{"url":"/dataset/drive","name":"DRIVE","full_name":"Digital Retinal Images for Vessel Extraction","description_markdown":"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). \r\n\r\nThe 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.\r\n\r\nSource: [Ant Colony based Feature Selection Heuristics for Retinal Vessel Segmentation](https://arxiv.org/abs/1403.1735)\r\nImage Source: [https://drive.grand-challenge.org/](https://drive.grand-challenge.org/)","description_withheld":null,"homepage":"https://drive.grand-challenge.org/","introduced_date":"2004-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Ridge-based vessel segmentation in color images of the retina","first_author":null,"url":"https://doi.org/10.1109/TMI.2004.825627"},"license":{"name":"CC-BY-4.0","url":"https://grand-challenge.org/policies/terms-of-service/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Medical Image Segmentation","url":"/task/medical-image-segmentation","datasets_with_task":"/datasets/task/medical-image-segmentation"},{"name":"Retinal Vessel Segmentation","url":"/task/retinal-vessel-segmentation","datasets_with_task":"/datasets/task/retinal-vessel-segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DRIVE"],"data_loaders":[{"repo":"https://github.com/open-mmlab/mmsegmentation","url":"https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md","frameworks":["pytorch"]},{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/drive-dataset","frameworks":["tf","pytorch"]}],"num_papers_in_archive":311,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/retinal-vessel-segmentation-on-drive","task":"Retinal Vessel Segmentation","dataset_variant":"DRIVE","rows":22,"metrics":["AUC","F1 score","Accuracy","mIoU","sensitivity","Specificity","MCC","1:1 Accuracy","Average IOU","DSC"],"first_row_in_archive_order":{"model":"Swin-Res-Net","paper":"/paper/enhancing-retinal-vascular-structure","metrics":{"AUC":"0.9931"},"code_links":[{"title":"orobix/retina-unet","url":"https://github.com/orobix/retina-unet/blob/master/lib/pre_processing.py"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/medical-image-segmentation-on-drive-1","task":"Medical Image Segmentation","dataset_variant":"DRIVE","rows":5,"metrics":["mIoU","F1 score","Recall","Specificity","Precision"],"first_row_in_archive_order":{"model":"MERIT-GCASCADE","paper":"/paper/g-cascade-efficient-cascaded-graph","metrics":{"F1 score":"0.8290","Recall":"0.8281","Specificity":"0.9844","mIoU":"0.7081"},"code_links":[{"title":"SLDGroup/G-CASCADE","url":"https://github.com/SLDGroup/G-CASCADE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dual-encoding-feature-filtering-generalized","title":"Dual encoding feature filtering generalized attention UNET for retinal vessel segmentation","date":"2025-06-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/full-scale-representation-guided-network-for","title":"Full-scale Representation Guided Network for Retinal Vessel Segmentation","date":"2025-01-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hi-gmisnet-generalized-medical-image","title":"Hi-gMISnet: generalized medical image segmentation using DWT based multilayer fusion and dual mode attention into high resolution pGAN","date":"2024-05-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/da-net-a-disentangled-and-adaptive-network","title":"DA-Net: A Disentangled and Adaptive Network for Multi-Source Cross-Lingual Transfer Learning","date":"2024-03-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/enhancing-retinal-vascular-structure","title":"Enhancing Retinal Vascular Structure Segmentation in Images With a Novel Design Two-Path Interactive Fusion Module Model","date":"2024-03-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/g-cascade-efficient-cascaded-graph","title":"G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation","date":"2023-10-24","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-learning-architectures-for-diagnosis-of","title":"Deep Learning Architectures for Diagnosis of Diabetic Retinopathy","date":"2023-03-31","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/segmentation-of-blood-vessels-optic-disc","title":"Segmentation of Blood Vessels, Optic Disc Localization, Detection of Exudates and Diabetic Retinopathy Diagnosis from Digital Fundus Images","date":"2022-07-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/full-resolution-network-and-dual-threshold","title":"Full-Resolution Network and Dual-Threshold Iteration for Retinal Vessel and Coronary Angiograph Segmentation","date":"2022-07-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/exploring-the-limits-of-data-augmentation-for","title":"Exploring The Limits Of Data Augmentation For Retinal Vessel Segmentation","date":"2021-05-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fanet-a-feedback-attention-network-for","title":"FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation","date":"2021-03-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/study-group-learning-improving-retinal-vessel","title":"Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels","date":"2021-03-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sa-unet-spatial-attention-u-net-for-retinal","title":"SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation","date":"2020-04-07","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/iternet-retinal-image-segmentation-utilizing","title":"IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks","date":"2019-12-12","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/bi-directional-convlstm-u-net-with-densley","title":"Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions","date":"2019-08-31","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/et-net-a-generic-edge-attention-guidance","title":"ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation","date":"2019-07-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ce-net-context-encoder-network-for-2d-medical","title":"CE-Net: Context Encoder Network for 2D Medical Image Segmentation","date":"2019-03-07","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/dunet-a-deformable-network-for-retinal-vessel","title":"DUNet: A deformable network for retinal vessel segmentation","date":"2018-11-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/laddernet-multi-path-networks-based-on-u-net","title":"LadderNet: Multi-path networks based on U-Net for medical image segmentation","date":"2018-10-17","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/deep-vessel-segmentation-by-learning","title":"Deep Vessel Segmentation By Learning Graphical Connectivity","date":"2018-06-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/road-extraction-by-deep-residual-u-net","title":"Road Extraction by Deep Residual U-Net","date":"2017-11-29","rows_on_this_dataset":1,"code_links":13,"syntology":null},{"paper":"/paper/u-net-convolutional-networks-for-biomedical","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","date":"2015-05-18","rows_on_this_dataset":1,"code_links":487,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":757,"samples_ran":510,"samples_unverified":247,"pointer_only_for_licence":426,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":766,"samples_ran":516,"samples_unverified":250,"pointer_only_for_licence":435,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}