Vessel Pixels Research Articles

A supervised blood vessel segmentation technique for digital Fundus images using Zernike Moment based features.

This paper proposes a new supervised method for blood vessel segmentation using Zernike moment-based shape descriptors. The method implements a pixel wise classification by computing a 11-D feature vector comprising of both statistical (gray-level) features and shape-based (Zernike moment) features. Also the feature set contains optimal coefficients of the Zernike Moments which were derived based on the maximum differentiability between the blood vessel and background pixels. A manually selected training points obtained from the training set of the DRIVE dataset, covering all possible manifestations were used for training the ANN-based binary classifier. The method was evaluated on unknown test samples of DRIVE and STARE databases and returned accuracies of 0.945 and 0.9486 respectively, outperforming other existing supervised learning methods. Further, the segmented outputs were able to cover thinner blood vessels better than previous methods, aiding in early detection of pathologies.

Robust retinal optic disc and optic cup segmentation via stationary wavelet transform and maximum vessel pixel sum

Glaucoma leads to irreversible blindness and its diagnosis relies heavily on cup to disc ratio. This ratio can be calculated by segmenting the optic disc (OD) and optic cup (OC) from the fundus image. However, the segmentation of OD and OC is a complex process and should be carried out with utmost accuracy to screen the risk of glaucoma. In order to circumvent this complexity, this study presents two novel algorithms to segment the OD and OC boundaries, respectively by creating an automated region of interest (ROI). The first algorithm uses the inverse polar transform to segment OD where the horizontal coefficients of sixth level decomposition Daubechies stationary wavelet transform of ROI is processed. The second algorithm uses maximum vessel pixel sum to extract the complete OC region by extending the partial cup edges to the nasal side of the cup boundary. This approach covers the region under central retinal blood vessels also which were missing in earlier research. The proposed algorithms achieved an accuracy rate up to 99.70% for OD and 99.47% for OC segmentation, respectively even under severe retinal pathological conditions.

MSCNN-AM: A Multi-Scale Convolutional Neural Network With Attention Mechanisms for Retinal Vessel Segmentation

Automatic retinal vessel segmentation has drawn significant attention in early diagnosis and treatment of many diseases, such as diabetes, retinal diseases, and coronary heart disease. However, due to vessels exhibit variations in morphology and low contrast, it is still challenging to obtain accurate segmentation results. In this paper, aiming at upgrading the accuracy and sensitivity of existing vessel segmentation methods, we propose a Multi-Scale Convolutional Neural Network with Attention Mechanisms (MSCNN-AM). For extraction of blood vessels at different scales, we introduce atrous separable convolutions with varying dilation rates, which could capture global and multi-scale vessel information better. Meanwhile, in order to reduce false-positive predictions for tiny vessel pixels, we also adopt attention mechanisms so that the proposed MSCNN-AM can pay more attention to retinal vessel pixels instead of background pixels. Because the green channel shows better vessel contrast and less noise than other channels in the RGB image, our proposed MSCNN-AM is trained and tested with green channel images only, excluding extra pre-processing and post-processing steps. The proposed method is evaluated on three public datasets, including DRIVE, STARE, and CHASE_DB1. In addition, we adopt six objective metrics to verify the performance of the MSCNN-AM, including sensitivity (Se), specificity (Sp), accuracy (Acc), F1-score, an area under a receiver operating characteristic curve (AUC-ROC), and an area under precision/recall curve (AUC-PR). Experimental results indicate that our proposed method outperforms most of the existing methods with a sensitivity of 0.8342/0.8412/0.8132 and an accuracy of 0.9555/0.9658/0.9644 on DRIVE, STARE, and CHASE_DB1 separately.

Attention Guided U-Net With Atrous Convolution for Accurate Retinal Vessels Segmentation

The accuracy of retinal vessels segmentation is of great significance for the diagnosis of cardiovascular diseases such as diabetes and hypertension. Especially, the segmentation accuracy of the end of vessels will be affected by the area outside the retinal in fundus image. In this paper, we propose an attention guided U-Net with atrous convolution(AA-UNet), which guides the model to separate vessel and non-vessel pixels and reuses deep features. Firstly, AA-UNet regresses a boundary box to the retinal region to generate an attention mask, which was used as a weighting function to multiply the differential feature map in the model to make the model pay more attention to the vessels region. Secondly, atrous convolution replaces ordinary convolution in feature layer, which can increase the receptive field and reduce the amount of computation. Then, we add two shortcuts to the atrous convolution in order to reuse the features, so that the details of vessel are more prominent. We test our model with the accuracy are 0.9558/0.9640/0.9608 and AUC are 0.9847/0.9824/0.9865 on DRIVE, STARE and CHASE_DB1 datasets, respectively. The results show that our method has improvement in the accuracy of retinal vessels segmentation, and exceeded other representative retinal vessels segmentation methods.

Detection of bifurcations and cross-over points from retinal vasculature map using modified window feature-point detection approach

Identification of feature points such as bifurcation points and cross-over points in retinal fundus images is useful for predicting the various cardiovascular diseases. In this paper, a new approach called the Modified Window Feature-point Detection (MWFD) is proposed to identify the vascular feature points in the fundus image. The MWFD technique makes use of two different windows 3×3 and 5×5 with alternative vessel pixel property for the detection of all feature points. This paper also resolves the problem of conversion of one cross-over point into two bifurcation points generated due to skeletonisation. The simulation is performed on the DRIVE database using MATLAB software. Simulation results show quantitative improvements in detection of feature points from retinal fundus image by increasing the number of true positives and reducing false positives and false negatives. These results provide an efficient and reliable technique for analysis of various retinal structures.

Determinación de la parábola de la vasculatura de la retina mediante un algoritmo computacional de segmentación

El análisis cuantitativo de la arquitectura de las venas temporales superior e inferior y su monitoreo sobre el tiempo puede facilitar el diagnóstico y tratamiento oportuno de la retinopatía diabética. En este trabajo se presenta un novedoso método que consiste de dos etapas correspondientes a la segmentación automática y modelado parabólico de las venas temporales superior e inferior en imágenes de fondo de ojo. En la primera etapa, el detector lineal multiescala (DLM) es empleado para detectar estructuras de tipo arterial en imágenes de la retina. Debido a que DLM es un método de realzado arterial, es necesario aplicar una estrategia de umbralización para clasificar pixeles de tipo arterial con respecto al fondo de la imagen, donde un valor de umbral determinado de forma experimental es comparado con cinco métodos de umbralización del estado del arte. En esta etapa, el método de segmentación propuesto es comparado con seis métodos especializados del estado del arte en términos de eficiencia de segmentación. En la segunda etapa, se desempeña un modelado parabólico mediante una estrategia de optimización utilizando un Algoritmo de Distribución Marginal Univariada sobre las arterias previamente segmentadas, y los resultados son comparados con dos métodos paramétricos del estado del arte y con las delineaciones realizadas por especialistas. Los resultados de segmentación arterial utilizando el detector lineal multiescala demostraron una alta eficiencia de segmentación obteniendo un valor de 0.9618 utilizando la base de datos DRIVE de imágenes de fondo de ojo. De igual forma, los resultados de modelado parabólico entregaron una eficiencia promedio de 0.825 con respecto a las delineaciones realizadas por especialistas oftalmólogos de las venas temporales superior e inferior. En base a los resultados de eficiencia y al tiempo computacional (5.62 segundos), el método propuesto puede considerarse como altamente apropiado para desempeñar diagnóstico asistido por computadora en el área de oftalmología.

Segmentation of retinal blood vessels based on feature-oriented dictionary learning and sparse coding using ensemble classification approach.

Accurate segmentation of the blood vessels from a retinal image plays a significant role in the prudent examination of the vessels. A supervised blood vessel segmentation technique to extract blood vessels from a retinal image is proposed. The uniqueness of the work lies in the implementation of feature-oriented dictionary learning and sparse coding for the accurate classification of the pixels in an image. First, the image is split into patches and for each patch, Gabor features are extracted at multiple scales and orientations to create a set of feature vectors (this is done for the whole training set). Then, an overcomplete feature-oriented dictionary is trained from the extracted Gabor features (selected on the basis of standard deviation) using the generalized K-means for singular value decomposition dictionary learning technique. Sparse representations are subsequently calculated for the corresponding features from the dictionary. The combination of feature vectors and sparse representations constitutes the final feature vector. This feature vector is then fed into the ensemble classifier for the classification of pixels into either blood vessel pixels or nonblood vessel pixels. The method is evaluated on publicly available DRIVE and STARE datasets, as they contain ground truth images precisely marked by experts. The results obtained on both of the datasets show that the proposed technique outperforms most of the state-of-the-art techniques reported in the literature.

A Multi-Scale Directional Line Detector for Retinal Vessel Segmentation.

The assessment of transformations in the retinal vascular structure has a strong potential in indicating a wide range of underlying ocular pathologies. Correctly identifying the retinal vessel map is a crucial step in disease identification, severity progression assessment, and appropriate treatment. Marking the vessels manually by a human expert is a tedious and time-consuming task, thereby reinforcing the need for automated algorithms capable of quick segmentation of retinal features and any possible anomalies. Techniques based on unsupervised learning methods utilize vessel morphology to classify vessel pixels. This study proposes a directional multi-scale line detector technique for the segmentation of retinal vessels with the prime focus on the tiny vessels that are most difficult to segment out. Constructing a directional line-detector, and using it on images having only the features oriented along the detector’s direction, significantly improves the detection accuracy of the algorithm. The finishing step involves a binarization operation, which is again directional in nature, helps in achieving further performance improvements in terms of key performance indicators. The proposed method is observed to obtain a sensitivity of 0.8043, 0.8011, and 0.7974 for the Digital Retinal Images for Vessel Extraction (DRIVE), STructured Analysis of the Retina (STARE), and Child Heart And health Study in England (CHASE_DB1) datasets, respectively. These results, along with other performance enhancements demonstrated by the conducted experimental evaluation, establish the validity and applicability of directional multi-scale line detectors as a competitive framework for retinal image segmentation.

The influence of MC1R ondermal morphological features of photo-exposed skin in women revealed by reflectance confocal microscopy and optical coherence tomography.

The melanocortin 1 receptor (MC1R) gene is one of the major determinants of skin pigmentation. It is a highly polymorphic gene and some of its polymorphisms have been related to specific skin phenotypes, increased risk of skin cancers and skin photoageing. Currently, its contribution to changes in dermal features in photo-exposed skin is unknown. The main objective of this study is to evaluate the potential correlation between MC1R status and specific healthy photo-exposed skin characteristics. Skin facial features were estimated by evaluation with standard digital photography with automated featurescount, reflectance confocal microscopy (RCM) and optical coherence tomography (OCT) in 100 healthy women. Skin of the forearms was used as a control. The study found an association between RHC MC1R polymorphisms and dermal features in photo-exposed areas being represented by increased vessel density and pixel density in OCT (P=.025 and P=.001, respectively) and increased coarse collagen in RCM (P=.034), as compared to non-RHC subjects. To our knowledge this is previously unreported. Additionally, previously reported correlations between light hair colour and pigmented spots with MC1R RHC polymorphisms have been confirmed. Our results suggest the role of RHC MC1R variants in dermal variations of facial skin, as compared to non-RHC variants. To our knowledge this is previously unreported.

Improving retinal vessel segmentation with joint local loss by matting

Besides the binary segmentation, many retinal image segmentation methods also produce a score map, where a nonnegative score is assigned for each pixel to indicate the likelihood of being a vessel. This observation inspires us to propose a new approach as a post-processing step to improve existing methods by formulating segmentation as a matting problem. A trimap is obtained via a bi-level thresholding of the score map from existing methods, which is instrumental in focusing the attention to pixels of these unknown areas. A dedicated end-to-end matting algorithm is further developed to retrieve those vessel pixels in the unknown areas, and to produce the final vessel segmentation by minimizing global pixel loss and local matting loss. Our approach is shown to be particularly effective in rescuing thin and tiny vessels that may lead to disconnections of vessel fragments. Moreover, it is observed that our approach is capable of improving the overall segmentation performance across a broad range of existing methods.

Retinal blood vessel segmentation from diabetic retinopathy images using tandem PCNN model and deep learning based SVM

Diabetic Retinopathy (DR) occurs due to Type-II diabetes. It causes damages to the retinal blood vessels and reason for visual impairment. The predicted center is around the probability of variation in the estimation of retinal veins, and the crisp enrolls vessel development inside the retina. To witness the changes segmentation of retinal blood vessels has to be made. A framework to upgrade the quality of the segmentation results over morbid retinal images is proposed. This framework utilizes Contrast Limited Adaptive Histogram Equalization (CLAHE) for eliminating the background from the source image and enhances the foreground blood vessel pixels, Tandem Pulse Coupled Neural Network (TPCNN) model is endorsed for automatic feature vectors generation, and Deep Learning Based Support Vector Machine (DLBSVM) is proposed for classification and extraction of blood vessels. The DLBSVM parameters are fine-tuned via Firefly algorithm. The STARE, DRIVE, HRF, REVIEW, and DRIONS fundus image datasets are deliberated to assess the recommended techniques. The results render that the proposed technologies improve the segmentation with 80.61% Sensitivity, 99.54% Specificity, and 99.49% Accuracy.

Image processing-based model for tortuosity measurement of retinal blood vessels

Purpose: The study of retinal blood vessel morphology is of great importance in retinal image analysis. The retinal blood vessels have a number of distinct features such as width, diameter, tortuosity, etc. In this paper, a method is proposed to measure the tortuosity of retinal blood vessels obtained from retinal fundus images. Tortuosity is a situation in which blood vessels become tortuous, that is, curved or non-smooth. It is one of the earliest changes that occur in blood vessels in some retinal diseases. Hence, its detection at an early stage can prevent the progression of retinal diseases such as diabetic retinopathy, hypertensive retinopathy, retinopathy of prematurity, etc. The present study focuses on the measurement of retinal blood vessel tortuosity for the analysis of hypertensive retinopathy. Hypertensive retinopathy is a condition in which the retinal vessels undergo changes and become tortuous due to long term high blood pressure. Early recognition of hypertensive retinopathy signs remains an important step in determining the target-organ damage and risk assessment of hypertensive patients. Hence, this paper attempts to estimate tortuosity using image-processing techniques that have been tested on artery and vein segments of retinal images.
 Design: Image processing-based model designed to measure blood vessel tortuosity.
 Methods: In this paper, a novel image processing-based model is proposed for tortuosity measurement. This parameter will be helpful for analyzing hypertensive retinopathy. To test the eff ectiveness of the system in determining tortuosity, the method is first applied on a set of synthetically generated blood vessels. Then, the method is repeated on blood vessel (both artery and vein) segments extracted from retinal images collected from publicly available databases and on images collected from a local eye hospital. The blood vessel segment images that are used in the method are binary images where blood vessels are represented by white pixels (foreground), while black pixels represent the background. Vessels are then classified into normal, moderately tortuous, and severely tortuous by following the analysis performed on the images in the Retinal Vessel Tortuosity Data Set (RET-TORT) obtained from BioIm Lab, Laboratory of Biomedical Imaging (Padova, Italy). This database consists of 30 artery segments and 30 vein segments, which were manually ordered on the basis of increasing tortuosity by Dr. S. Piermarocchi, a retinal specialist belonging to the Department of Ophthalmology of the University of Padova (Italy). The artery and vein segments with the fewest number of turns are given a low tortuosity ranking, while those with the greatest number of turns are given a high tortuosity ranking by the expert. Based on this concept, our proposed method defines retinal image segments as normal when they present the fewest number of twists/turns, moderately tortuous when they present more twists/turns than normal but fewer than severely tortuous vessels, and severely tortuous when they present a greater number of twists/turns than moderately tortuous vessels. On implementing our image processing-based method on binary blood vessel segment images that are represented by white pixels, it is found that the vessel pixel (white pixels) count increases with increasing vessel tortuosity. That is, for normal blood vessels, the white pixel count is less compared to moderately tortuous and severely tortuous vessels. It should be noted that the images obtained from the different databases and from the local hospital for this experiment are not hypertensive retinopathy images. Instead, they are mostly normal eye images and very few of them show tortuous blood vessels.
 Results: The results of the synthetically generated vessel segment images from the baseline for the evaluation of retinal blood vessel tortuosity. The proposed method is then applied on the retinal vessel segments that are obtained from the DRIVE and HRF databases, respectively. Finally, to evaluate the capability of the proposed method in determining the tortuosity level of the blood vessels, the method is tested with a standard tortuous database, namely, the RET-TORT database. The results are then compared with the tortuosity level mentioned in the database. It was found that our method is able to classify blood vessel images as normal, moderately tortuous, and severely tortuous, with results closely matching the clinical ordering provided by the expert in the RET-TORT database. Subjective evaluation was also performed by research scholars and postgraduate students to cross-validate the results.
 Conclusion: The close correlation between the tortuosity evaluation using the proposed method and the clinical ordering of retinal vessels as provided by the retinal specialist in the RET-TORT database shows that, although simple, this method can evaluate the tortuosity of vessel segments effectively.

An Improved Retinal Blood Vessel Detection System Using an Extreme Learning Machine

Retinal images are commonly used to diagnose various diseases, such as diabetic retinopathy, glaucoma, and hypertension. An important step in the analysis of such images is the detection of blood vessels, which is usually done manually and is time consuming. The main proposal in this work is a fast method for retinal blood vessel detection using Extreme Learning Machine (ELM). ELM requires only one iteration to complete its training and it is a robust and fast network in all aspects. The proposal is a compact and efficient representation of retinal images in which the authors achieved a reduction up to 39% of the initial data volume, while still keeping representativeness. To achieve such a reduction whilst maintaining the representativeness, three features (local tophat, local average, and local variance) were used. According to the simulations carried out, this proposal achieved an accuracy of about 95% for most results, outperforming most of the state-of-art methods. Furthermore, this proposal has greater sensitivity, meaning that more vessel pixels are detected correctly.

Retinal Vessel Segmentation using Round-wise Features Aggregation on Bracket-shaped Convolutional Neural Networks.

With the recent advent of deep learning in medical image processing, retinal blood vessel segmentation topic has been comprehensively handled by numerous research works. However, since the ratio between the number of vessel and background pixels is heavily imbalanced, many attempts utilized patches augmented from original fundus images along with fully convolutional networks for addressing such pixel-wise labeling problem, which significantly costs computational resources. In this paper, a method using Round-wise Features Aggregation on Bracket-shaped convolutional neural networks (RFA-BNet) is proposed to exclude the necessity of patches augmentation while efficiently handling the irregular and diverse representation of retinal vessels. Particularly, given raw fundus images, typical feature maps extracted from a pretrained backbone network are employed for a bracket-shaped decoder, wherein middle-scale features are continuously exploited round-by-round. Then, the decoded maps having highest resolution of each round are aggregated to enable the built model to flexibly learn various degrees of embedded semantic details while retaining proper annotations of thin and small vessels. Finally, the proposed approach showed its effectiveness in terms of sensitivity (0.7932), specificity (0.9741), accuracy (0.9511), and AUROC (0.9732) on DRIVE dataset.

Retinal vessel segmentation by a divide-and-conquer funnel-structured classification framework

Accurate vessel segmentation is a fundamental and challenging task for the retinal fundus image analysis. Current approaches typically train a global discriminative model for retinal vessel classification that is difficult to fit the complex pattern of vessel structure. In this paper, we propose a novel divide-and-conquer funnel-structured classification framework for retinal vessel segmentation. More specifically, a dividing algorithm, named multiplex vessel partition (MVP), is proposed to divide retinal vessel into well constrained subsets where vessel pixels with similar geometrical property are grouped. A set of homogeneous classifiers are trained in parallel to form discriminative decision for each group. This decomposes a complex classification problem into a number of relatively simpler ones. Moreover, a funnel-structured vessel segmentation (FsVS) framework is proposed to reclassify the uncertain samples caused by imperfect grouping of pixels. This alleviates the problem in data partition at the dividing phase and further enhances the complexity and discriminative capability of the decision model. Both quantitative and qualitative experimental comparisons on three publicly available databases show that the proposed framework produces high performance for retinal vessel segmentation, achieving 95.47–96.46% vessel segmentation accuracy, 83.72–85.79% local vessel segmentation accuracy, 78.63–81.92% F1-score and 76.55–80.13% Matthew correlation coefficient respectively, better than the state-of-the-art methods.

Retinal blood vessel extraction employing effective image features and combination of supervised and unsupervised machine learning methods.

In medicine, retinal vessel analysis of fundus images is a prominent task for the screening and diagnosis of various ophthalmological and cardiovascular diseases. In this research, a method is proposed for extracting the retinal blood vessels employing a set of effective image features and combination of supervised and unsupervised machine learning techniques. Further to the common features used in extracting blood vessels, three strong features having a significant influence on the accuracy of the vessel extraction are utilized. The selected combination of the different types of individually efficient features results in a rich local information with better discrimination for vessel and non-vessel pixels. The proposed method first extracts the thick and clear vessels in an unsupervised manner, and then, it extracts the thin vessels in a supervised way. The goal of the combination of the supervised and unsupervised methods is to deal with the problem of intra-class high variance of image features calculated from various vessel pixels. The proposed method is evaluated on three publicly available databases DRIVE, STARE and CHASE_DB1. The obtained results (DRIVE: Acc = 0.9531, AUC = 0.9752; STARE: Acc = 0.9691, AUC = 0.9853; CHASE_DB1: Acc = 0.9623, AUC = 0.9789) demonstrate the better performance of the proposed method compared to the state-of-the-art methods.

A Hierarchical Image Matting Model for Blood Vessel Segmentation in Fundus Images.

In this paper, a hierarchical image matting model is proposed to extract blood vessels from fundus images. More specifically, a hierarchical strategy is integrated into the image matting model for blood vessel segmentation. Normally the matting models require a user specified trimap, which separates the input image into three regions: the foreground, background and unknown regions. However, creating a user specified trimap is laborious for vessel segmentation tasks. In this paper, we propose a method that first generates trimap automatically by utilizing region features of blood vessels, then applies a hierarchical image matting model to extract the vessel pixels from the unknown regions. The proposed method has low calculation time and outperforms many other state-of-art supervised and unsupervised methods. It achieves a vessel segmentation accuracy of 96.0%, 95.7% and 95.1% in an average time of 10.72s, 15.74s and 50.71s on images from three publicly available fundus image datasets DRIVE, STARE, and CHASE DB1, respectively.

Spatiotemporal pattern analysis of potential light seine fishing areas in the East China sea using VIIRS day/night band imagery

ABSTRACT Light seine fishing, one of the most efficient methods used in modern fisheries, is performed based on fish phototaxis. In this study, the East China Sea was selected as the study area, and fishing vessel pixels (pixels representing light seine fishing vessels) were detected in five years of Visible Infrared Imaging Radiometer Suite (VIIRS) day/night band (DNB) imagery according to three indicators: the Spike Median Index (SMI), Sharpness Index (SI), and Spike Height Index (SHI). Subsequently, cluster, barycenter, range and direction, and density analyses were conducted to comprehensively evaluate the spatiotemporal patterns of potential light seine fishing areas in the East China Sea. The following conclusions were drawn from the study: (1) the number of fishing vessel pixels exhibited obvious monthly characteristics that are consistent with the fishing moratorium that has been enforced in this region; (2) at the study area scale, light seine fishing occurred in one cluster, and the pattern in the interior of the cluster exhibited spatiotemporal periodicity; (3) the barycenter of the fishing areas displayed opposing movement trends in the first half and the second half of the year, and the movements were closely linked to water temperature changes. In addition, seasonally concentrated fishing areas were observed in winter, spring and summer; (4) the peak fishing month advanced from September to August beginning in 2014, and the fishing areas displayed a strong tendency in orientation that was highly consistent with the distribution of the Kuroshio Front in the East China Sea; and (5) light seine fishing activities were mainly concentrated in the second half of the year, especially in summer, but the intensity has declined in recent years. Our results are in good agreement with the results of other scholars and provide reliable information concerning where and when light seine fishing occurs. These results also suggest that VIIRS DNB imagery can be effectively used to detect light seine fishing areas.

A Three-Stage Deep Learning Model for Accurate Retinal Vessel Segmentation.

Automatic retinal vessel segmentation is a fundamental step in the diagnosis of eye-related diseases, in which both thick vessels and thin vessels are important features for symptom detection. All existing deep learning models attempt to segment both types of vessels simultaneously by using a unified pixel-wise loss that treats all vessel pixels with equal importance. Due to the highly imbalanced ratio between thick vessels and thin vessels (namely the majority of vessel pixels belong to thick vessels), the pixel-wise loss would be dominantly guided by thick vessels and relatively little influence comes from thin vessels, often leading to low segmentation accuracy for thin vessels. To address the imbalance problem, in this paper, we explore to segment thick vessels and thin vessels separately by proposing a three-stage deep learning model. The vessel segmentation task is divided into three stages, namely thick vessel segmentation, thin vessel segmentation, and vessel fusion. As better discriminative features could be learned for separate segmentation of thick vessels and thin vessels, this process minimizes the negative influence caused by their highly imbalanced ratio. The final vessel fusion stage refines the results by further identifying nonvessel pixels and improving the overall vessel thickness consistency. The experiments on public datasets DRIVE, STARE, and CHASE_DB1 clearly demonstrate that the proposed three-stage deep learning model outperforms the current state-of-the-art vessel segmentation methods.

A framework for retinal vessel segmentation from fundus images using hybrid feature set and hierarchical classification

Retinal blood vessels play an imperative role in detection of many ailments, such as cardiovascular diseases, hypertension, and diabetic retinopathy. The automated way of segmenting vessels from retinal images can help in early detection of many diseases. In this paper, we propose a framework based on hybrid feature set and hierarchical classification approach to segment blood vessels from digital retinal images. Firstly, we apply bidirectional histogram equalization on the inverted green channel to enhance the fundus image. Six discriminative feature extraction methods have been employed comprising of local intensities, local binary patterns, histogram of gradients, divergence of vector field, high-order local autocorrelations, and morphological transformation. The selection of feature sets has been carried out by classifying vessel and background pixels using random forests and evaluating the segmentation performance for each category of features. The selected feature sets are then used in conjunction with our proposed hierarchical classification approach to segment the vessels. The proposed framework has been tested on the DRIVE, STARE, and CHASEDB1 which are the benchmark datasets for retinal vessel segmentation methods. The results obtained from the experimental analysis show that the proposed framework can achieve better results than most state-of-the-art methods.