Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification

By Elisa Ricci, Renzo Perfetti. IEEE Transactions on Medical Imaging, 2007

872 citations recorded by the source corpus.

Subfields: Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/e4ba7291c9d5609bc712c5ae5a8dceaabc23c32b

How researchers see this paper

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

In Ophthalmology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Optic Disk and Cup Segmentation From Monocular Color Retinal Images for Glaucoma Assessment (2011, neutral): “Several methods have been proposed for vessel segmentation in literature (see [50]).”
A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Gray-Level and Moment Invariants-Based Features (2011, methodology): “Ricci and Pefetti [53], to research the dependence of their classification method on the dataset, carried out an experiment based on, firstly, training the classifier on each of the DRIVE and STARE databases, and then, testing it on the other.”
Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel Segmentation (2018, methodology): “and Perfetti [19] combined a line detector with the support vector machine for vessel segmentation.”
Fast Retinal Vessel Detection and Measurement Using Wavelets and Edge Location Refinement (2012, background): “[12], wavelet coefficients [13] or filter correlations [14,15].”
Convolutional Networks Can Learn to Generate Affinity Graphs for Image Segmentation (2010, methodology): “In other work, Ricci and Perfetti (2007) use a hand-designed set of thin, oriented line detectors, as well as local average intensities, as features for input to an SVM classifier.”
Hierarchical retinal blood vessel segmentation based on feature and ensemble learning (2015, background): “Ricci and Perfetti [21] deployed line operators to form a feature vector.”
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].”
A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images (2016, methodology): “Compared to other supervised methods [8], [16], [17], [24], our method can achieve unsupervised learning of the optimal feature for vessel detection.”
AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020, positive): “been proposed for this purpose, a common choice being support vector machines [95], due to the ease of implementation and the well understood nonlinear kernels.”
Automated Vessel Segmentation Using Infinite Perimeter Active Contour Model with Hybrid Region Information with Application to Retinal Images (2015, background): “, k-nearest neighbors [17], support vector machine (SVM) [18], [19], artificial neural networks (ANN) [20], Gaussian mixture models (GMM) [8], [21], AdaBoost [22], or conditional random fields (CRFs) [23]) so that it can be used for the classification of image pixels as either vessel or not in a new”
Glaucoma risk index: Automated glaucoma detection from color fundus images (2010, background): “, 2007) or supervised approaches (Ricci and Perfetti, 2007; Soares et al., 2006; Staal et al., 2004; Niemeijer et al., 2007) as well as a combination of those (Sofka and Stewart, 2006; Ricci and Perfetti, 2007).”
An approach to localize the retinal blood vessels using bit planes and centerline detection (2012, methodology): “Moreover, the line detector presented in [29] is utilized to generate the line strength image shown in Fig.”
Blood Vessel Segmentation of Fundus Images by Major Vessel Extraction and Subimage Classification (2015, methodology): “The method in [27] uses line operators and a support vector machine (SVM) classifier with a three-feature set per pixel.”
DUNet: A deformable network for retinal vessel segmentation (2018, background): “Various classiﬁers such as k-NN classiﬁer [19], support vector machine (SVM) [20] [21], artiﬁcial neural networks (ANN) [22], AdaBoost [23] etc, have been proposed to deal with different tasks.”
Robust Retinal Vessel Segmentation via Locally Adaptive Derivative Frames in Orientation Scores (2016, methodology): “Since the green channel of retinal images in RGB datasets has better contrast between the vessels and the background [2], [9], [15], [19], [28], we will only use the green channel for our experiments.”
Segmentation of retinal blood vessels using the radial projection and semi-supervised approach (2011, methodology): “In [12], a modified line operator was applied to construct the feature vector, used to train a supervised classifier.”
An effective retinal blood vessel segmentation method using multi-scale line detection (2013, methodology): “The problem with the segmentation produced by Ricci-line [8] method is the partial merging of two close vessels and the spurious segmentation at the crossover point.”
An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation (2012, methodology): “You et al. [25] computed the feature vector by using the steerable complex wavelet followed by calculating the line strength [22]; the SVM is used for semisupervised classification.”
Segmenting Retinal Blood Vessels With Deep Neural Networks (2016, methodology): “A representative of this group is the first of two methods proposed in [12], which uses line detectors to accumulate the evidence for the presence of blood vessels at individual image pixels.”