Related Experiment Video
Updated: Dec 14, 2025
Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model
Published on: April 2, 2021
Artificial Intelligence in Retinopathy of Prematurity Diagnosis
Brittni A Scruggs1, R V Paul Chan2, Jayashree Kalpathy-Cramer3
1Casey Eye Institute, Department of Ophthalmology, Oregon Health & Science University, Portland, OR, USA.
Insights
Artificial intelligence (AI) offers automated diagnosis for retinopathy of prematurity (ROP), a leading cause of childhood blindness. This review explores AI
Area of Science:
- Ophthalmology and Medical Artificial Intelligence
Background:
- Retinopathy of prematurity (ROP) is a significant cause of pediatric blindness globally.
- Current ROP diagnosis involves subjective subclassification (zone, stage, plus disease), leading to expert disagreement.
- Existing ROP screening methods lack efficiency and objectivity.
Purpose of the Study:
- To review the development of artificial intelligence (AI) for automated ROP diagnosis.
- To focus on AI's role in the objective diagnosis of 'plus disease' in ROP.
- To identify clinical and technical challenges in AI development and real-world implementation for ROP.
Main Methods:
- Review of current literature on AI applications in ROP diagnosis.
- Analysis of AI algorithms developed for ROP subclassification, particularly 'plus disease'.
- Discussion of challenges in translating AI tools from research to clinical practice.
Main Results:
- AI demonstrates potential for automated, quantifiable, and objective ROP diagnosis.
- AI can improve efficiency and consistency in ROP screening and diagnosis.
- Significant clinical and technical hurdles exist for widespread AI adoption in ROP care.
Conclusions:
- AI holds promise for revolutionizing ROP diagnosis, enhancing objectivity and efficiency.
- Addressing challenges in AI development and implementation is crucial for clinical success.
- Further research and validation are needed to integrate AI into routine ROP management.
Abstract:
Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide. The diagnosis of ROP is subclassified by zone, stage, and plus disease, with each area demonstrating significant intra- and interexpert subjectivity and disagreement. In addition to improved efficiencies for ROP screening, artificial intelligence may lead to automated, quantifiable, and objective diagnosis in ROP. This review focuses on the development of artificial intelligence for automated diagnosis of plus disease in ROP and highlights the clinical and technical challenges of both the development and implementation of artificial intelligence in the real world.
