Much ground has been made in educating the general public, as well as clinicians on how breast density is tied to higher breast cancer risk, and one group has been beating the drum for over a dozen years now.
DenseBreast-info.org (DBI) is an educational resource that aims to educate patients and clinicians, including those in radiology, about breast density. This includes providing resources for both groups and updating people about insurance coverage laws for supplemental imaging needed for women with dense breasts.
DBI co-founders JoAnn Pushkin and Wendie Berg, MD, PhD, join the show to discuss the group's work, history, and forward-looking initiatives. Berg, a previous MinnieCast guest, is a breast radiologist with the University of Pittsburgh School of Medicine and Magee-Womens Hospital of UPMC.
JoAnn Pushkin and Wendie Berg, MD, PhD, discuss how public knowledge of breast density has grown over the past decade.
The two discuss DBI's work in supporting efforts such as the introduction of the Find It Early Act, which would require all health insurance plans to cover screening and diagnostic breast imaging with no out-of-pocket costs for women with dense breasts or at higher risk.
DBI has also supported the addition of breast density notification laws and state insurance coverage laws, as well as led the creation of World Dense Breast Day for the National Day Calendar.
Pushkin and Berg also discuss imaging techniques and guidelines for women to follow when they receive notification for their breast density.
Watch the full video below.
![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)









