Retinal vessel classification: sorting arteries and veins

A Hybrid Method to Enhance Thick and Thin Vessels for Blood Vessel Segmentation

Retinal blood vessels have been presented to contribute confirmation with regard to tortuosity, branching angles, or change in diameter as a result of ophthalmic disease. Although many enhancement filters are extensively utilized, the Jerman filter responds quite effectively at vessels, edges, and bifurcations and improves the visualization of structures. In contrast, curvelet transform is specifically designed to associate scale with orientation and can be used to recover from noisy data by curvelet shrinkage. This paper describes a method to improve the performance of curvelet transform further. A distinctive fusion of curvelet transform and the Jerman filter is presented for retinal blood vessel segmentation. Mean-C thresholding is employed for the segmentation purpose. The suggested method achieves average accuracies of 0.9600 and 0.9559 for DRIVE and CHASE_DB1, respectively. Simulation results establish a better performance and faster implementation of the suggested scheme in comparison with similar approaches seen in the literature.

Differential artery-vein analysis in quantitative retinal imaging: a review

Quantitative retinal imaging is essential for eye disease detection, staging classification, and treatment assessment. It is known that different eye diseases or severity stages can affect the artery and vein systems in different ways. Therefore, differential artery-vein (AV) analysis can improve the performance of quantitative retinal imaging. In this article, we provide a brief summary of technical rationales and clinical applications of differential AV analysis in fundus photography, optical coherence tomography (OCT), and OCT angiography (OCTA).

Multi-Task Siamese Network for Retinal Artery/Vein Separation via Deep Convolution Along Vessel

Vascular tree disentanglement and vessel type classification are two crucial steps of the graph-based method for retinal artery-vein (A/V) separation. Existing approaches treat them as two independent tasks and mostly rely on ad hoc rules (e.g. change of vessel directions) and hand-crafted features (e.g. color, thickness) to handle them respectively. However, we argue that the two tasks are highly correlated and should be handled jointly since knowing the A/V type can unravel those highly entangled vascular trees, which in turn helps to infer the types of connected vessels that are hard to classify based on only appearance. Therefore, designing features and models isolatedly for the two tasks often leads to a suboptimal solution of A/V separation. In view of this, this paper proposes a multi-task siamese network which aims to learn the two tasks jointly and thus yields more robust deep features for accurate A/V separation. Specifically, we first introduce Convolution Along Vessel (CAV) to extract the visual features by convolving a fundus image along vessel segments, and the geometric features by tracking the directions of blood flow in vessels. The siamese network is then trained to learn multiple tasks: i) classifying A/V types of vessel segments using visual features only, and ii) estimating the similarity of every two connected segments by comparing their visual and geometric features in order to disentangle the vasculature into individual vessel trees. Finally, the results of two tasks mutually correct each other to accomplish final A/V separation. Experimental results demonstrate that our method can achieve accuracy values of 94.7%, 96.9%, and 94.5% on three major databases (DRIVE, INSPIRE, WIDE) respectively, which outperforms recent state-of-the-arts.

Retinal Vascular Network Topology Reconstruction and Artery/Vein Classification via Dominant Set Clustering

The estimation of vascular network topology in complex networks is important in understanding the relationship between vascular changes and a wide spectrum of diseases. Automatic classification of the retinal vascular trees into arteries and veins is of direct assistance to the ophthalmologist in terms of diagnosis and treatment of eye disease. However, it is challenging due to their projective ambiguity and subtle changes in appearance, contrast, and geometry in the imaging process. In this paper, we propose a novel method that is capable of making the artery/vein (A/V) distinction in retinal color fundus images based on vascular network topological properties. To this end, we adapt the concept of dominant set clustering and formalize the retinal blood vessel topology estimation and the A/V classification as a pairwise clustering problem. The graph is constructed through image segmentation, skeletonization, and identification of significant nodes. The edge weight is defined as the inverse Euclidean distance between its two end points in the feature space of intensity, orientation, curvature, diameter, and entropy. The reconstructed vascular network is classified into arteries and veins based on their intensity and morphology. The proposed approach has been applied to five public databases, namely INSPIRE, IOSTAR, VICAVR, DRIVE, and WIDE, and achieved high accuracies of 95.1%, 94.2%, 93.8%, 91.1%, and 91.0%, respectively. Furthermore, we have made manual annotations of the blood vessel topologies for INSPIRE, IOSTAR, VICAVR, and DRIVE datasets, and these annotations are released for public access so as to facilitate researchers in the community.

Artery/Vein Vessel Tree Identification in Near-Infrared Reflectance Retinographies

An accurate identification of the retinal arteries and veins is a relevant issue in the development of automatic computer-aided diagnosis systems that facilitate the analysis of different relevant diseases that affect the vascular system as diabetes or hypertension, among others. The proposed method offers a complete analysis of the retinal vascular tree structure by its identification and posterior classification into arteries and veins using optical coherence tomography (OCT) scans. These scans include the near-infrared reflectance retinography images, the ones we used in this work, in combination with the corresponding histological sections. The method, firstly, segments the vessel tree and identifies its characteristic points. Then, Global Intensity-Based Features (GIBS) are used to measure the differences in the intensity profiles between arteries and veins. A k-means clustering classifier employs these features to evaluate the potential of artery/vein identification of the proposed method. Finally, a post-processing stage is applied to correct misclassifications using context information and maximize the performance of the classification process. The methodology was validated using an OCT image dataset retrieved from 46 different patients, where 2,392 vessel segments and 97,294 vessel points were manually labeled by an expert clinician. The method achieved satisfactory results, reaching a best accuracy of 93.35% in the identification of arteries and veins, being the first proposal that faces this issue in this image modality.

Artery/vein classification of retinal vessels using classifiers fusion

The morphological changes in retinal blood vessels indicate cardiovascular diseases and consequently those diseases lead to ocular complications such as Hypertensive Retinopathy. One of the significant clinical findings related to this ocular abnormality is alteration of width of vessel. The classification of retinal vessels into arteries and veins in eye fundus images is a relevant task for the automatic assessment of vascular changes. This paper presents an important approach to solve this problem by means of feature ranking strategies and multiple classifiers decision-combination scheme that is specifically adapted for artery/vein classification. For this, three databases are used with a local dataset of 44 images and two publically available databases, INSPIRE-AVR containing 40 images and VICAVR containing 58 images. The local database also contains images with pathologically diseased structures. The performance of the proposed system is assessed by comparing the experimental results with the gold standard estimations as well as with the results of previous methodologies, achieving promising classification performance, with an over all accuracy of 90.45%, 93.90% and 87.82%, in retinal blood vessel separation for Local, INSPIRE-AVR and VICAVR dataset, respectively.

Artery-vein segmentation in fundus images using a fully convolutional network

Epidemiological studies demonstrate that dimensions of retinal vessels change with ocular diseases, coronary heart disease and stroke. Different metrics have been described to quantify these changes in fundus images, with arteriolar and venular calibers among the most widely used. The analysis often includes a manual procedure during which a trained grader differentiates between arterioles and venules. This step can be time-consuming and can introduce variability, especially when large volumes of images need to be analyzed. In light of the recent successes of fully convolutional networks (FCNs) applied to biomedical image segmentation, we assess its potential in the context of retinal artery-vein (A/V) discrimination. To the best of our knowledge, a deep learning (DL) architecture for simultaneous vessel extraction and A/V discrimination has not been previously employed. With the aim of improving the automation of vessel analysis, a novel application of the U-Net semantic segmentation architecture (based on FCNs) on the discrimination of arteries and veins in fundus images is presented. By utilizing DL, results are obtained that exceed accuracies reported in the literature. Our model was trained and tested on the public DRIVE and HRF datasets. For DRIVE, measuring performance on vessels wider than two pixels, the FCN achieved accuracies of 94.42% and 94.11% on arteries and veins, respectively. This represents a decrease in error of 25% over the previous state of the art reported by Xu et al. (2017). Additionally, we introduce the HRF A/V ground truth, on which our model achieves 96.98% accuracy on all discovered centerline pixels. HRF A/V ground truth validated by an ophthalmologist, predicted A/V annotations and evaluation code are available at https://github.com/rubenhx/av-segmentation.

Color Fundus Image Guided Artery-Vein Differentiation in Optical Coherence Tomography Angiography

Purpose

This study aimed to develop a method for automated artery-vein classification in optical coherence tomography angiography (OCTA), and to verify that differential artery-vein analysis can improve the sensitivity of OCTA detection and staging of diabetic retinopathy (DR).

Methods

For each patient, the color fundus image was used to guide the artery-vein differentiation in the OCTA image. Traditional mean blood vessel caliber (m-BVC) and mean blood vessel tortuosity (m-BVT) in OCTA images were quantified for control and DR groups. Artery BVC (a-BVC), vein BVC (v-BVC), artery BVT (a-BVT), and vein BVT (a-BVT) were calculated, and then the artery-vein ratio (AVR) of BVC (AVR-BVC) and AVR of BVT (AVR-BVT) were quantified for comparative analysis. Sensitivity, specificity, and accuracy were used as performance metrics of artery-vein classification. One-way, multilabel ANOVA with Bonferroni's test and Student's t-test were employed for statistical analysis.

Results

Forty eyes of 20 control subjects and 80 eyes of 48 NPDR patients (18 mild, 16 moderate, and 14 severe NPDR) were evaluated in this study. The color fundus image-guided artery-vein differentiation reliably identified individual arteries and veins in OCTA. AVR-BVC and AVR-BVT provided significant (P < 0.001) and moderate (P < 0.05) improvements, respectively, in detecting and classifying NPDR stages, compared with traditional m-BVC analysis.

Conclusions

Color fundus image-guided artery-vein classification provides a feasible method to differentiate arteries and veins in OCTA. Differential artery-vein analysis can improve the sensitivity of OCTA detection and classification of DR. AVR-BVC is the most-sensitive feature, which can classify control and mild NPDR, providing a quantitative biomarker for objective detection of early DR.

A Review on the Extraction of Quantitative Retinal Microvascular Image Feature

Digital image processing is one of the most widely used computer vision technologies in biomedical engineering. In the present modern ophthalmological practice, biomarkers analysis through digital fundus image processing analysis greatly contributes to vision science. This further facilitates developments in medical imaging, enabling this robust technology to attain extensive scopes in biomedical engineering platform. Various diagnostic techniques are used to analyze retinal microvasculature image to enable geometric features measurements such as vessel tortuosity, branching angles, branching coefficient, vessel diameter, and fractal dimension. These extracted markers or characterized fundus digital image features provide insights and relates quantitative retinal vascular topography abnormalities to various pathologies such as diabetic retinopathy, macular degeneration, hypertensive retinopathy, transient ischemic attack, neovascular glaucoma, and cardiovascular diseases. Apart from that, this noninvasive research tool is automated, allowing it to be used in large-scale screening programs, and all are described in this present review paper. This paper will also review recent research on the image processing-based extraction techniques of the quantitative retinal microvascular feature. It mainly focuses on features associated with the early symptom of transient ischemic attack or sharp stroke.

Automated classification and quantitative analysis of arterial and venous vessels in fundus images

It is known that retinopathies may affect arteries and veins differently. Therefore, reliable differentiation of arteries and veins is essential for computer-aided analysis of fundus images. The purpose of this study is to validate one automated method for robust classification of arteries and veins (A-V) in digital fundus images. We combine optical density ratio (ODR) analysis and blood vessel tracking algorithm to classify arteries and veins. A matched filtering method is used to enhance retinal blood vessels. Bottom hat filtering and global thresholding are used to segment the vessel and skeleton individual blood vessels. The vessel tracking algorithm is used to locate the optic disk and to identify source nodes of blood vessels in optic disk area. Each node can be identified as vein or artery using ODR information. Using the source nodes as starting point, the whole vessel trace is then tracked and classified as vein or artery using vessel curvature and angle information. 50 color fundus images from diabetic retinopathy patients were used to test the algorithm. Sensitivity, specificity, and accuracy metrics were measured to assess the validity of the proposed classification method compared to ground truths created by two independent observers. The algorithm demonstrated 97.52% accuracy in identifying blood vessels as vein or artery. A quantitative analysis upon A-V classification showed that average A-V ratio of width for NPDR subjects with hypertension decreased significantly (43.13%).

Combining ODR and Blood Vessel Tracking for Artery-Vein Classification and Analysis in Color Fundus Images

Purpose

This study aims to develop a fully automated algorithm for artery–vein (A-V) and arteriole-venule classification and to quantify the effect of hypertension on A-V caliber and tortuosity ratios of nonproliferative diabetic retinopathy (NPDR) patients.

Methods

We combine an optical density ratio (ODR) analysis and blood vessel tracking (BVT) algorithm to classify arteries and veins and arterioles and venules. An enhanced blood vessel map and ODR analysis are used to determine the blood vessel source nodes. The whole vessel map is then tracked beginning from the source nodes and classified as vein (venule) or artery (arteriole) using vessel curvature and angle information. Fifty color fundus images from NPDR patients are used to test the algorithm. Sensitivity, specificity, and accuracy metrics are measured to validate the classification method compared to ground truths.

Results

The combined ODR-BVT method demonstrates 97.06% accuracy in identifying blood vessels as vein or artery. Sensitivity and specificity of A-V identification are 97.58%, 97.81%, and 95.89%, 96.68%, respectively. Comparative analysis revealed that the average A-V caliber and tortuosity ratios of NPDR patients with hypertension have 48% and 15.5% decreases, respectively, compared to that of NPDR patients without hypertension.

Conclusions

Automated A-V classification has been achieved by combined ODR-BVT analysis. Quantitative analysis of color fundus images verified robust performance of the A-V classification. Comparative quantification of A-V caliber and tortuosity ratios provided objective biomarkers to differentiate NPDR groups with and without hypertension.

Translational Relevance

Automated A-V classification can facilitate quantitative analysis of retinal vascular distortions due to diabetic retinopathy and other eye conditions and provide increased sensitivity for early detection of eye diseases.

Multiscale self-quotient filtering for an improved unsupervised retinal blood vessels characterisation

Digital images often suffer from contrast variability and non-uniform illumination, which seriously affect the evaluation of biomarkers such as the arteriolar to venular ratio. This biomarker provides valuable information about many pathological conditions such as diabetes, hypertension etc. Hence, in order to efficiently estimate the biomarkers, correct classification of retinal vessels extracted from digital images, into arterioles and venules is an important research problem. This paper presents an unsupervised retinal vessel classification approach which utilises the multiscale self-quotient filtering, to pre-process the input image before extracting the discriminating features. Thereafter the squared-loss mutual information clustering method is used for the unsupervised classification of retinal vessels. The proposed vessel classification method was evaluated on the publicly available DRIVE and INSPIRE-AVR databases. The proposed unclassified framework resulted in 93.2 and 88.9% classification rate in zone B for the DRIVE and the INSPIRE-AVR dataset respectively. The proposed method outperformed other tested methods available in the literature. Retinal vessel classification, in an unsupervised setting is a challenging task. The present framework provided high classification rate and therefore holds a great potential to aid computer aided diagnosis and biomarker research.

A review on automatic analysis techniques for color fundus photographs

In this paper, we give a review on automatic image processing tools to recognize diseases causing specific distortions in the human retina. After a brief summary of the biology of the retina, we give an overview of the types of lesions that may appear as biomarkers of both eye and non-eye diseases. We present several state-of-the-art procedures to extract the anatomic components and lesions in color fundus photographs and decision support methods to help clinical diagnosis. We list publicly available databases and appropriate measurement techniques to compare quantitatively the performance of these approaches. Furthermore, we discuss on how the performance of image processing-based systems can be improved by fusing the output of individual detector algorithms. Retinal image analysis using mobile phones is also addressed as an expected future trend in this field.

Artery/vein classification of retinal blood vessels using feature selection

Automated classification of retinal vessels in fundus images is the first step towards measurement of retinal characteristics that can be used to screen and diagnose vessel abnormalities for cardiovascular and retinal disorders. This paper presents a novel approach to vessel classification to compute the artery/vein ratio (AVR) for all blood vessel segments in the fundus image. The features extracted are then subjected to a selection procedure using Random Forests (RF) where the features that contribute most to classification accuracy are chosen as input to a polynomial kernel Support Vector Machine (SVM) classifier. The most dominant feature was found to be the vessel information obtained from the Light plane of the LAB color space. The SVM is then subjected to one time training using 10-fold cross validation on images randomly selected from the VICAVR dataset before testing on an independent test dataset, derived from the same database. An Area Under the ROC Curve (AUC) of 97.2% was obtained on an average of 100 runs of the algorithm. The proposed algorithm is robust due to the feature selection procedure, and it is possible to get similar accuracies across many datasets.

Modulation of retinal image vasculature analysis to extend utility and provide secondary value from optical coherence tomography imaging

Retinal image analysis is emerging as a key source of biomarkers of chronic systemic conditions affecting the cardiovascular system and brain. The rapid development and increasing diversity of commercial retinal imaging systems present a challenge to image analysis software providers. In addition, clinicians are looking to extract maximum value from the clinical imaging taking place. We describe how existing and well-established retinal vasculature segmentation and measurement software for fundus camera images has been modulated to analyze scanning laser ophthalmoscope retinal images generated by the dual-modality Heidelberg SPECTRALIS(®) instrument, which also features optical coherence tomography.

Retinal Artery-Vein Classification via Topology Estimation

We propose a novel, graph-theoretic framework for distinguishing arteries from veins in a fundus image. We make use of the underlying vessel topology to better classify small and midsized vessels. We extend our previously proposed tree topology estimation framework by incorporating expert, domain-specific features to construct a simple, yet powerful global likelihood model. We efficiently maximize this model by iteratively exploring the space of possible solutions consistent with the projected vessels. We tested our method on four retinal datasets and achieved classification accuracies of 91.0%, 93.5%, 91.7%, and 90.9%, outperforming existing methods. Our results show the effectiveness of our approach, which is capable of analyzing the entire vasculature, including peripheral vessels, in wide field-of-view fundus photographs. This topology-based method is a potentially important tool for diagnosing diseases with retinal vascular manifestation.

An easy method to differentiate retinal arteries from veins by spectral domain optical coherence tomography: retrospective, observational case series

Background

Recently it was shown that retinal vessel diameters could be measured using spectral domain optical coherence tomography (OCT). It has also been suggested that retinal vessels manifest different features on spectral domain OCT (SD-OCT) depending on whether they are arteries or veins. Our study was aimed to present a reliable SD-OCT assisted method of differentiating retinal arteries from veins.

Methods

Patients who underwent circular OCT scans centred at the optic disc using a Spectralis OCT (Heidelberg Engineering, Heidelberg, Germany) were retrospectively reviewed. Individual retinal vessels were identified on infrared reflectance (IR) images and given unique labels for subsequent grading. Vessel types (artery, vein or uncertain) assessed by IR and/or fluorescein angiography (FA) were referenced as ground truth. From OCT, presence/absence of the hyperreflective lower border reflectivity feature was assessed. Presence of this feature was considered indicative for retinal arteries and compared with the ground truth.

Results

A total of 452 vessels from 26 eyes of 18 patients were labelled and 398 with documented vessel type (302 by IR and 96 by FA only) were included in the study. Using SD-OCT, 338 vessels were assigned a final grade, of which, 86.4% (292 vessels) were classified correctly. Forty three vessels (15 arteries and 28 veins) that IR failed to differentiate were correctly classified by SD-OCT. When using only IR based ground truth for vessel type the SD-OCT based classification approach reached a sensitivity of 0.8758/0.9297, and a specificity of 0.9297/0.8758 for arteries/veins, respectively.

Conclusion

Our method was able to classify retinal arteries and veins with a commercially available SD-OCT alone, and achieved high classification performance. Paired with OCT based vessel measurements, our study has expanded the potential clinical implication of SD-OCT in evaluation of a variety of retinal and systemic vascular diseases.