Dear Women's Imaging Insider,
It's well known that Black women are more likely than their white peers to die from breast cancer, and a new study in Cancer suggests that comorbidities may be one of the many reasons behind this statistic.
The retrospective study found that Black women had higher rates of hypertension, high cholesterol, and diabetes at breast cancer diagnosis. This held true even after the authors adjusted for age and body mass index score. Read more in this edition's Insider Exclusive.
Also new in the Women's Imaging Community, two nomograms showed promise for predicting axillary lymph node metastasis and disease-free survival among women with early-stage breast cancer. The nomograms utilized "signatures" derived from MRI radiomics and patient clinical risk characteristics.
In 2020 it's impossible to write a newsletter without mentioning the COVID-19 pandemic. Just last week, the pandemic prompted the U.S. Food and Drug Administration (FDA) to relax some of the regulatory requirements for breast imaging facilities under the Mammography Quality Standards Act.
The FDA's change is one of many that breast imaging facilities have experienced this year. It's a reflection of the intense disruption that has resulted in thousands of missed mammograms, which may be impossible to make up, according to some research.
The 2020 RSNA meeting took place virtually last week, and women's imaging research was definitely a highlight.
One of my favorite presentations was on an algorithm that outperformed the Tyrer-Cuzick risk assessment model for assessing short-term breast cancer risk. The team behind the algorithm believes it could be picking up on unique biomarkers from mammograms.
The following presentations may also be of interest:
- Breast MRI for surgical planning and breast cancer screening
- Artificial intelligence for identifying interval breast cancers
- Contrast-enhanced spectral mammography and its role in diagnostic imaging
As the year draws to a close, I'd like to wish you a wonderful and safe holiday season as well as a very happy new year. I'm already counting down to 2021 -- a year with (hopefully) fewer COVID-19 stories in the newsletters.


















![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)
