DRIVE: Digital Retinal Images for Vessel Extraction
The DRIVE database has been established to enable comparative studies on segmentation of blood vessels in retinal images. Retinal vessel segmentation and delineation of morphological attributes of retinal blood vessels, such as length, width, tortuosity, branching patterns and angles are utilized for the diagnosis, screening, treatment, and evaluation of various cardiovascular and ophthalmologic diseases such as diabetes, hypertension, arteriosclerosis and chorodial neovascularization. Automatic detection and analysis of the vasculature can assist in the implementation of screening programs for diabetic retinopathy, can aid research on the relationship between vessel tortuosity and hypertensive retinopathy, vessel diameter measurement in relation with diagnosis of hypertension, and computer-assisted laser surgery. Automatic generation of retinal maps and extraction of branch points have been used for temporal or multimodal image registration and retinal image mosaic synthesis. Moreover, the retinal vascular tree is found to be unique for each individual and can be used for biometric identification.
The photographs for the DRIVE database were obtained from a diabetic retinopathy screening program in The Netherlands. The screening population consisted of 400 diabetic subjects between 25-90 years of age. Forty photographs have been randomly selected, 33 do not show any sign of diabetic retinopathy and 7 show signs of mild early diabetic retinopathy. Here is a brief description of the abnormalities in these 7 cases:
25_training: pigment epithelium changes, probably butterfly maculopathy with pigmented scar in fovea, or choroidiopathy, no diabetic retinopathy or other vascular abnormalities.
26_training: background diabetic retinopathy, pigmentary epithelial atrophy, atrophy around optic disk
32_training: background diabetic retinopathy
03_test: background diabetic retinopathy
08_test: pigment epithelium changes, pigmented scar in fovea, or choroidiopathy, no diabetic retinopathy or other vascular abnormalities
14_test: background diabetic retinopathy
17_test: background diabetic retinopathy
Each image has been JPEG compressed.
The images were acquired using a Canon CR5 non-mydriatic 3CCD camera with a 45 degree field of view (FOV). Each image was captured using 8 bits per color plane at 768 by 584 pixels. The FOV of each image is circular with a diameter of approximately 540 pixels. For this database, the images have been cropped around the FOV. For each image, a mask image is provided that delineates the FOV.
The set of 40 images has been divided into a training and a test set, both containing 20 images. For the training images, a single manual segmentation of the vasculature is available. For the test cases, two manual segmentations are available; one is used as gold standard, the other one can be used to compare computer generated segmentations with those of an independent human observer. Furthermore, a mask image is available for every retinal image, indicating the region of interest. All human observers that manually segmented the vasculature were instructed and trained by an experienced ophthalmologist. They were asked to mark all pixels for which they were for at least 70% certain that they were vessel.
Results should be submitted as a single zip-file that contains a binary PNG-file with the vessel predictions for the corresponding files in the test set. Filenames should be [1.png, 2.png, ..., 20.png]. The dice-coefficient will be calculated for every image in the test set (only pixels within the mask are considered). The leaderbord is sorted based on highest average dice-coefficient.
See http://www.isi.uu.nl/Research/Databases/DRIVE/ for the original web-page on this challenge