Combining mammogram AI, genetics, and health information to personalize breast cancer screening by subtype
Project 3: Integration of mammographic AI, clinical, and genomics information to improve breast cancer subtype- specific risk-based screening and prevention
This project combines mammogram AI, genetic testing, and health records to better predict different types of breast cancer and tailor screening for each person.
Quick facts
| Grant type | P01 program project |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of California, San Francisco NIH-funded |
| Lab location | 1 site (San Francisco, United States) |
| Project ID | NIH-11191531 on NIH RePORTER |
What this research studies
As a patient who gets screening mammograms, this work aims to use computer analysis of my mammograms together with genetic results and clinical information to understand my risk for specific breast cancer subtypes. The team will train deep-learning AI on mammogram images, add germline genetic risk scores from GWAS, and include clinical factors like age and family history. The new risk model will be integrated into the ongoing WISDOM screening program so risk-based screening plans can reflect subtype-specific chances of fast- or slow-growing cancers. Data will come from existing WISDOM participants and linked medical records, with models validated against known cancer outcomes.
Who could benefit from this research
Good fit: Ideal candidates are people who receive routine mammograms and are eligible for or enrolled in the WISDOM program and who can share their mammogram images, genetic data, and health history.
Not a fit: People without access to mammography or genetic testing, those outside the study catchment or unwilling to share records, and those with very rare hereditary syndromes not represented in the data may not benefit.
Why it matters
Potential benefit: If successful, the approach could catch aggressive cancers earlier for those at highest risk and reduce unnecessary tests for those at low risk.
How similar studies have performed: Separate studies have shown promise for mammogram-based AI and for genetic risk scores, but combining them for subtype-specific, risk-based screening is relatively new.
Where this research is happening
San Francisco, United States
- University of California, San Francisco — San Francisco, United States (Active)
Researchers
- Principal investigator: Arasu, Vignesh a — University of California, San Francisco
- Study coordinator: Arasu, Vignesh a
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.