Retinopathy of Prematurity: Using AI to Improve How We Watch for Change in Preterm Babies' Eyes
Official title: Analyzing Retinal Microanatomy in Retinopathy of Prematurity to Improve Care
Funded at Duke University · NIH-11374353 · Data updated 2026-11-12
A Duke study is using artificial intelligence to analyze baby eye images and other retinal data to make monitoring for retinopathy of prematurity easier and less stressful for preterm infants.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Duke University NIH-funded |
| Lab location | 1 site (Durham, United States) |
| Project start | March 10, 2016 |
| Project end | May 31, 2030 |
| Funding year | 2026 |
| Award (this year) | $743,844 |
| NIH project number | 2R01EY025009-10 |
| Project ID | NIH-11374353 on NIH RePORTER |
Who could benefit from this research
✓Could help
Infants with or at risk for retinopathy of prematurity, typically born preterm and monitored during the early weeks to months after birth.
✕Less likely to help
Infants without ROP risk factors or not requiring enhanced imaging or AI-guided monitoring would not benefit from this approach.
What this research studies
This project aims to capture retinal information from preterm infants at the bedside using infrared optical coherence tomography and specialized imaging software. It will develop AI models that interpret those images to help clinicians decide when treatment is needed, with a focus on reducing stress for the infant and improving care after treatment. The approach builds on previous low-stress imaging methods and will use newer wide-field instruments to obtain richer retinal data. By translating image data into practical guidance aligned with standard care scales, the work seeks to support better, personalized follow-up and treatment decisions for ROP. The effort includes ongoing follow-up and data processing to connect imaging findings with clinical outcomes.
Why it matters
Potential benefit: If successful, this could enable faster, gentler monitoring of at-risk infants and help clinicians tailor treatment timing to preserve vision.
How similar studies have gone: Past work showed that low-stress bedside imaging and image processing can improve retinal information available to clinicians; AI-based interpretation is a logical next step.
Where this research is happening
-
Duke University
Durham, United States Active
Researchers
- Principal investigator: Toth, Cynthia Ann — Duke University
- Study coordinator: Toth, Cynthia Ann
Related research
Other NIH-funded projects on the same topics.
-
Butyrate-based approach to prevent vision loss in premature babies with retinopathy
A study is exploring whether increasing butyrate levels can prevent vision-damaging retinopathy in premature infants by addressing gut bacteria and metabolic pathways.
-
TopoROP: Multi-View Analysis to Diagnose Retinopathy of Prematurity
A new AI-based tool analyzes retinal images to help doctors diagnose Retinopathy of Prematurity in premature babies and other patients at risk.
-
Long-term endotypes of prematurity-related lung disease in former preemies
A long-term study looking at why some babies born very early develop lasting breathing problems and how their genes might explain these different paths.
-
Deep learning tool to diagnose retinopathy of prematurity in newborns
A new AI-based diagnostic tool uses eye images from premature babies to help clinicians identify treatment-needed retinopathy of prematurity.
-
Cortical dystonia in kids born early
Researchers are studying why premature birth leads to dystonia in cerebral palsy and looking for new ways to help children and adults who have this condition.
-
AI-enhanced wide-field eye scans for detecting retinopathy of prematurity
Using faster handheld wide-field eye scans plus AI to find early signs of retinopathy of prematurity in premature babies and help guide treatment.
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.