Tuesday, December 3 | 3:00 p.m.-3:10 p.m. | SSJ01-01 | Arie Crown Theater
Women want to know their breast density and have access to supplemental tests if their tissue is dense, whether they are patients at county hospitals or outpatient radiology clinics, according to research to be presented in this Tuesday afternoon session.Dr. Jafi Lipson, from Stanford University Medical Center, and colleagues gave a nine-question survey to 132 women at a county hospital, prior to the women's mammogram appointments. The surveys were available in English, Spanish, and Vietnamese.
Participants were asked if they were aware of their breast density, they were informed about the decreased sensitivity of mammography in dense breast tissue, and they were asked whether they were willing to pay for additional testing if they had dense tissue. A similar survey was conducted at an academic hospital outpatient radiology clinic.
At the county hospital, 5% of women knew their breast density status, compared with 24% of women at the outpatient clinic. Seventy-nine percent of women at the county hospital wanted to know their breast density and were interested in additional screening tests, despite high false-positive rates. Seventy-three percent were interested in whole-breast ultrasound, but only 28% were will to pay out of pocket for the test, compared with 73% of women at the outpatient clinic.
The discrepancy could lead to inequity in healthcare if supplemental tests for women with dense breast tissue are not covered by insurance, Lipson's 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=112&q=70&w=112)






