Ridge-based vessel segmentation in color images of the retina

By Joes Staal, Michael David Abràmoff, Meindert Niemeijer, Max A. Viergever, B. van Ginneken. IEEE Transactions on Medical Imaging, 2004

4,272 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/ac9748ea3945eb970cc32a37db7cfdfd0f22e74c

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

Learning Separable Filters (2013, methodology): “• The DRIVE dataset [34] is a set of 40 retinal scans captured for the diagnosis of various diseases.”
A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images (2016, methodology): “The other technique is ‘leave-one-out’ [22], [25], in which each image is tested using a network model trained on the other 19 images.”
Computer Methods and Programs in Biomedicine (positive): “93 20 images (DRIVE database [68] ) Acc = 0 .”
Deep Retinal Image Understanding (2016, methodology): “We also retrain HED [24] (state of the art in generic contour detection with CNNs) on DRIVE and STARE using their public code.”
Segmenting Retinal Blood Vessels With Deep Neural Networks (2016, methodology): “For instance, though the method described in [9] ultimately engages learning, it relies on multiple (a dozen or more) features based on domain knowledge.”
An Active Contour Model for Segmenting and Measuring Retinal Vessels (2009, methodology): “The use of pattern recognition techniques [7], [8] allows for relatively sophisticated local appearance modelling.”
An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation (2012, methodology): “Staal et al. [5] used ridge profiles to compute 27 features for each pixel and applied a feature selection scheme to pick those which result in better class separability by a kNN classifier.”
Generative Adversarial Network in Medical Imaging: A Review (2018, neutral): “D43 Staal et al. (2004) DRIVE Blood vessels segmentation Eye Fundus imaging”
Automatic detection of microaneurysms in color fundus images (2007, methodology): “We therefore propose a postprocessing step, in order to remove all candidates situated on vessels (for vessel detection, see Zana and Klein, 2001; Staal et al., 2004; Walter and Klein, 2005).”
Blood Vessel Segmentation of Fundus Images by Major Vessel Extraction and Subimage Classification (2015, methodology): “The approach in [25] improved this method by applying ridge-based vessel detection.”
Recurrent residual U-Net for medical image segmentation (2019, background): “The size of each original image is 565 × 584 pixels.(47) To develop a square dataset, the images are cropped to only contain the data from columns 9 to 574, which then makes each image size 565 × 565 pixels.”
Synthetic Medical Images from Dual Generative Adversarial Networks (2017, methodology): “To generate a high quality synthetic dataset, we propose the use of two GANs, breaking down the generation problem into two parts: We illustrate the process with retinal fundi images.”
Robust Retinal Vessel Segmentation via Locally Adaptive Derivative Frames in Orientation Scores (2016, methodology): “Even with only 4 orientations, the LAD-OS approach is able to reach the AUC values of 0.9537 and 0.9692, compared to 0.9538 and 0.9623 of the LID-OS approach with 34 orientations on the DRIVE and STARE datasets, respectively.”