Related Experiment Video
Updated: May 12, 2026
Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases
Published on: March 11, 2016
FARFUM-RoP, A dataset for computer-aided detection of Retinopathy of Prematurity
Morteza Akbari1, Hamid-Reza Pourreza2,3, Elias Khalili Pour4
1Machine Vision Lab., Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, 9177948974, Iran.
Insights
A new public dataset, FARFUM-RoP, aids Retinopathy of Prematurity (ROP) research. This dataset supports AI development for detecting Plus Disease, a severe form of ROP in premature infants.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Retinopathy of Prematurity (ROP) is a leading cause of blindness in premature infants, stemming from abnormal retinal blood vessel development.
- Plus Disease signifies severe ROP, crucial for timely diagnosis and intervention.
- Artificial Intelligence (AI) shows promise in ROP detection, but requires high-quality, diverse datasets.
Purpose of the Study:
- To introduce FARFUM-RoP, a novel, publicly available dataset for ROP research.
- To facilitate the development and validation of AI algorithms for ROP and Plus Disease detection.
- To promote collaboration and data sharing within the ROP research community.
Main Methods:
- The FARFUM-RoP dataset contains 1533 ROP fundus images from 68 patients.
- Images were independently annotated by five experienced childhood ophthalmologists.
- Annotations include classifications of 'Normal,' 'Pre-Plus,' and 'Plus' disease stages.
Main Results:
- The dataset provides a valuable resource for training and testing AI models.
- Expert annotations offer a robust ground truth for evaluating AI performance in identifying ROP severity.
- The dataset adheres to ethical principles, with patient consent obtained for data collection.
Conclusions:
- The FARFUM-RoP dataset represents a significant contribution to ROP research.
- Availability of this dataset will accelerate AI-driven advancements in diagnosing and managing ROP.
- This resource supports the development of more accurate and accessible ROP screening tools.
Abstract:
Retinopathy of Prematurity (ROP) is a critical eye disorder affecting premature infants, characterized by abnormal blood vessel development in the retina. Plus Disease, indicating severe ROP progression, plays a pivotal role in diagnosis. Recent advancements in Artificial Intelligence (AI) have shown parity with or surpass human experts in ROP detection, especially Plus Disease. However, the success of AI systems depends on high-quality datasets, emphasizing the need for collaboration and data sharing among researchers. To address this challenge, the paper introduces a new public dataset, FARFUM-RoP (Farabi and Ferdowsi University of Mashhad's ROP dataset), comprising 1533 ROP fundus images from 68 patients, annotated independently by five experienced childhood ophthalmologists as "Normal," "Pre-Plus," or "Plus." Ethical principles and consent were meticulously followed during data collection. The paper presents the dataset structure, patient details, and expert labels.
