Dear Women's Imaging Insider,
Triple-negative breast cancer may comprise only 15% of breast cancers, but it's a tricky beast as it often demonstrates benign morphological features on ultrasound, according to new research from Bosnia and Herzegovina and Croatia. What exactly are those features? And what's the best course of action for radiologists? Find out.
Radiation dose to patients is always a concern, but even more so for pregnant patients as radiation exposure to the fetus may cause deterministic and/or stochastic effects. How much dose is OK? What are good clinical practices? Researchers from a Belgian hospital sought to provide some answers and conducted an internal audit. Discover their findings now.
Digital breast tomosynthesis (DBT) is gaining popularity, with good reason. A new study, led by Dr. Fiona Gilbert from the University of Cambridge in the U.K., found that adding DBT to conventional mammography boosted the specificity of breast screening and cut the recall of women with benign lesions by more than half. DBT plus mammography also showed sensitivity gains in some groups of women.
The researchers added that DBT will be helpful in the assessment clinic to improve specificity of the mammographic examination, particularly for younger women with dense breasts.
Speaking of dense breasts, did you hear about a new Dutch study? It's well-known that mammography is less effective in women with dense breast tissue, and that women with dense tissue have a three- to sixfold higher breast cancer risk than those with entirely fatty tissue. But what has not been established is which supplemental modality is best for these women. Read more here.
Also in your Women's Imaging Community, French researchers found screening mammography's benefits have been overestimated due to unconventional statistical methods, but screening advocates have been quick to stress the authors have ignored numerous publications proving the efficacy of screening. Get the story here.
As a counterpoint, a study with a 17-year follow-up found there is indeed a reduction in breast cancer mortality as a result of mammography screening in women who start getting exams at age 40 -- at least in the first 10 years of follow-up.
There's still more, much more, in your Women's Imaging Community, so head on over there to read the rest, or check below this message. As always, I enjoy hearing from you, so please keep in touch.




![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)







