AI to improve reading of 3D mammograms

Population-Based Evaluation of Artificial Intelligence for Mammography Priorto Widespread Clinical Translation

NIH-funded research University of Wisconsin-Madison · NIH-11335178

This project looks at whether commercial AI tools can help doctors read 3D screening mammograms for women who get routine breast cancer screening.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionUniversity of Wisconsin-Madison NIH-funded
Lab location1 site (Madison, United States)
Project IDNIH-11335178 on NIH RePORTER

What this research studies

Researchers will compare four commercially available AI tools that interpret 3D digital breast tomosynthesis (DBT) using large, population-based screening datasets linked to cancer outcomes so the results reflect real-world practice. The team will analyze existing screening images and follow-up data rather than small, enriched case sets to determine which AI systems detect clinically important cancers and how they perform versus routine radiologist reads. The study addresses prior limits like single-institution datasets, short follow-up, and focus on 2D mammography by using diverse, population-level DBT data.

Who could benefit from this research

Good fit: Ideal candidates are women undergoing routine screening mammography, especially those who receive 3D DBT at participating screening centers.

Not a fit: Women who do not undergo routine screening mammography (for example most under age 40 or those already diagnosed and being treated for breast cancer) are unlikely to benefit directly from this screening-focused project.

Why it matters

Potential benefit: If successful, this work could lead to more accurate detection of clinically important breast cancers and fewer missed cancers or unnecessary follow-ups for women screened with DBT.

How similar studies have performed: Previous retrospective and reader studies have shown promising improvements with AI on mammography but were often small, single-center, or used enriched case sets, so population-level benefit remains unproven.

Where this research is happening

Madison, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.