DRIVE

Digital Retinal Images for Vessel Extraction

Dataset Information
Modalities
Images, Medical
Languages
English
Introduced
2004
License
CC-BY-4.0
Homepage
Official Website
Contents

Overview

The Digital Retinal Images for Vessel Extraction (DRIVE) dataset is a dataset for retinal vessel segmentation. It consists of a total of JPEG 40 color fundus images; including 7 abnormal pathology cases. The images were obtained from a diabetic retinopathy screening program in the Netherlands. The images were acquired using Canon CR5 non-mydriatic 3CCD camera with FOV equals to 45 degrees. Each image resolution is 584*565 pixels with eight bits per color channel (3 channels).

The set of 40 images was equally divided into 20 images for the training set and 20 images for the testing set. Inside both sets, for each image, there is circular field of view (FOV) mask of diameter that is approximately 540 pixels. Inside training set, for each image, one manual segmentation by an ophthalmological expert has been applied. Inside testing set, for each image, two manual segmentations have been applied by two different observers, where the first observer segmentation is accepted as the ground-truth for performance evaluation.

Source: Ant Colony based Feature Selection Heuristics for Retinal Vessel Segmentation
Image Source: https://drive.grand-challenge.org/

Variants: DRIVE

Associated Benchmarks

This dataset is used in 2 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Retinal Vessel Segmentation DEFFA-Unet Dual encoding feature filtering generalized … 2025-06-02
Retinal Vessel Segmentation FSG-Net Full-scale Representation Guided Network for … 2025-01-31
Retinal Vessel Segmentation DA-Net DA-Net: A Disentangled and Adaptive … 2024-03-07
Retinal Vessel Segmentation Swin-Res-Net Enhancing Retinal Vascular Structure Segmentation … 2024-03-03
Retinal Vessel Segmentation MERIT-GCASCADE G-CASCADE: Efficient Cascaded Graph Convolutional … 2023-10-24
Medical Image Segmentation PVT-GCASCADE G-CASCADE: Efficient Cascaded Graph Convolutional … 2023-10-24
Medical Image Segmentation MERIT-GCASCADE G-CASCADE: Efficient Cascaded Graph Convolutional … 2023-10-24
Retinal Vessel Segmentation PVT-GCASCADE G-CASCADE: Efficient Cascaded Graph Convolutional … 2023-10-24
Retinal Vessel Segmentation DR_2021 Segmentation of Blood Vessels, Optic … 2022-07-09
Retinal Vessel Segmentation U-Net Exploring The Limits Of Data … 2021-05-19
Medical Image Segmentation FANet FANet: A Feedback Attention Network … 2021-03-31
Retinal Vessel Segmentation Study Group Learning Study Group Learning: Improving Retinal … 2021-03-05
Retinal Vessel Segmentation SA-UNet SA-UNet: Spatial Attention U-Net for … 2020-04-07
Retinal Vessel Segmentation IterNet IterNet: Retinal Image Segmentation Utilizing … 2019-12-12
Retinal Vessel Segmentation BCDU-Net (d=3) Bi-Directional ConvLSTM U-Net with Densley … 2019-08-31
Medical Image Segmentation BCDU-net Bi-Directional ConvLSTM U-Net with Densley … 2019-08-31
Retinal Vessel Segmentation ET-Net ET-Net: A Generic Edge-aTtention Guidance … 2019-07-25
Retinal Vessel Segmentation CE-Net CE-Net: Context Encoder Network for … 2019-03-07
Retinal Vessel Segmentation DUNet DUNet: A deformable network for … 2018-11-03
Retinal Vessel Segmentation LadderNet LadderNet: Multi-path networks based on … 2018-10-17

Research Papers

Recent papers with results on this dataset:

External Links: