Monday, November 29 | 3:40 p.m.-3:50 p.m. | SSE12-05 | Room S102D
Women at high risk for breast cancer aren't getting screened with MRI -- in addition to mammography -- as called for by guidelines from the American Cancer Society (ACS), according to a new study to be presented in this Monday session.Lora Barke, DO, and colleagues from Invision Sally Jobe Breast Centers and Radiology Imaging Associates of Englewood, CO, will present research showing that there's a need to address structural, economic, and behavioral barriers to breast MRI screening before the effects of guidelines recommending this exam for high-risk women can be evaluated.
Barke's group evaluated breast cancer risk for 65,417 women who came to Invision Sally Jobe Breast Centers for screening between January 2008 and January 2009. The group assessed risk using the Gail model for women who reported a family history of cancer, recommending a screening MRI to those who had at least a 20% lifetime risk. The team then followed these women for a minimum of two months after they'd received the recommendation to determine if they had received a screening MRI. The follow-up period ended in March 2009.
Of the total cohort, screening MRI was recommended for 1,217 women, or 1.9% -- these women had a lifetime risk of breast cancer greater than 20%. Of these 1,217, only 176, or 14.5%, actually had the recommended MRI exam, Barke found.
MRI screening of women at high risk of breast cancer is rare, and there is an urgent need for new strategies to encourage women to follow through, 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=112&q=70&w=112)


