Abstract—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. Index Terms—Fundus, Gabor, pattern classification, retina, vessel segmentation, wavelet.

Abstract—This paper presents a set of algorithms for robust detection of vasculature in noisy retinal video images. Three methods are studied for effective handling of outliers. The first method is based on Huber’s censored likelihood ratio test. The second is based on the use of a-trimmed test statistic. The third is based on robust model selection algorithms. All of these algorithms rely on a mathematical model for the vasculature that accounts for the expected variations in intensity/texture profile, width, orientation, scale, and imaging noise. These unknown parameters are estimated implicitly within a robust detection and estimation framework. The proposed algorithms are also useful as nonlinear vessel enhancement filters. The proposed algorithms were evaluated over carefully constructed phantom images, where the ground truth is known a priori, as well as clinically recorded images for which the ground truth was manually compiled. A comparative evaluation of the proposed approaches is presented. Collectively, these methods outperformed prior approaches based on Chaudhuri et al. (1989) matched filtering, as well as the verification methods used by prior exploratory tracing algorithms, such as the work of Can et al. (1999). The Huber censored likelihood test yielded the best overall improvement, with a 145.7 % improvement over the exploratory tracing algorithm, and a 43.7 % improvement in detection rates over the matched filter. Index Terms—Hypothesis testing, mathematical models of vasculature, retinal fundus images, robust model selection, vasculature detection and segmentation, vessel enhancement, vessel segmentation. I.

Motivated by the goals of improving detection of low-contrast and narrow vessels and eliminating false detections at non-vascular structures, a new technique is presented for extracting vessels in retinal images. The core of the technique is a new likelihood ratio test that combines matchedfilter responses, confidence measures and vessel boundary measures. Matched filter responses are derived in scale-space to extract vessels of widely varying widths. A vessel confidence measure is defined as a projection of a vector formed from a normalized pixel neighborhood onto a normalized ideal vessel profile. Vessel boundary measures and associated confidences are computed at potential vessel boundaries. Combined, these responses form a 6-dimensional measurement vector at each pixel. A training technique is used to develop a mapping of this vector to a likelihood ratio that measures the "vesselness" at each pixel. Results comparing this vesselness measure to matched filters alone and to measures based on the Hessian of intensities show substantial improvements both qualitatively and quantitatively. The Hessian can be used in place of the matched filter to obtain similar but less-substantial improvements or to steer the matched filter by preselecting kernel orientations. Finally, the new vesselness likelihood ratio is embedded into a vessel tracing framework, resulting in an e#cient and e#ective vessel centerline extraction algorithm.

Abstract not found

Motivated by the goals of improving detection of low-contrast and narrow vessels and eliminating false detections at non-vascular structures, a new technique is presented for extracting vessels in retinal images. The core of the technique is a new likelihood ratio test that combines matched filter responses, confidence measures and vessel boundary measures. Matched filter responses are derived in scale-space to extract vessels of widely varying widths. A vessel confidence measure is defined as a projection of a vector formed from a normalized pixel neighborhood onto a normalized ideal vessel profile. Vessel boundary measures and associated confidences are computed at potential vessel boundaries. Combined, these responses form a 6-dimensional measurement vector at each pixel. A learning technique is applied to map this vector to a likelihood ratio that measures the "vesselness" at each pixel. Results comparing this vesselness measure to matched filters alone and to measures based on the intensity Hessian show substantial improvements both qualitatively and quantitatively. When the Hessian is used in place of the matched filter, similar but less-substantial improvements are obtained. Finally, the new vesselness likelihood ratio is embedded into a vessel tracing framework, resulting in an e#cient and e#ective vessel extraction algorithm.

Abstract—An automated method is presented for selecting optimal parameter settings for vessel/neurite segmentation algorithms using the minimum description length principle and a recursive random search algorithm. It trades off a probabilistic measure of image-content coverage against its conciseness. It enables nonexpert users to select parameter settings objectively, without knowledge of underlying algorithms, broadening the applicability of the segmentation algorithm, and delivering higher morphometric accuracy. It enables adaptation of parameters across batches of images. It simplifies the user interface to just one optional parameter and reduces the cost of technical support. Finally, the method is modular, extensible, and amenable to parallel computation. The method is applied to 223 images of human retinas and cultured neurons, from four different sources, using a single segmentation algorithm with eight parameters. Improvements in segmentation quality compared to default settings using 1000 iterations ranged from 4.7%–21%. Paired-tests showed that improvements are statistically significant @ H HHHSA. Most of the improvement occurred in the first 44 iterations. Improvements in description lengths and agreement with the ground truth were strongly correlated @ aHUVA. Index Terms—Image segmentation, minimum description length, optimization methods, segmentation evaluation. I.

Unsupervised methods for automatic vessel segmentation from retinal images are attractive when only small datasets, with associated ground truth markings, are available. We present an unsupervised, curvature-based method for segmenting the complete vessel tree from colour retinal images. The vessels are modeled as trenches and the medial lines of the trenches are extracted using the curvature information derived from a novel curvature estimate. The complete vessel structure is then extracted using a modified region growing method. Testresults of the algorithm using the DRIVE dataset are superior to previously reported unsupervised methods and comparable to those obtained with the supervised methods in [1],[2]. Index Terms — retina, curvature, vessel segmentation, unsupervised, ridge.

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 continuous twodimensional Morlet wavelet transform responses taken at multiple scales. The Morlet 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 [34] and STARE [16] databases of manually labeled non-mydriatic images. On the DRIVE database, it achieves an area under the receiver operating characteristic (ROC) curve of 0.9598 and an accuracy of 0.9467 versus 0.9473 for a second human observer.

Abstract. Retinal vessel segmentation is an essential step of the diagnoses of various eye diseases. In this paper, we propose an automatic, efficient and unsupervised method based on gradient matrix, the normalized cut criterion and tracking strategy. Making use of the gradient matrix of the Lucas-Kanade equation, which consists of only the first order derivatives, the proposed method can detect a candidate window where a vessel possibly exists. The normalized cut criterion, which measures both the similarity within groups and the dissimilarity between groups, is used to search a local intensity threshold to segment the vessel in a candidate window. The tracking strategy makes it possible to extract thin vessels without being corrupted by noise. Using a multi-resolution segmentation scheme, vessels with different widths can be segmented at different resolutions, although the window size is fixed. Our method is tested on a public database. It is demonstrated to be efficient and insensitive to initial parameters. 1

Automated image analysis algorithms are presented for detection and classification of changes in longitudinal time-series of color retinal fundus images. They are applicable to clinical practice, quantitative scoring of clinical trials, computer-assisted reading centers, and training. This work focuses on diabetes-related changes, although the techniques have broader applicability. Retinal features, including the vasculature, vessel branching/crossover locations, optic disk, and fovea are extracted automatically. The images are registered to sub-pixel accuracy using a 12-dimensional mapping that accounts for the unknown retinal curvature and camera parameters. The images are corrected for non-uniform illumination using a robust homomorphic surface fitting algorithm. The changes in non-vascular regions are segmented using an algorithm that is robust to relevant artifacts such as dust particles in the optical path. They are classified into five clinically significant categories using a Bayesian algorithm constrained by Markov Random Fields. A flicker animation overlaid with change analysis results allows qualitative and quantitative assessment by the user. A multi-observer validation on 43 image pairs from 22 eyes involving non-proliferative and proliferative diabetic retinopathies, showed a 96.83 % change detection rate, a 3.17 % miss rate, and a 17.65 % false alarm rate. The performance in correctly classifying the changes was 97.39 %.