Personalized 3D AI to improve breast cancer screening
SCH: Robust Multimodal Longitudinal AI for Enhanced Breast Cancer Screening
This project builds AI that uses current and past 3D mammograms to help find breast cancer earlier for people getting routine screening mammograms.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Connecticut Storrs NIH-funded |
| Lab location | 1 site (Storrs-Mansfield, United States) |
| Project ID | NIH-11145896 on NIH RePORTER |
What this research studies
This work will create AI that reads 3D mammograms (digital breast tomosynthesis) and compares them with your prior images to spot changes over time. The team will train and test the AI using large collections of de-identified mammograms and related clinical information to reduce false alarms and missed cancers. The approach focuses on real-world screening scans and aims to lower radiologist workload while improving accuracy. If it works, the system could be used alongside routine screening visits to support faster, clearer follow-up decisions.
Who could benefit from this research
Good fit: People who get routine screening mammograms—especially women age 40 and older who receive 3D (DBT) imaging and have prior mammograms on file—are the ideal candidates to benefit from this work.
Not a fit: Those without 3D mammograms, without prior imaging available, men with breast conditions, or people with known advanced breast cancer are less likely to benefit from this specific screening-focused approach.
Why it matters
Potential benefit: If successful, this could help detect cancers earlier and reduce unnecessary callbacks and biopsies from false positives.
How similar studies have performed: AI tools have shown promise improving detection and reducing workload in 2D mammography, but applying multimodal, longitudinal AI to 3D DBT images is newer and less proven.
Where this research is happening
Storrs-Mansfield, United States
- University of Connecticut Storrs — Storrs-Mansfield, United States (Active)
Researchers
- Principal investigator: Nabavi, Sheida — University of Connecticut Storrs
- Study coordinator: Nabavi, Sheida
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.