Retinal Vessel Centerline Extraction Using Multiscale Matched Filters, Confidence and Edge Measures

By M. Sofka, Charles V. Stewart. IEEE Transactions on Medical Imaging, 2006

380 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/488d9c8d61428513bd9bfb6cf028a1499ad0022b

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

An approach to localize the retinal blood vessels using bit planes and centerline detection (2012, background): “Sofka and Stewart [17] presented a likelihood ratio test for vessel centerlines extraction that combines matched filter responses, confidence measures and vessel boundary measures .”
FABC: Retinal Vessel Segmentation Using AdaBoost (2010, methodology): “Following [6], at each scale, the matched filter is implemented by taking the maximum responses over a discrete set of kernel orientations at each pixel.”
Submitted to Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Multiscale Centerline Detection (neutral): “A number of schemes have been proposed to solve the first problem [1], [27], [39], [50], [58].”
A review of biometric technology along with trends and prospects (2014, background): “Ocular region modalities: (a) Iris, (b) Retina [142], (c) Sclera Vasculature”
Segmentation of retinal blood vessels using the radial projection and semi-supervised approach (2011, methodology): “In [7], a multiscale matched filter was applied for vessels, using an appropriate normalizing multiplier to allow the combination of response across scales.”
Projection onto the Manifold of Elongated Structures for Accurate Extraction (2015, methodology): “They are typically used to compute the Hessian matrix [14, 36, 28, 13, 29] or the Oriented Flux matrix [22, 1, 41, 33, 44], whose eigenvalues then serve to estimate the likelihood that a pixel or voxel lies on a centerline.”
Robust Vessel Segmentation in Fundus Images (2013, methodology): “Similar methods and improvements were published later on by different authors [5–8].”