AI screening that detects glaucoma across diverse populations
Official title: Developing Population-Generalizable Deep Learning Models for Automated Glaucoma Screening
Funded at Schepens Eye Research Institute · NIH-11184318 · Data updated 2026-11-12
This project builds AI that reads retinal photos and OCT scans to find glaucoma early for people from different racial and ethnic backgrounds.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Schepens Eye Research Institute NIH-funded |
| Lab location | 1 site (Boston, United States) |
| Project start | September 30, 2024 |
| Project end | July 31, 2029 |
| Funding year | 2025 |
| Award (this year) | $580,542 |
| NIH project number | 5R01EY036222-02 |
| Project ID | NIH-11184318 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates would be adults who can have retinal photos or OCT scans taken during routine eye care or screening visits, especially individuals from underrepresented racial or ethnic groups.
✕Less likely to help
People without access to retinal imaging, those whose disease cannot be detected by fundus/OCT imaging, or patients already diagnosed and stably treated for glaucoma may not get direct benefit from participation.
What this research studies
You would have routine retinal photos and optical coherence tomography (OCT) scans analyzed by an AI program designed to work well across groups such as Asian, Black, and other populations. The team will train models using images labeled by clinical guidelines and compare their new methods to standard approaches like oversampling and transfer learning. They will also create new performance measures that penalize models that do well on some groups but poorly on others, aiming for consistent results across populations. The work is done at Schepens Eye Research Institute with partner datasets and clinics to include a broad range of patients.
Why it matters
Potential benefit: If successful, this could enable low-cost, widely available glaucoma screening in primary care and pharmacies that catches disease earlier and reduces preventable vision loss.
How similar studies have gone: Previous AI work has shown promise detecting glaucoma from retinal images but often performs worse when moved to different populations, so this project focuses on improving that real-world consistency.
Where this research is happening
-
Schepens Eye Research Institute
Boston, United States Active
Researchers
- Principal investigator: Wang, Mengyu — Schepens Eye Research Institute
- Study coordinator: Wang, Mengyu
Related research
Other NIH-funded projects on the same topics.
-
Population-wide deep learning glaucoma screening Models
Aims to create AI eye-screening tools that work well for diverse populations so people can get easy glaucoma checks from primary care or pharmacies.
-
Finding Glaucoma Vision Loss Early with Computer Learning
This project uses advanced computer learning to help doctors find vision changes in glaucoma patients sooner, especially for veterans.
-
Using deep learning to detect and predict glaucoma progression from eye scans
This study is looking at how we can better spot and track primary open angle glaucoma using advanced computer technology, so that patients can get the help they need sooner and manage their condition more effectively.
-
Creating fair AI models for glaucoma screening
This study is working on using smart computer technology to help find glaucoma early, especially for people from different backgrounds who might not have easy access to eye care, so that everyone can get the right diagnosis without needing expensive specialist visits.
-
IOP and CSF Pressure in Glaucoma Risk
This grant studies how eye pressure and cerebrospinal fluid pressure together influence glaucoma risk and vision loss.
-
Integrative histo-genomic analysis to guide cancer risk and targeted therapies with interpretable AI
Researchers are developing an advanced AI-powered approach to map genetic and cellular patterns across breast and cervical cancers to help tailor treatments.
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.