CHASE_DB1 retinal vessel reference dataset

A public retinal vessel reference dataset CHASE_DB1 made available by Kingston University, London in collaboration with St. George’s, University of London. This is a subset of retinal images of multi-ethnic children from the Child Heart and Health Study in England (CHASE) dataset. This subset contains 28 retinal images captured from both eyes from 14 of the children recruited in the study. In this subset each retinal image is also accompanied by two ground truth images. This is provided in the form of two manual vessel segmentations made by two independent human observers for each of the images, in which each pixel is assigned a "1" label if it is part of a blood vessel and a "0" label otherwise. Making this subset publicly available allows for the scientific community to train and test computer vision algorithms (specifically vessel segmentation methodologies). Most importantly this subset allows for performance comparisons - several algorithms being evaluated on the same database allows for direct comparisons of their performances to be made.

Image

The Child Heart and Health Study in England (CHASE), is a cardiovascular health survey across 200 primary schools in London, Birmingham, and Leicester. The retinal imaging was carried out in 46 schools and demonstrated associations between retinal vessel tortuosity and early risk factors for cardiovascular disease in over 1000 British primary school children of different ethnic origin. The retinal images of both of the eyes of each child were recorded with a hand-held Nidek NM-200-D fundus camera. The images were captured at 30 degree field-of-view with a resolution of 1280 × 960 pixels. The dataset of images are characterized by having nonuniform background illumination, poor contrast of blood vessels as compared with the background and wider arteriolars that have a bright strip running down the centre known as the central vessel reflex. This work is based on using a subset of images to create a retinal vessel reference dataset representing multi-ethnic school children known as CHASE_DB1. 28 retinal images are contained, acquired from both eyes of 14 children (8 white, 3 South Asian, 3 of other ethnic origin, mean age 10 years) recruited from one primary school in North-East London. For each image, there are two ground truths images for vessel segmentation made by two independent human observers.