Retinal Vessel Extraction Using First-Order Derivative of Gaussian and Morphological Processing

Assessment of blood vessels in retinal images is an important factor for many medical disorders. The changes in the retinal vessels due to the pathologies can be easily identified by segmenting the retinal vessels. Segmentation of retinal vessels is done to identify the early diagnosis of the disease like glaucoma, diabetic retinopathy, macular degeneration, hypertensive retinopathy and arteriosclerosis. In this paper, we propose two automatic blood vessel segmentation methods. The first proposed algorithm starts with the extraction of blood vessel centerline pixels. The final segmentation is obtained using an iterative region growing method that merges the contents of several binary images resulting from vessel width dependent modified morphological filters on normalized retinal images. In the second proposed algorithm the blood vessel is segmented using normalized modified morphological operations and neuro fuzzy classifier. Normalized morphological operations are used to enhance the vessels and neuro fuzzy classifier is used to segment retinal blood vessels. These methods are applied on the publicly available DRIVE database and the experimental results obtained by using green channel images have been presented and their results are compared with recently published methods. The results demonstrate that our algorithms are very effective methods to detect retinal blood vessels. DOI: http://dx.doi.org/10.11591/ijece.v4i3.5829

This paper presents an efficient method for automatic segmentation of blood vessels in retinal images. Specifically, we also delineate vascular intersections/crossovers. The proposed algorithm is composed of three steps: matched filter, fuzzy k-median (FKMED), and length filter. The segmentation results are compared with clinically generated vessel segmentation and are evaluated in terms of sensitivity and specificity. The results are encouraging and will be used for further application such as personal identification.

Automatic segmentation of the retinal vasculature is a first step in computer-assisted diagnosis and treatment planning. The extraction of retinal vessels in pediatric retinal images is challenging because of comparatively wide arterioles with a light streak running longitudinally along the vessel's center, the central vessel reflex. A new method for automatic segmentation was developed and tested. A supervised method for retinal vessel segmentation in the images of multi-ethnic school children was developed based on ensemble classifier of bootstrapped decision trees. A collection of dual Gaussian, second derivative of Gaussian and Gabor filters, along with the generalized multiscale line strength measure and morphological transformation is used to generate the feature vector. The feature vector encodes information to handle the normal vessels as well as the vessels with the central reflex. The methodology is evaluated on CHASE_DB1, a relatively new public retinal image database of multi-ethnic school children, which is a subset of retinal images from the Child Heart and Health Study in England (CHASE) dataset. The segmented retinal images from the CHASE_DB1 database produced best case accuracy, sensitivity and specificity of 0.96, 0.74 and 0.98, respectively, and worst case measures of 0.94, 0.67 and 0.98, respectively. A new retinal blood vessel segmentation algorithm was developed and tested with a shared database. The observed accuracy, speed, robustness and simplicity suggest that the algorithm may be a suitable tool for automated retinal image analysis in large population-based studies.

A comprehensive survey on segmentation techniques for retinal vessel segmentation

In this paper, we present an automatic method based on context-dependent characteristics for the detection and classification of arterial vessels and venous vessels in retinal fundus images. It provides a non-invasive opportunity and effective foundation for the diagnosis of several medical pathologies. In the proposed method, a combination of shifted filter responses is used, which can selectively respond to vessels. It achieves orientation selectivity by computing the weighted geometric mean of the output of a pool of Difference-of-Gaussian filters, whose supports are aligned in a collinear manner. We then configure two combinations of shifted filters, namely symmetric and asymmetric, that are selective for bars and bar-endings, respectively. We achieve vessel detection by summing up the responses of the two filters. Then we extract the morphology and topological characteristics based on the vessel segmentation, and specifically present context-dependent features of blood vessels, including the shape, structure, relative position, context information and other important features. Based on these features, we use JointBoost classifier to construct potential function for conditional random fields (CRFs) model, and train the labeled samples to classify arteriovenous blood vessels in retinal images. The training and testing data sets were prepared according to the results based on DRIVE dataset provided by Estrada et al. The experimental results show that the accuracy of the proposed method for vein and artery detection is 91.1% and 94.5%, respectively, which is superior to that of the state-of-the-art methods. It can be used as a clinical reference for computer-assisted quantitative analysis of fundus images.

Some ocular and cardiovascular diseases can be detected through the increased tortuosity of retinal blood vessels. Objective tortuosity measures can be obtained from digital image analysis of a retinography. This study tested a set of local tortuosity indices under a change in the frame center (macula, optic disc) of the eye fundus image. We illustrate the effects of such a change on 40 pairs of vessels evaluated with eight tortuosity indices. We show that the frame center change caused significant differences in the mean values of the vast majority of the tortuosity indices analyzed. The index defined as the ratio of the curvature to the arc length of a vessel segment proved to be the most robust in relation to a frame center change. Experimental results obtained from the analysis of clinical images are provided and discussed.

Many chronic eye diseases can be conveniently investigated by observing structural changes in retinal blood vessel diameters. However, detecting changes in an accurate manner in face of interfering pathologies is a challenging task. The task is generally performed through an automatic computerized process. The literature shows that powerful methods have already been proposed to identify vessels in retinal images. Though a significant progress has been achieved toward methods to separate blood vessels from the uneven background, the methods still lack the necessary sensitivity to segment fine vessels. Recently, a multi-scale line-detector method proved its worth in segmenting thin vessels. This paper presents modifications to boost the sensitivity of this multi-scale line detector. First, a varying window size with line-detector mask is suggested to detect small vessels. Second, external orientations are fed to steer the multi-scale line detectors into alignment with flow directions. Third, optimal weights are suggested for weighted linear combinations of individual line-detector responses. Fourth, instead of using one global threshold, a hysteresis threshold is proposed to find a connected vessel tree. The overall impact of these modifications is a large improvement in noise removal capability of the conventional multi-scale line-detector method while finding more of the thin vessels. The contrast-sensitive steps are validated using a publicly available database and show considerable promise for the suggested strategy.

Microvascular reactivity in rehabilitating cardiac patients based on measurements of retinal blood vessel diameters

A novel automated method for the segmentation of blood vessels in retinal images based upon enhancement and maximum entropy thresholding is proposed. Blood vessels usually have poor local contrast. Before thresholding fundus images, several matched filters are employed to enhance the contrast of blood vessels. The matched-filter-response (MFR) image is processed by a thresholding scheme in order to extract blood vessels from the background. Then, the proposed thresholding approach evaluates two-dimensional entropies based on the gray level-gradient cooccurrence matrix. The 2D threshold vector that maximizes the edge class entropies is selected. This thresholding method utilizes the information of gray level and gradient in the MFR image. It is found that the proposed algorithm works well in normal or abnormal retinal images.

Slope Chain Code-based scale-independent tortuosity measurement on retinal vessels.

Imaging of retinal blood vessels may assist in the diagnosis and monitoring of diseases such as glaucoma, diabetic retinopathy, and hypertension. However, close examination reveals that the contrast and apparent diameter of vessels are dependent on the wavelength of the illuminating light. In this study multispectral images of large arteries and veins within enucleated swine eyes are obtained with a modified fundus camera by use of intravitreal illumination. The diameters of selected vessels are measured as a function of wavelength by cross-sectional analysis. A fixed scale with spectrally independent dimension is placed above the retina to isolate the chromatic effects of the imaging system and eye. Significant apparent differences between arterial and venous diameters are found, with larger diameters observed at shorter wavelengths. These differences are due primarily to spectral absorption in the cylindrical blood column.

The aim of this study was to examine the effects of elcatonin, a synthetic derivative of eel calcitonin, on rat retinal blood vessels, and to determine how diabetes affects the retinal vascular responses. Ocular fundus images were captured with an original high-resolution digital fundus camera in vivo. The retinal vascular responses were evaluated by measuring the diameter of retinal blood vessels contained in the digital images. Both systemic blood pressure and heart rate were continuously recorded. Elcatonin increased the diameter of retinal blood vessels but decreased mean blood pressure in a dose-dependent manner, whereas it had no significant effect on heart rate. A diminished retinal vasodilator response and significant pressor response to elcatonin were observed in rats injected intravenously with N(G)-nitro-L-arginine methyl ester, a nitric oxide (NO) synthase inhibitor. Intravitreal injection of indomethacin, a non-selective cyclooxygenase (COX) inhibitor, and SQ22536, an adenylyl cyclase inhibitor, markedly attenuated the vasodilator effects of elcatonin on retinal blood vessels. The retinal vasodilator responses to elcatonin were unaffected 2 weeks after the induction of diabetes by a combination of streptozotocin treatment and D-glucose feeding. These results suggest that elcatonin dilates rat retinal blood vessels via NO- and COX-dependent mechanisms and that the adenylyl cyclase-adenosine 3',5'-cyclic monophosphate system plays a major role in the vasodilator mechanisms. The retinal vasodilatory effects of elcatonin seem to be preserved at early stages of diabetes.

To develop a robust and effective design, the proposed research uses a model that analyses blood vessels in retinal images by leveraging Deep Learning and Image Processing techniques. Deep learning, one of the AI techniques, has experienced rapid growth and is widely used in the medical field to analyse medical images, driving advancements in technology and medicine. The U-Net semantic segmentation neural network is the primary deep learning model used in our study. Training data consists of a set of retinal images, and the model’s performance is assessed on the training set. Once testing is complete, the results help evaluate the accuracy and effectiveness of the model and the techniques utilised in this research. This study indicates that deep learning segmentation techniques can offer valuable insights beyond standard pixel-based detection techniques. The proposed method gives a better understanding of retinal blood vessel analysis. Researchers used the DRIVE dataset for this research. It has 20,512x512 training and testing images for the model’s training and testing. The neural network's blood vessel shape recognition helps diagnose eye diseases. Diseases include hypertension, diabetic retinopathy, etc. The neural network's effectiveness makes the system suited for real-time blood vessel detection. This paper accurately mapped major and minor blood arteries. Thus, 96.53% of this research succeeded. The mean intersection over union is 8184. This exceeds the previous E-NET model of 7744.

The low-contrast and narrow blood vessels in retinal images are difficult to be extracted but useful in revealing certain systemic disease. Motivated by the goals of improving detection of such vessels, we propose the radial projection method to locate the vessel centerlines. Then the supervised classification is used for extracting the major structures of vessels. The final segmentation is obtained by the union of the two types of vessels after removal schemes. Our approach is tested on the STARE database, the results demonstrate that our algorithm can yield better segmentation.

Hypertensive Retinopathy (HR) is an eye disease occurs due to high blood pressure. This disease primarily damages the blood vessels in retina by altering the vessel caliber. The damage is evaluated by calculation of Arterio-venous Ratio (AVR), which quantifies the change in diameter of retinal blood vessels. It is basically the ratio of arterioles to venules diameter. In order to calculate AVR for an automatic diagnosis of HR, the vascular characterization is an essential step. This paper presents an automatic system for retinal vessel classification which is based on novel combination of intensity and gradient based features. The automated system first segments the retinal vessels, then extracts features and finally classifies the vessels as arteries and veins. The proposed system is tested and validated on locally gathered fundus image database, taken from AFIO, Pakistan. The proposed approach provides an accuracy of 93.49 % and 93.47 % for veins and arteries, respectively.