AI that reads microscope tissue images and molecular tests
Multimodal and Generative AI for Pathology
This project builds AI tools that read microscope tissue images alongside molecular test data to help doctors diagnose cancers and other diseases more accurately.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Broad Institute, INC. NIH-funded |
| Lab location | 1 site (Cambridge, United States) |
| Project ID | NIH-11090762 on NIH RePORTER |
What this research studies
If you or a loved one has a biopsy or tissue sample, this project builds computer programs that learn from microscope images and molecular test results to give clearer information about disease. The team trains advanced AI (deep learning and generative models) to reduce variability between human pathologists and to combine tissue appearance with genetics or other molecular data. They use self-supervised and multimodal methods so the AI can learn from large amounts of data without needing every image to be hand-labeled. The tools will be shared as research software so hospitals and labs can try them.
Who could benefit from this research
Good fit: People who would most likely benefit are patients who need tissue biopsies for cancer diagnosis, transplant monitoring, or other conditions evaluated by pathology.
Not a fit: Patients without tissue biopsies or whose care doesn't rely on histopathology or molecular testing are unlikely to benefit directly.
Why it matters
Potential benefit: If successful, these tools could make pathology diagnoses more consistent and help guide more personalized treatment choices.
How similar studies have performed: Previous AI studies have shown promise in reading pathology slides, but combining images with multi-omics data and generative, self-supervised methods is a newer approach.
Where this research is happening
Cambridge, United States
- Broad Institute, INC. — Cambridge, United States (Active)
Researchers
- Principal investigator: Mahmood, Faisal — Broad Institute, INC.
- Study coordinator: Mahmood, Faisal
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.