Breast imaging software developer Volpara Solutions is highlighting a study published online May 11 in the Journal of Breast Imaging that combined the company's VolparaDensity software with a breast density risk calculator to improve breast cancer risk stratification.
The group, led by senior author Dr. Jennifer Harvey from the University of Virginia, used the Tyrer-Cuzick evaluation tool to calculate breast density risk for 474 women diagnosed with invasive breast cancer. The tool relies on volumetric breast density measurements acquired using VolparaDensity software, among other sources.
The researchers discovered that the addition of breast density measures to traditional risk factors improved patient risk stratification and helped correctly categorize more women at high and low risk of breast cancer than standard methods alone. They concluded that breast density measurements from software such as VolparaDensity could facilitate risk-adapted breast cancer screening and prevention strategies.
"Breast density is a strong risk factor for breast cancer, and ... contributes as much information as all other factors combined, nearly doubling the predictive value of the risk model," co-author Jack Cuzick, PhD, from the Wolfson Institute of Preventive Medicine in the U.K. said in a statement from Volpara. "Screening programs need to take this into consideration in order to develop a personalized breast care plan for each woman."











![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)






