Retinal vessels identification and localization aim to separate the different retinal vasculature structure tissues, either wide or narrow ones, from the fundus image background and other retinal anatomical structures such as optic disc, macula, and abnormal lesions. Retinal vessels identification studies are attracting more and more attention in recent years due to non-invasive fundus imaging and the crucial information contained in vasculature structure which is helpful for the detection and diagnosis of a variety of retinal pathologies included but not limited to: Diabetic Retinopathy (DR), glaucoma, hypertension, and Age-related Macular Degeneration (AMD). With the development of almost two decades, the innovative approaches applying computer-aided techniques for segmenting retinal vessels are becoming more and more crucial and coming closer to routine clinical applications. The purpose of this paper is to provide a comprehensive overview for retinal vessels segmentation techniques. Firstly, a brief introduction to retinal fundus photography and imaging modalities of retinal images is given. Then, the preprocessing operations and the state of the art methods of retinal vessels identification are introduced. Moreover, the evaluation and validation of the results of retinal vessels segmentation are discussed. Finally, an objective assessment is presented and future developments and trends are addressed for retinal vessels identification techniques.

https://www.mdpi.com/2076-3417/8/2/155/pdf

Retinal Vessels Segmentation Techniques and Algorithms: A Survey

Eye exam can be as efficacious as physical one in determining health concerns. Retina screening can be the very first clue for detecting a variety of hidden health issues including pre-diabetes and diabetes. Through the process of clinical diagnosis and prognosis; ophthalmologists rely heavily on the binary segmented version of retina fundus image; where the accuracy of segmented vessels, optic disc, and abnormal lesions extremely affects the diagnosis accuracy which in turn affect the subsequent clinical treatment steps. This paper proposes an automated retinal fundus image segmentation system composed of three segmentation subsystems follow same core segmentation algorithm. Despite of broad difference in features and characteristics; retinal vessels, optic disc, and exudate lesions are extracted by each subsystem without the need for texture analysis or synthesis. For sake of compact diagnosis and complete clinical insight, our proposed system can detect these anatomical structures in one session with high accuracy even in pathological retina images. The proposed system uses a robust hybrid segmentation algorithm combines adaptive fuzzy thresholding and mathematical morphology. The proposed system is validated using four benchmark datasets: DRIVE and STARE (vessels), DRISHTI-GS (optic disc), and DIARETDB1 (exudates lesions). Competitive segmentation performance is achieved, outperforming a variety of up-to-date systems and demonstrating the capacity to deal with other heterogeneous anatomical structures.

A Multi-Anatomical Retinal Structure Segmentation System for Automatic Eye Screening Using Morphological Adaptive Fuzzy Thresholding

Recently, there has been an advancement in the development of innovative computer-aided techniques for the segmentation and classification of retinal vessels, the application of which is predominant in clinical applications Consequently, this study aims to provide a detailed overview of the techniques available for segmentation and classification of retinal vessels Initially, retinal fundus photography and retinal image patterns are briefly introduced Then, an introduction to the pre-processing operations and advanced methods of identifying retinal vessels is deliberated In addition, a discussion on the validation stage and assessment of the outcomes of retinal vessels segmentation is presented In this paper, the proposed methods of classifying arteries and veins in fundus images are extensively reviewed, which are categorized into automatic and semi-automatic categories There are some challenges associated with the classification of vessels in images of the retinal fundus, which include the low contrast accompanying the fundus image and the inhomogeneity of the background lighting The inhomogeneity occurs as a result of the process of imaging, whereas the low contrast which accompanies the image is caused by the variation between the background and the contrast of the various blood vessels This means that the contrast of thicker vessels is higher than those that are thinner Another challenge is related to the color changes that occur in the retina from different subjects, which are rooted in biological features Most of the techniques used for the classification of the retinal vessels are based on geometric and visual characteristics that set the veins apart from the arteries In this study, different major contributions are summarized as review studies that adopted deep learning approaches and machine learning techniques to address each of the limitations and problems in retinal blood vessel segmentation and classification techniques We also review the current challenges, knowledge gaps and open issues, limitations and problems in retinal blood vessel segmentation and classification techniques

Comprehensive review of retinal blood vessel segmentation and classification techniques: intelligent solutions for green computing in medical images, current challenges, open issues, and knowledge gaps in fundus medical images

Intensity inhomogeneity is one of the major challenges for image segmentation in general and for retinal image segmentation in particular. Besides, using one single algorithm for identifying and extracting multi-anatomical structures is considered the most challengeable duty in retinal image segmentation due to the dramatic difference between different retinal anatomical and non-anatomical structures. In this poster, A novel, robust, and stand-alone algorithm based on hybrid combination between adaptive fuzzy thresholding and mathematical morphology used to extract multi-anatomical objects with broad features and characteristics in retinal image is proposed. Retinal Vessels , Optic Disk and Exudate lesions are extracted without the need for texture analysis or synthesis. The algorithm was validated using three benchmark databases. In addition, it performs well at extracting vessels and optic disc from pathological retinal images.

Retinal blood vessel segmentation plays an important part in the early diagnosis and treatment of eye disease. It is a tool for ophthalmologists. Many diseases can be identified by examining manifestations and images of blood vessels, including diabetic retinopathy, retinopathy of prematurity, age-related macular degeneration, retinopathy due to hypertension, glaucoma and others. Early detection allows physicians to provide patients with effective treatment, while in the opposite case, the late detection of retinal disease can ultimately lead to blindness. One of the indices when examining the retina is an evaluation of blood vessels based on tortuosity, i.e. the degree of curvature of blood vessels. This article presents a comprehensive overview of all segmentation techniques for retinal blood vessel extraction from images taken with a fundus camera in adults and older children or with a RetCam fundus camera in new-borns and younger children over the last 10 years. An integral part of this review is a comprehensive overview with information on all available public and private databases with retinal images. The review includes an evaluation of segmentation techniques based on objectivization parameters, including information on all objectivization parameters used in this article. As already mentioned, the degree of curvature of retinal blood vessels is used to classify severity of blood vessels tortuosity. There is no uniform metric for determining tortuosity, but this review presents a comprehensive overview of all metrics and calculations used to determine the degree of tortuosity of retinal blood vessels.

/pdf/recent-techniques-and-trends-for-retinal-blood-vessel-nj70qvjzb4.pdf

Recent Techniques and Trends for Retinal Blood Vessel Extraction and Tortuosity Evaluation: A Comprehensive Review

In this paper, segmentation of retinal vessel is done using an innovative procedure named as Morphological Angular Scale-Space (MASS). A linear structuring element rotated at different angles determines the connected components and ensuring that connectivity is not lost across the vessels. A scale-space is created by varying the length of the linear structuring element. Evolution to higher scales gradually reduces non-vessel like elements from the processing image with information from the lower scales being utilized to build the image of higher scales. The method, attains lowest mean square error value at a certain scale, which is observed to be better than most of the other morphological techniques of vessel segmentation. A publicly available DRIVE database is used for analysis of the MASS technique as well as to compare with other methods.

Retinal vessel segmentation using Morphological Angular Scale-Space

Automatic recovery of text from historical documents is a difficult task due to their degradation because of different types of noise. Applying a global threshold or a chosen threshold based on visual intuition misses the finer handwritten text with low intensity values. These low intensity text are actually considered as a part of background when applying global threshold and are neglected. A single threshold is unable to segment the whole image clearly as various levels of intensities are present in text because of degradation. For restoration of missing texts we propose a thresholding algorithm based on mathematical morphology, which generates very fine adaptive threshold. After applying global threshold, left out background image consists of some mixed image background and handwritten text intensities on which we apply mathematical morphology (opening and closing), which produces a smooth contour and gives an adaptive threshold. The resultant thresholded image have clear uniform background and foreground with enhanced character appearance.

Historical Handwritten Document Image Segmentation Using Morphology

Robust speckle reducing anisotropic diffusion

Accurate vessel structure segmentation from an ophthalmoscopic image of the retina is a major task of early computer-aided diagnosis of diabetic retinopathy. This chapter proposes an unsupervised segmentation technique by discriminating the statistical distribution of the area of the isolated objects. An adaptive mathematical morphology-based algorithm is used for the initial segmentation, followed by a locally adaptive threshold to extract the vessel structure from the background. Unfortunately, along with the vessel structure, an innumerable number of noisy artifacts are introduced by this process. To discriminate the vessels from the artifacts, the statistical distribution of the area of isolated objects is computed. As noise and vessels assume different statistical distributions, depending on the shape and monotonicity of the histogram, a threshold is determined to separate the noisy objects and the blood vessel structure. This method extracts the vessel structure from the background with an accuracy of 96.38%.

Segmentation of retinal blood vessel structure based on statistical distribution of the area of isolated objects

The aim of preserving historical handwritten documents is to restore the degraded text containing information. But generally global threshold fails to restore the text adequately. Adaptive (local) thresholding is required for preserving the text in these documents. In recent past many standard adaptive thresholding methods have been proposed for binarization of handwritten text document images. We propose a new adaptive thresholding method using locally adaptive mathematical morphology. Formulation of an adaptive structural element is a challenging work and addressed recently by some researchers. Our method at initial step binarizes the image applying global threshold. The residual background image below threshold containing low intensity texts mixed with noise is further processed. A new approach for constructing spatially variant operator corresponding to local variances is proposed. Gaussian surface is selected as an adaptive gray-scale structuring element for mathematical morphological operations (opening and closing), whose parameters base and height depends on local variance. The proposed method successfully demises various kinds of degraded documents enhancing textures with clear background. Experimental result on real historical handwritten document and artificial images show that our method outperforms several other existing methods both visually and using some evaluation metrics.

Rohit Kamal Chatterjee

Papers

Retinal vessel segmentation using Morphological Angular Scale-Space

Historical Handwritten Document Image Segmentation Using Morphology

Robust speckle reducing anisotropic diffusion

Segmentation of retinal blood vessel structure based on statistical distribution of the area of isolated objects

A Thresholding Approach for Text Extraction in Handwritten Historical Documents Using Adaptive Morphology