
Asian American women face significant barriers to breast cancer screening, with notable differences by ethnicity and recent immigration status, according to research published June 23 in the Journal of the American College of Radiology.
A team led by Young-Jin Sohn from New York University found that although women of Asian ancestry have traditionally been considered low risk for adverse breast cancer-specific outcomes, aggregated data may mask health disparities seen among subgroups.
The U.S. Asian population increased 72% over the past two decades, making it the fastest growth rate of any major racial group. There are over 20 million Asian and Asian American women in the U.S. who identify with at least one of 19 different origin groups.
While U.S. Asian women have a lower breast cancer incidence rate than non-Hispanic white women, heterogeneity exists among this population. For example, a previous study showed a three-fold difference in breast cancer incidence rates among Asian subgroups in the U.S., ranging from 36.9 per 100,000 Laotian women to 126.5 per 100,000 Japanese women.
Better understanding of barriers to breast cancer prevention and treatment efforts is needed to develop more effective strategies aimed at reducing disparities in care among different origin groups within the U.S. Asian population, Sohn and colleagues 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)









