Related Experiment Video
Updated: Jul 28, 2026
Fundus Photography as a Convenient Tool to Study Microvascular Responses to Cardiovascular Disease Risk Factors in Epidemiological Studies
Published on: October 22, 2014
DR HAGIS-a fundus image database for the automatic extraction of retinal surface vessels from diabetic patients
Sven Holm1, Greg Russell1, Vincent Nourrit2
1University of Manchester , Faculty of Biology, Medicine and Health, Division of Pharmacy and Optometry, Manchester, United Kingdom.
Insights
The DR HAGIS database offers diverse retinal images for testing diabetic retinopathy algorithms. It achieved high accuracy in vessel segmentation, aiding automated screening tool development.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Diabetic retinopathy screening programs generate diverse retinal images due to varied equipment and patient comorbidities.
- Existing datasets may not fully represent the variability encountered by human graders in real-world screening.
Purpose of the Study:
- To introduce the DR HAGIS database, a novel collection of retinal fundus images.
- To provide a realistic dataset for evaluating automatic vessel extraction algorithms in ophthalmology.
- To establish baseline performance metrics for vessel segmentation algorithms using this dataset.
Main Methods:
- The DR HAGIS database comprises 39 high-resolution color fundus images from a UK diabetic retinopathy screening program.
- Images exhibit variations in size, resolution, and include patients with comorbidities like hypertension, age-related macular degeneration, and glaucoma.
- Manual segmentation of vasculature was performed for all images; two vessel extraction algorithms were applied for baseline testing.
Main Results:
- A pixel intensity-based method achieved a mean segmentation accuracy of 95.83%.
- A Gabor filter-based algorithm yielded a mean segmentation accuracy of 95.71%.
- Both methods demonstrated high performance on the diverse DR HAGIS dataset.
Conclusions:
- The DR HAGIS database effectively simulates the variability of clinical retinal images.
- The established baseline measurements provide a benchmark for future automated vessel extraction algorithm development.
- This dataset supports the advancement of automated diabetic retinopathy screening technologies.
Abstract:
A database of retinal fundus images, the DR HAGIS database, is presented. This database consists of 39 high-resolution color fundus images obtained from a diabetic retinopathy screening program in the UK. The NHS screening program uses service providers that employ different fundus and digital cameras. This results in a range of different image sizes and resolutions. Furthermore, patients enrolled in such programs often display other comorbidities in addition to diabetes. Therefore, in an effort to replicate the normal range of images examined by grading experts during screening, the DR HAGIS database consists of images of varying image sizes and resolutions and four comorbidity subgroups: collectively defined as the diabetic retinopathy, hypertension, age-related macular degeneration, and Glaucoma image set (DR HAGIS). For each image, the vasculature has been manually segmented to provide a realistic set of images on which to test automatic vessel extraction algorithms. Modified versions of two previously published vessel extraction algorithms were applied to this database to provide some baseline measurements. A method based purely on the intensity of images pixels resulted in a mean segmentation accuracy of 95.83% ([Formula: see text]), whereas an algorithm based on Gabor filters generated an accuracy of 95.71% ([Formula: see text]).
