Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response

By A. Hoover, V. Kouznetsova, Michael H. Goldbaum. IEEE Transactions on Medical Imaging, 2000

2,694 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/44885e8f48a653f4e8fca4d28e5661823d91da7a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Ophthalmology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Transformers in Medical Imaging: A Survey (2022, neutral): “3 Eng/Zh 728 DEN [359] 15,709 CFP+FFA 1 7 Eng STARE [360] 397 CFP+FFA 5 - Eng 397”
Hierarchical retinal blood vessel segmentation based on feature and ensemble learning (2015, methodology): “STARE database The STARE (Structured Analysis of the Retina) database [1] contains 20 images for blood vessel segmentation, out of which ten images contain pathology.”
Retinal image analysis: concepts, applications and potential. (2006, background): “…element’’ (kernel) that has a Gaussian cross-proﬁle section, extruded or rotated into three dimensions to identify the cross-proﬁle of the blood vessel, which typically has a Gaussian or a Gaussian derivative proﬁle (Chaudhuri et al., 1989b; Hoover et al., 2000; Lowell et al., 2004b) (Fig.”
Retinal vascular tree morphology: a semi-automatic quantification (2002, background): “Those studies that have characterized continuous blood vessel trees from retinal images, by means of image processing techniques, have been mainly focused on the detection process rather than the measurement of geometrical or topological properties [9]–[11].”
An Active Contour Model for Segmenting and Measuring Retinal Vessels (2009, background): “Hoover's seminal work combined local appearance modelling with vessel growing and pruning [10].”
Recurrent residual U-Net for medical image segmentation (2019, background): “The second dataset, STARE, contains 20 color images, and each image has a size of 700 × 605 pixels.(48,50) Owing to the small number of samples Fig.”
Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation (2022, methodology): “[124] 2D Fundus DRIVE [137], STARE [138], CHASE DB1 [139] Add a leaking GAN to pollute the discriminator by leaking information from the generator for more moderate generations Adversarial learning”
A Three-Stage Deep Learning Model for Accurate Retinal Vessel Segmentation (2019, methodology): “Three public datasets DRIVE [20], STARE [38] and CHASE_DB1 [39] are used for evaluation.”
A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images (2017, methodology): “Our experiments were carried out on DRIVE [44], STARE [46], CHASEDB1 [12], and HRF [24], [47], four standard publicly available datasets of fundus images used for the evaluation of blood vessel segmentation algorithms.”
Retinal Vessel Centerline Extraction Using Multiscale Matched Filters, Confidence and Edge Measures (2006, methodology): “In addition, matched-filterbased LRV is significantly better (p 0.0001 for STARE and p 0.005 for DRIVE) than the Frangi-based LRV.”
Retinal Imaging and Image Analysis (2010, neutral): “Fundus imaging examples are represented by the STARE [72], DRIVE [73], REVIEW [99] and MESSIDOR databases [100], with large numbers of annotated retinal fundus images, with expert annotations for vessel segmentation, vessel width measurements, and diabetic retinopathy detection, as well as competiti”
Deep Retinal Image Understanding (2016, methodology): “We also retrain HED [24] (state of the art in generic contour detection with CNNs) on DRIVE and STARE using their public code.”
An approach to localize the retinal blood vessels using bit planes and centerline detection (2012, background): “[37], Xiaoyi and Mojon [38] and Yao and Chen [39].”
An effective retinal blood vessel segmentation method using multi-scale line detection (2013, background): “…as part of a vessel, the vessel may be misunderstood as two vessels. if two close vessels are merged together, they will be considered as one wide vessel. poor segmentation such as the disconnection at vessel crossover regions (where two vessels cross each other) will cause difficulties for…”
Robust Vessel Segmentation in Fundus Images (2013, methodology): “Sometimes these methods were combined with other approaches [9–12].”
Glaucoma risk index: Automated glaucoma detection from color fundus images (2010, methodology): “Therefore, we used the green channel for a proper image processing as only this channel shows a reliable saturation.”