2016
DOI: 10.1109/tmi.2016.2587062
|View full text |Cite
|
Sign up to set email alerts
|

Robust Retinal Vessel Segmentation via Locally Adaptive Derivative Frames in Orientation Scores

Abstract: This paper presents a robust and fully automatic filter-based approach for retinal vessel segmentation. We propose new filters based on 3D rotating frames in so-called orientation scores, which are functions on the Lie-group domain of positions and orientations [Formula: see text]. By means of a wavelet-type transform, a 2D image is lifted to a 3D orientation score, where elongated structures are disentangled into their corresponding orientation planes. In the lifted domain [Formula: see text], vessels are enh… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

1
164
1

Year Published

2017
2017
2021
2021

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 329 publications
(166 citation statements)
references
References 39 publications
1
164
1
Order By: Relevance
“…Conversely, other retinal anatomical structures have high contrast to other background tissues but with indistinct features in comparison with abnormal structures; optic disc and exudates lesions represent typical examples. All these challenges, in terms of medical image processing, make the classical segmentation techniques such as Sobel operators [26], Prewitt operators [27], gradient operators [28], and Robert and Krish differential operations [29] inefficient This challenge opens the room for a field of research specialized in detecting and segmenting thin (filamentary) retinal vascular structures, as in [18][19][20][21][22][23][24][25]. Secondly, Vessels identification in pathological retinal images faces a tension between accurate vascular structure extraction and false responses near pathologies (such as hard and soft exudates, hemorrhages, microaneuryms and cotton wool spots) and other nonvascular structures (such as optic disc and fovea region).…”
Section: Retinal Image Processingmentioning
confidence: 99%
See 1 more Smart Citation
“…Conversely, other retinal anatomical structures have high contrast to other background tissues but with indistinct features in comparison with abnormal structures; optic disc and exudates lesions represent typical examples. All these challenges, in terms of medical image processing, make the classical segmentation techniques such as Sobel operators [26], Prewitt operators [27], gradient operators [28], and Robert and Krish differential operations [29] inefficient This challenge opens the room for a field of research specialized in detecting and segmenting thin (filamentary) retinal vascular structures, as in [18][19][20][21][22][23][24][25]. Secondly, Vessels identification in pathological retinal images faces a tension between accurate vascular structure extraction and false responses near pathologies (such as hard and soft exudates, hemorrhages, microaneuryms and cotton wool spots) and other nonvascular structures (such as optic disc and fovea region).…”
Section: Retinal Image Processingmentioning
confidence: 99%
“…(a) (b) This challenge opens the room for a field of research specialized in detecting and segmenting thin (filamentary) retinal vascular structures, as in [18][19][20][21][22][23][24][25]. Secondly, Vessels identification in pathological retinal images faces a tension between accurate vascular structure extraction and false responses near pathologies (such as hard and soft exudates, hemorrhages, microaneuryms and cotton wool spots) and other nonvascular structures (such as optic disc and fovea region).…”
Section: Retinal Image Processingmentioning
confidence: 99%
“…To reveal the relative performance of our proposed method, we compared it with several existing state‐of‐the‐art vessel detection methods on the most popular datasets: DRIVE and STARE. The results are shown in Table , and the chosen methods have been ordered by the category the methods belonging to the most recent seven supervised methods and nine unsupervised segmentation methods . Note, a different AUC calculation was used in: AUC = ( se + sp )/2.…”
Section: Resultsmentioning
confidence: 99%
“…Note, to the best knowledge of the authors, only Zhang et al have tested their segmentation method on IOSTAR dataset. In consequence, we only compared with the performance obtained by in the bottom of Table and by no means exhaustive. In contrast, our method has better performance in terms of all metrics.…”
Section: Resultsmentioning
confidence: 99%
“…31 After applying a preprocessing step, they use several deep learning architectures to segment vessels. Second-order locally adaptive derivatives have been used in several papers for extracting vessel structures; Zhang et al 32 proposed a simpler version of this method by avoiding a computation of full Laplacian in vessel enhancements (geometric diffusions), which is much easier to understand and reproduce.…”
Section: Introductionmentioning
confidence: 99%