EIARG2: Digital Retinal Images of ROP Data Set

1 Introduction

The EIARG2 database has been provided by the Eye Images Analysis Research Group for image based studies on blood vessel tortuosity. The research community is invited to test its algorithms on this database.

2 Using the database

The data included in this database can be used, free of charge, for research and educational purposes. Copy, redistribution, and any unauthorized commercial use are prohibited. Any researcher reporting results that use this database must acknowledge the EIARG2 data set by adding the following information:

 "On curvature based automatic grading of retinal blood vessel tortuosity (preprint)".

In addition, we appreciate to hear about any publications that use the EIARG2 database. Feedback on the database and this website is also welcomed. We further encourage authors and ophthalmologists to give us their grading of the data set. These grading would be provided on the website with reference to their work for future use by other research groups. The person to contact is[M1]  Hamid Reza Pourreza (This email address is being protected from spambots. You need JavaScript enabled to view it. )

3 Data description

120 full images of retina were chosen by experts from preterm infants in Retina Research Center, Mashhad University of 
Medical Science in Khatam-al-Anbya hospital of Mashhad, Mashhad, Iran. Photographs were taken by Ret Cam 3  
(Clarity Medical System Inc., Pleasanton, CA, USA). Field of view of RetCam3 is 130 degrees.

4 Medical diagnoses

Three ophthalmologists on three different occasions have graded the tortuosity of the images by grading them based on existence of tortuosity. To see the grading and the grading based on nonlinear and linear curvature methods please refer to the annotation file attached to the zip file.