Ridge-based vessel segmentation in color images of the retina
Abstract
A method is presented for automated segmentation of vessels in two-dimensional color images of the retina. This method can be used in computer analyses of retinal images, e.g., in automated screening for diabetic retinopathy. The system is based on extraction of image ridges, which coincide approximately with vessel centerlines. The ridges are used to compose primitives in the form of line elements. With the line elements an image is partitioned into patches by assigning each image pixel to the closest line element. Every line element constitutes a local coordinate frame for its corresponding patch. For every pixel, feature vectors are computed that make use of properties of the patches and the line elements. The feature vectors are classified using a kappaNN-classifier and sequential forward feature selection. The algorithm was tested on a database consisting of 40 manually labeled images. The method achieves an area under the receiver operating characteristic curve of 0.952. The method is compared with two recently published rule-based methods of Hoover et al. and Jiang et al. The results show that our method is significantly better than the two rule-based methods (p < 0.01). The accuracy of our method is 0.944 versus 0.947 for a second observer.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The DRIVE dataset consists of 20 images and is a standardized benchmark for evaluating retinal blood vessel segmentation methods in diabetic retinopathy screening.
“The DRIVE [45] dataset consists of 20 images, developed to provide a standardized benchmark for evaluating retinal blood vessel segmentation methods in the context of diabetic retinopathy screening.”
From rNCA: Self-Repairing Segmentation Masks (2025) · cites this paper as [45]
Cited by
Sorted by citations
Domain adaptation for medical image analysis: A survey
Guan, H., & Liu, M. (2022) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2021.3117407 · Cited by 1,057 · see citing works
Kwon, Y., Won, J.-H., Kim, B. J., & Paik, M. C. (2020) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2019.106816 · Cited by 424 · see citing works
Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images
Zhou, K., Xiao, Y., Yang, J., Cheng, J., Liu, W., Luo, W., Gu, Z., Liu, J., & Gao, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58565-5_22 · Cited by 146 · see citing works
Variation-Aware Federated Learning With Multi-Source Decentralized Medical Image Data
Yan, Z., Wicaksana, J., Wang, Z., Yang, X., & Cheng, K.-T. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3040015 · Cited by 137 · see citing works
Zhou, Y., Wang, B., He, X., Cui, S., & Shao, L. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3045475 · Cited by 155 · see citing works
Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models
Anthony, L. F. W., Kanding, B., & Selvan, R. (2020) · arXiv · doi:10.48550/arxiv.2007.03051 · Cited by 255 · see citing works
“U-net DRIVE This is a standard U-net model (Ron-neberger et al., 2015) trained on the DRIVE dataset 6 https://www.eea.europa. eu/data-and-maps/data/co2-intensity-of-electricity-generation 7 https://energidataservice.dk/ 8 https://carbonintensity.org.uk/ 9 https://docs.python.org/3/library/ logging.html 10 https://www.…”
MethodInfluentialLim, G., Bellemo, V., Xie, Y., Lee, X. Q., Yip, M. Y. T., & Ting, D. S. W. (2020) · Eye and Vision · doi:10.1186/s40662-020-00182-7 · Cited by 96 · see citing works
Deep Learning Approach for Medical Image Analysis
Adegun, A. A., Viriri, S., & Ogundokun, R. O. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/6215281 · Cited by 52 · see citing works
Fundus Disease Image Classification based on Improved Transformer
Yang, H., Chen, J., & Xu, M. (2021) · 2021 International Conference on Neuromorphic Computing (ICNC) · doi:10.1109/icnc52316.2021.9608181 · Cited by 31 · see citing works
Fully automatized parallel segmentation of the optic disc in retinal fundus images
Díaz-Pernil, D., Fondón, I., Peña-Cantillana, F., & Gutiérrez-Naranjo, M. A. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2016.04.025 · Cited by 28 · see citing works
SpinDrop: Dropout-Based Bayesian Binary Neural Networks With Spintronic Implementation
Ahmed, S. T., Danouchi, K., Münch, C., Prenat, G., Anghel, L., & Tahoori, M. B. (2023) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2023.3242146 · Cited by 25 · see citing works
clDice - a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation
Shit, S., Paetzold, J. C., Sekuboyina, A., Ezhov, I., Unger, A., Zhylka, A., Pluim, J. P. W., Bauer, U., & Menze, B. H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01629 · Cited by 60 · see citing works
“In 2D, we evaluate on the DRIVE retina dataset [43], the Massachusetts Roads dataset [28] and the CREMI neuron dataset [12].”
MethodDeep learning: step forward to high‐resolution in vivo shortwave infrared imaging
Baulin, V. A., Usson, Y., & Le Guével, X. (2021) · Journal of Biophotonics · doi:10.1002/jbio.202100102 · Cited by 10 · see citing works
rNCA: Self-Repairing Segmentation Masks
Silbernagel, M., Alonso, A., Petersen, J., Ibragimov, B., de Bruijne, M., & Wyburd, M. K. (2025) · arXiv · doi:10.48550/arxiv.2512.13397
“The DRIVE [45] dataset consists of 20 images, developed to provide a standardized benchmark for evaluating retinal blood vessel segmentation methods in the context of diabetic retinopathy screening.”
- Authors
- Staal, J., Abramoff, M. D., Niemeijer, M., Viergever, M. A., & van Ginneken, B.
- Affiliations
- University Medical Center Utrecht (NL)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2004-04
- Volume
- 23
- Issue
- 4
- Pages
- 501-509
- ISSN
- 0278-0062 (ISSN-L)
- OpenAlex
- W2150769593
- Cited by
- 4,202
- References
- 0
- Citations by year
- 2026: 241 · 2025: 355 · 2024: 323 · 2023: 350 · 2022: 349 · 2021: 319 · 2020: 295 · 2019: 315 · 2018: 217 · 2017: 220 · 2016: 175 · 2015: 172 · 2014: 148 · 2013: 134 · 2012: 130
- FWCI
- 24.58
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Health Sciences › Medicine › Ophthalmology › Retinal Diseases and Treatments
- Keywords
- retinal vessel segmentation, color retinal images, ridge extraction, vessel centerline, line element, local coordinate frames, feature vectors, k-nearest neighbors, sequential forward feature selection, diabetic retinopathy screening, automated retinal analysis
- MeSH terms
- Algorithms, Color, Diabetic Retinopathy, Expert Systems, Fluorescein Angiography, Humans, Image Interpretation, Computer-Assisted, Ophthalmoscopy, Pattern Recognition, Automated, Retina, Retinal Vessels, Sensitivity and Specificity, Reproducibility of Results, Cluster Analysis, Databases, Factual
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
