Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification

By João V. B. Soares, J. Leandro, Roberto Marcondes Cesar Junior, H. Jelinek, Michael J. Cree. IEEE Transactions on Medical Imaging, 2005

1,577 citations recorded by the source corpus.

We present a method for automated segmentation of the vasculature in retinal images. The method produces segmentations by classifying each image pixel as vessel or nonvessel, based on the pixel's feature vector. Feature vectors are composed of the pixel's intensity and two-dimensional Gabor wavelet transform responses taken at multiple scales. The Gabor wavelet is capable of tuning to specific frequencies, thus allowing noise filtering and vessel enhancement in a single step. We use a Bayesian classifier with class-conditional probability density functions (likelihoods) described as Gaussian mixtures, yielding a fast classification, while being able to model complex decision surfaces. The probability distributions are estimated based on a training set of labeled pixels obtained from manual segmentations. The method's performance is evaluated on publicly available DRIVE (Staal et al.,2004) and STARE (Hoover et al.,2000) databases of manually labeled images. On the DRIVE database, it achieves an area under the receiver operating characteristic curve of 0.9614, being slightly superior than that presented by state-of-the-art approaches. We are making our implementation available as open source MATLAB scripts for researchers interested in implementation details, evaluation, or development of methods

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

View Paper: https://www.semanticscholar.org/paper/767746905903ce168b7813d8b482ee63574bc743

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 Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation (2012, methodology): “The detailed procedure can be seen in [21] and [27].”
Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation (2018, methodology): “Another approach is the “leave-one-out” method, in which each image is tested, and training is conducted on the remaining 19 samples [47].”
Hierarchical retinal blood vessel segmentation based on feature and ensemble learning (2015, background): “However, fine vessels are not important for clinical importance [20,23].”
Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel Segmentation (2018, positive): “[18] used the two-dimensional Gabor wavelet transfor-”
A Three-Stage Deep Learning Model for Accurate Retinal Vessel Segmentation (2019, methodology): “[24] used the two-dimensional Gabor wavelet transformation response and the pixel intensity as the feature vector, and conducted vessel segmentation based on a Bayesian classifier.”
Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification (2007, methodology): “A similar approach is adopted in [17] where the orientation spans from 0 to 170 at steps of 10 , and in [13] where only four orientations are used.”
Robust Retinal Vessel Segmentation via Locally Adaptive Derivative Frames in Orientation Scores (2016, methodology): “[2] fail in the cases of micro-crossing and central reflex.”
FABC: Retinal Vessel Segmentation Using AdaBoost (2010, methodology): “The method presented in [5] also adopts supervised classification.”
Retinal Imaging and Image Analysis (2010, neutral): “5) with hundreds of papers published [74], [75].”
Ilastik: Interactive learning and segmentation toolkit (2011, methodology): “[12], adaptive local thresholding scheme from Jiang et al.”
An effective retinal blood vessel segmentation method using multi-scale line detection (2013, methodology): “It can be observed that both Staal and Soares et al. methods are ineffective in dealing with central reflex when assigning those pixels at the center of central reflex vessels as background.”
Weakly supervised histopathology cancer image segmentation and classification (2014, background): “A number of supervised approaches for medical image segmentation have also been proposed before, for example on histopathology images (Kong et al., 2011) and vasculature retinal images (Soares et al., 2006).”