
Women with dense breast tissue want adjunct screening that is sensitive and inexpensive -- although higher sensitivity might outweigh cost, according to a study published February 28 in the Journal of Breast Imaging.
A team led by Dr. Matthew Miller, PhD, of the University of Virginia in Charlottesville conducted a survey of 508 patients with dense breast tissue presenting for screening mammography. The survey asked participants to do the following:
- Estimate their personal breast cancer risk compared with their peers
- Indicate their level of concern related to recalls, radiation exposure, and intravenous contrast allergies
- List factors that might prevent them from getting supplemental screening exams
Of survey participants, 59.9% believed it was likely or very likely that a cancer could be missed on a mammogram, but only 8.9% had undergone supplemental screening in the past three years. The most common deterrents to additional screening were pain (66.9%) and anxiety that supplemental screening would lead to additional procedures (31.1%).
Survey participants were asked to select among three hypothetical adjunct breast cancer screening modalities -- breast MRI, contrast-enhanced spectral mammography (CESM), and automated breast ultrasound (ABUS) -- and they strongly preferred whichever exam was most sensitive, even if this meant higher cost (31.9%) or administration of IV contrast (62%).
"Our data suggest that patients with dense breasts prefer adjunct screening exams that are both sensitive and inexpensive, although an increase in sensitivity could outweigh additional cost or even IV-line placement," the team 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)










