AI-powered glaucoma screening tool using fundus photos
Official title: Validation and Implementation of an Artificial Intelligence Machine-to-Machine (M2M) Model for Glaucoma Screening
Funded at University of Miami School of Medicine · NIH-11419186 · Data updated 2026-11-12
A machine-learning model analyzes fundus photos to estimate glaucoma-related nerve damage, aiming to make screening cheaper and easier for adults.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Miami School of Medicine NIH-funded |
| Lab location | 1 site (Coral Gables, United States) |
| Project start | September 30, 2024 |
| Project end | July 31, 2028 |
| Funding year | 2026 |
| Award (this year) | $613,594 |
| NIH project number | 5R01EY036593-03 |
| Project ID | NIH-11419186 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults aged 21 and older who could benefit from glaucoma screening in various care settings.
✕Less likely to help
People without glaucoma or those already under comprehensive ophthalmic care with established diagnoses may see limited additional benefit.
What this research studies
This project trains a deep learning network to turn standard fundus photos into quantitative estimates of glaucomatous damage that match measurements from specialized imaging. It focuses on creating a scalable, machine-to-machine screening approach that could be used in general clinics or telemedicine to identify people who may have glaucoma earlier. The study builds on prior findings that the DL model can align with optical coherence tomography measurements and glaucoma detection. If successful, it could streamline screening, reduce costs, and improve access to eye care for adults.
Why it matters
Potential benefit: If successful, patients could receive faster, more affordable glaucoma screening and earlier detection of damage.
How similar studies have gone: Preliminary results show high agreement between DL predictions and SDOCT measurements, supporting feasibility.
Where this research is happening
-
University of Miami School of Medicine
Coral Gables, United States Active
Researchers
- Principal investigator: Medeiros, Felipe — University of Miami School of Medicine
- Study coordinator: Medeiros, Felipe
Related research
Other NIH-funded projects on the same topics.
-
IOP and CSF Pressure in Glaucoma Risk
This grant studies how eye pressure and cerebrospinal fluid pressure together influence glaucoma risk and vision loss.
-
Comparing tube positions in glaucoma implants to protect corneal cells
This trial compares two tube placements for glaucoma drainage implants to see which better protects corneal cells and controls eye pressure in people with uncontrolled glaucoma.
-
Automated topographic test for glaucoma detection and progression
A new automated method uses topographic structure-function mapping to help diagnose glaucoma earlier and track its progression in patients.
-
Using AI on eye scans and genes to predict glaucoma risk
This project uses artificial intelligence on eye scans, vision tests, and genetic information to find people most likely to develop or have worsening glaucoma.
-
AI-based glaucoma screening in community health centers
A new, easy-to-use AI screening approach will be tested in federally funded health centers to help identify people at risk for glaucoma, especially in communities with higher risk.
-
Understanding how glaucoma genes control eye cell function
A long-term research project will study how genetic factors affect eye cells in adults with glaucoma to uncover new ideas for protecting vision.
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.