AI-powered pathology tool to predict cancer outcomes and who will benefit from treatment
An AI-enabled Digital Pathology Platform for Multi-Cancer Diagnosis, Prognosis and Prediction of Therapeutic Benefit
['FUNDING_U01'] · EMORY UNIVERSITY · NIH-11376604
Using artificial intelligence on routine pathology slides to predict which cancer patients are likely to benefit from additional treatments and which might safely receive less therapy, especially where expensive gene tests aren't available.
Quick facts
| Phase | ['FUNDING_U01'] |
|---|---|
| Study type | Nih_funding |
| Sex | All |
| Sponsor | EMORY UNIVERSITY (nih funded) |
| Locations | 1 site (ATLANTA, UNITED STATES) |
| Trial ID | NIH-11376604 on ClinicalTrials.gov |
What this research studies
This project applies AI and computer-vision methods to standard H&E stained tumor slides to find patterns linked to how cancers behave and respond to treatment. The team trains models using large sets of labeled slides and patient outcome information from multiple cancer types (breast, prostate, lung, head and neck). The aim is a low-cost alternative to expensive gene-expression tests so doctors can better decide if a patient needs added chemotherapy or radiation or could have treatment reduced. Work is being developed at Emory and partner institutions building on prior promising digital pathology results from the investigators.
Who could benefit from this research
Good fit: Patients with breast, prostate, lung, or head and neck cancers who have available pathology (H&E) slides and are facing decisions about adjuvant chemotherapy or radiotherapy would be the most relevant candidates.
Not a fit: People without available tumor tissue or with cancer types not included in the training data, as well as patients needing immediate standard-of-care treatment, are unlikely to benefit directly from this work.
Why it matters
Potential benefit: If successful, the tool could help patients avoid unnecessary chemotherapy or radiation, reducing side effects, costs, and overtreatment.
How similar studies have performed: Prior digital pathology and pathomics work, including studies by this research team, have shown promising predictive signals but remain less established than commercial gene-expression tests.
Where this research is happening
ATLANTA, UNITED STATES
- EMORY UNIVERSITY — ATLANTA, UNITED STATES (ACTIVE)
Researchers
- Principal investigator: MADABHUSHI, ANANT — EMORY UNIVERSITY
- Study coordinator: MADABHUSHI, ANANT
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.