Dear Women's Imaging Insider,
Patient, radiologist, and facility characteristics can all affect how well mammograms are interpreted by radiologists. But how do technologists fit into the mix?
In a study we're highlighting in this edition of the Insider, researchers from the University of North Carolina explored this very question. They found that technologists definitely influence radiologists' performance for mammography -- get the details by clicking here.
When you've finished our Insider Exclusive, check out what else is going on in the Women's Imaging Community:
- Read what researchers from the Mayo Clinic in Rochester, MN, discovered about women's awareness of breast density as a risk factor for cancer.
- Learn how applying computer-aided detection twice to digital breast tomosynthesis exams boosts sensitivity and reduces radiation dose.
- Discover how giving women more information about the negative aspects of mammography, such as overdiagnosis, makes them less inclined to want breast screening.
- Check out what Harvard Medical School researchers found when they tracked mammography screening rates after the U.S. Preventive Services Task Force released its 2009 recommendations.
- Find out why Boston researchers believe breast density notification laws may not be helpful.
- Learn how interventional radiologists are working to make childbirth safer.
As always, if you have a comment, report, or article idea to share about any aspect of women's imaging, please 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.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)









