Breast imaging software developer Volpara Solutions is highlighting multiple scientific studies using its technology that were presented at ECR 2016 last week.
The company said that six posters and two oral presentations involved the use of its Volpara automated breast density and quantitative breast imaging software tools.
In one oral presentation, researchers from Institut Gustave Roussy in Paris used VolparaDensity and visual assessment by radiologists to track changes in breast density in 50 women who were positive for the BRCA gene and were scheduled for oophorectomy surgery to reduce their cancer risk. The study found a significant decline in volumetric density after the surgery, with a larger degree of change in younger patients.
In a poster presentation, U.S. researchers evaluated whether the cutoffs used by VolparaDensity to assign automated BI-RADS density categories needed to be updated to reflect changes made to the fifth edition of the BI-RADS lexicon. Readers found an agreement of 75% between grades made by the fourth edition of the Volpara software and assessments by radiologists using updated definitions.
In another study, Dutch researchers used VolparaAnalytics to examine whether different breast compression protocols affected applied force, pressure, and breast contact area. The findings showed that a protocol guided by pressure using a compression paddle with a real-time pressure indicator resulted in less force and pressure, as well as more consistency between patients.
Other Volpara studies at ECR 2016 covered a new algorithm for automatically assessing four breast positioning metrics from digital mammograms, the potential to use big-data analytics to reduce radiation dose with Volpara's quantitative tools, and the impact of mammography quality control on breast density.
![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)









