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)


