Retinal vessel extraction by matched filter with first-order derivative of Gaussian

By Bob Zhang, Lin Zhang, Lei Zhang, F. Karray. Comput. Biol. Medicine, 2010

557 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/efa5994cdfc6e9fc79bed2983e43b431c773c62f

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

A Three-Stage Deep Learning Model for Accurate Retinal Vessel Segmentation (2019, methodology): “[12] segmented blood vessels by applying amatched filter to the first-order derivative of the Gaussian filtered image.”
An approach to localize the retinal blood vessels using bit planes and centerline detection (2012, methodology): “Chutatape and co-workers [42] evaluated the suitability amplitude-modified second order Gaussian filter whereas Zhang et al. [43] proposed an extension and generalization of the matched filter with a first-order derivative of Gaussian.”
Robust Retinal Vessel Segmentation via Locally Adaptive Derivative Frames in Orientation Scores (2016, background): “These false positives can either be reduced by including a preprocessing or postprocessing step, or by integrating shape information of the vessel cross-section into vessel filtering, which can help to distinguish the differences between vessel and pathological profiles as in [17].”
Robust Vessel Segmentation in Fundus Images (2013, methodology): “The state-of-the-art vessel segmentation methods [12, 22] usually have high computational needs and achieve an accuracy of 90% to 94% on eye-fundus images, with sensitivity of 60% to 70% and specificity above 99% on average [26].”
Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database (2013, methodology): “This concept has been recently published in [30 – 32].”
Blood vessel segmentation methodologies in retinal images - A survey (2012, background): “The classical matched filter is generalized and extended [54] with the first-order derivative of the Gaussian (MF-FDOG) to exploit the property that for a blood vessel in the retina, the Gaussian shaped cross section is symmetric with respect to its peak position whereas the non-vessel edges, e.”
An effective retinal blood vessel segmentation method using multi-scale line detection (2013, background): “Different variants [17] [18] [19] [20] have been proposed to improve the performance of the original matched filter response, ranging from the use of a threshold probing technique [17], 'double-sided' thresholding [19], or the first order derivative of Gaussian image [20] to provide a better…”
A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images (2017, background): “This property can potentially contribute to a number of different biological and medical applications where the segmentation of such structures is required, including automatic plant root phenotyping [34] or neuron analysis [35].”
Deep Retinal Image Understanding (2016, methodology): “Classic methods for addressing the task of blood vessel segmentation involve hand crafted filters like line detectors [17,14] and vessel enhancement techniques [20,26,5].”