
Most breast care practices use supplemental screening in women with dense tissue, but the modalities used and the methods in which patients are referred vary widely, according to a study published online February 24 in the Journal of the American College of Radiology.
A team led by Dr. Sadia Choudhery of the Mayo Clinic in Rochester, MN, conducted a study that consisted of a 12-question survey sent to 902 American College of Radiology interpreting physicians. The survey included questions about practice features and the use of supplemental breast cancer screening in women with dense tissue. Of the total respondents, 68.4% worked in practices that offered supplemental screening.
Of supplemental screening modalities, ultrasound was the most common (53%). Ordering providers were primary referrers (56%). The group also found the following:
- Academic practices, private practices that specialized in breast care, and practices in the northeastern U.S. were more likely to provide supplemental screening.
- There were significant associations between state density notification legislation, the number of breast imaging trained radiologists in a practice, and the volume of mammograms performed per day and the availability of supplemental screening.
- Use of automated breast density assessment software and patient education material about density and supplemental screening was significantly linked with the availability of supplemental screening.
"There are practice features that correlate with the availability of supplemental screening, and understanding these features provides further insight into current trends in supplemental screening utilization," the group concluded.
![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)









