AI tool to detect retinopathy of prematurity in preterm infants
Deep Learning-based Diagnosis of Retinopathy of Prematurity
Using artificial intelligence to help doctors spot sight-threatening retinopathy in premature babies.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | The Trustees of the Stevens Institute of Technology NIH-funded |
| Lab location | 1 site (Hoboken, United States) |
| Project ID | NIH-11164687 on NIH RePORTER |
What this research studies
As a parent of a premature infant, this project aims to create an AI that learns from retinal photos to recognize treatment-needed ROP such as plus disease. The team will expand limited training data using image-augmentation techniques and work to make images from different cameras comparable. They will train and test the model to improve consistent detection despite variable image quality. The goal is a reliable diagnostic aid that can be applied across hospitals and imaging systems.
Who could benefit from this research
Good fit: Premature infants undergoing ROP screening whose retinal images can be shared with the research team with parental consent.
Not a fit: Adults, children without ROP, or infants who do not have retinal imaging available would not directly participate or benefit from this project.
Why it matters
Potential benefit: Could enable earlier and more consistent detection of treatment-required ROP, helping reduce preventable childhood blindness.
How similar studies have performed: AI has successfully aided detection of other retinal diseases and some early ROP tools showed promise, but applying models across different cameras and small infant datasets remains a challenge.
Where this research is happening
Hoboken, United States
- The Trustees of the Stevens Institute of Technology — Hoboken, United States (Active)
Researchers
- Principal investigator: Kang-Mieler, Jennifer J — The Trustees of the Stevens Institute of Technology
- Study coordinator: Kang-Mieler, Jennifer J
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.