Volpara Health Technologies is highlighting two peer-reviewed studies published during RSNA 2023 that featured the company's technology.
One study published in Medical Physics highlighted a model and methodology for international harmonization of mammography dose estimates. The model replaces assumptions of a homogeneous breast with a more representative fibroglandular tissue distribution and shifts to the use of percentage volumetric breast density, the company said. This aligns with a clinically implemented breast composition metric.
The study used Volpara's TruDensity algorithm to provide estimates of volumetric breast density from 2D and 3D images across multiple mammography system makes and models. The dose model will be integrated into Volpara's TruRadDose algorithm. It analyzes a patient's exposure to radiation from a mammogram, with the goal of ensuring patient safety while maintaining optimal image quality.
The second study, featured in European Radiology, studied whether using Volpara Analytics software could help breast radiographers to improve their screening image quality.
Using Volpara's TruPressure and TruPGMI AI algorithms, the study found that all radiographers improved their performance, with increases in quality scores of up to 16% compared to a baseline measurement. This improved mammography quality and potentially led to better screening outcomes for patients.

![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)








