Better computer tools to find patterns in medical images and complex lab tests
New Statistical Methods for Medical Signals and Images
The team is creating new computer and statistical tools to find health-relevant patterns in complex medical tests like genetic data, protein profiles, and medical images to help patients and clinicians.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Stanford University NIH-funded |
| Lab location | 1 site (Stanford, United States) |
| Project ID | NIH-11177871 on NIH RePORTER |
What this research studies
Researchers are building statistical and algorithmic methods that can tease apart subtle signals when tests produce many linked measurements, such as gene expression, mass spectrometry, or genome-wide data. One method groups related features before selecting signals (a cluster-aware lasso) and another focuses on picking genetic markers from summary GWAS results while controlling false discoveries. The tools will be validated on existing gene-expression, mass-spec, and GWAS datasets. The goal is to make analysis of high-dimensional medical data more reliable so findings can better inform future diagnostics and treatments.
Who could benefit from this research
Good fit: Ideal candidates are people who can contribute existing genomic, gene-expression, mass-spectrometry, or related de-identified clinical test data for analysis.
Not a fit: Patients without genomic, molecular, or advanced imaging test data, or those whose care does not involve high-dimensional laboratory tests, are unlikely to see direct benefit.
Why it matters
Potential benefit: If successful, these methods could help doctors and researchers identify clearer signals from complex tests, accelerating discovery of improved diagnostics and treatments.
How similar studies have performed: Foundational tools like the lasso and FDR control are widely used successfully, but the specific cluster-aware and GWAS-summary extensions here are newer and less tested at scale.
Where this research is happening
Stanford, United States
- Stanford University — Stanford, United States (Active)
Researchers
- Principal investigator: Johnstone, Iain M — Stanford University
- Study coordinator: Johnstone, Iain M
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.