Dear Women's Imaging Insider,
The question of whether radiologists should read a particular number of mammograms each year to optimize their performance has remained open to debate. But in the study we're highlighting in this month's Women's Imaging Insider, a group of Norwegian researchers say they've found the best range. Find out what they suggest.
After you've read our featured story, take a look at what else is going on in the Women's Imaging Community:
- How can your department cut mammography reading time for contrast-enhanced studies? It may be as simple as reversing the typical hanging protocol.
- Check out our coverage of the Danish breast cancer screening scandal.
- Read what Prof. Christiane Kuhl, head of radiology at Aachen University Hospital in Germany, had to say at the International Society for Magnetic Resonance in Medicine annual meeting in Montreal about personalized breast cancer screening.
- Discover how researchers from France used 3D MRI to visualize changes to the shape of the fetal brain and skull during the second stage of labor.
- Find out why Norwegian researchers say that digital breast tomosynthesis alone is safe for population-based screening.
If you have a comment or report to share about any aspect of women's imaging, I invite you to contact me.




![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)







