Dear Women's Imaging Insider,
We have plenty of stories to enlighten, entertain, and inform you at the Women's Imaging Digital Community.
Breast implants are becoming increasingly popular, and following the recent Poly Implant Prosthèse (PIP) scandal, it's essential for radiologists to be able to spot a complication. But first they need to know what's normal. Read the tips French researchers gave to delegates at the recent French radiology congress in Paris.
Predicting the likelihood of malignancy in a woman who presents with an adnexal lesion is of vital importance. Such predictions directly affect patient management, including the therapeutic approach and surgical technique, Portuguese radiologists told attendees at the recent European Society for Magnetic Resonance in Medicine and Biology congress in Lisbon. Get the story here.
Computer-aided detection (CAD) is helpful for detecting microcalcifications and masses, but what happens when the CAD marks are hidden? How does this affect a radiologist's ability to detect malignant masses? Find out in this study from Dutch researchers.
Other stories in your Women's Imaging Digital Community include:
- Research from Sweden on how best to read breast tomosynthesis images. Is it horizontally? Vertically? Slow frame rates? Click here to learn more.
- Findings from an independent U.K. panel on breast screening; whether it extends lives, whether the benefits outweigh the harms, and what about the prevalence of overdiagnosis?
- A study on ultrasharp 3D breast images with a technique that delivers less radiation than a mammogram.
Please do check out all our articles and, as usual, drop me a line if you have any questions, comments, or concerns.
November, of course, brings about the whirlwind of the RSNA congress, which your AuntMinnieEurope.com team will be attending. Check out our sister site's Road to RSNA section next week at radcast.auntminnie.com for a preview of women's imaging presentations at the Chicago meeting.
I look forward to seeing you at RSNA 2012!




![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.auntminnieeurope.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.auntminnieeurope.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)







