Blood vessel segmentation algorithms — Review of methods, datasets and evaluation metrics

Tensor-cut: A tensor-based graph-cut blood vessel segmentation method and its application to renal artery segmentation.

Retinopathies are the leading cause of eyesight loss, especially among diabetics. Due to the low contrast of blood vessels in fundus images, the visual inspection is a challenging job even for specialists. In this context, this work aims to implement image processing techniques to support contrast enhancement and segmentation of retinal blood vessels. The initial proposal consisted only of green channel separation, contrast limited adaptive histogram equalization, and 2D Gabor wavelet and mathematical morphology. The new proposal includes the edge and mask detection and the vessel enhancement 2D to preserve image’s characteristics. The development and validation of this work, in MatLab® environment, involved 40 images from Digital Retinal Images for Vessel Extraction (DRIVE), 20 images from Structured Analysis of the Retina (STARE), and 45 images from High-Resolution Fundus (HRF) database. In the unsupervised method context, the proposal presented the best performance regarding sensitivity and second place for balanced-accuracy on all databases. A subjective validation involving eleven ophthalmology professionals showed higher levels of acceptance (above 80%) after contrast limited adaptive histogram equalization (CLAHE) and vessel enhancement 2D steps and 75.5% for overall quality system. The main contributions refer to the inclusion of techniques for automatic mask detection, image edge removal, and suppression of vessels background to improve the retinal vessels segmentation process. In addition, this work made a computational interface named “Retinal Lab - A Tool for Fundus Image Analysis” available, which permits the users to adjust the contrast and segmentation of blood vessels in retinal images.

Background: Blood vessel segmentation plays an important role in medical image analysis. Modern blood vessel segmentation algorithms attempts to attempts to increase patient safety by providing better diagnosis and support to more accurate medical decisions. Methods: In 3D image processing techniques leads to an emerging area, and voxel classification. Most of the voxel classification algorithms are a manual classification. This work introduces a novel fully automatic blood vessel segmentation algorithm from 3D images using Hessian-based multi-scale filters (Frangi's filter) and Chan-Vese model with level-set framework. Parameters of Frangi's filter are adjusted by means of an evolutionary computation method, particle swarm optimization (PSO). 3D synthetic and real CTA clinical image database is used to test the proposed algorithm and show a correct voxel classification. Conclusion: The proposed algorithm shows results that are more accurate. Keywords: Particle swarm optimization, Chan-Vese model, level-set, Hessian-based multi-scale filter, 3D medical images, blood vessel segmentation.

Diabetic retinopathy (DR) occurs in patients who have had diabetes for at least five years. Diseased small blood vessels in the back of the eye cause a leakage of protein and blood in the retina. Diagnosis of diabetic retinopathy at early stage can be done through detection of blood vessels of retina. Blood vessel segmentation is a helpful tool in the treatment of diabetic retinopathy. Many studies have been carried out in the last decade in order to get an accurate blood vessel detection and segmentation in retinal images since vascular anomalies are one of the strongest manifestations of DR. Here, we propose a ruled-based algorithm called Star Networked Pixel Tracking to decide whether a processed pixel is a part of a vessel or not. The complement of the gray scale of the green channel from the original image is used. The blood vessels are enhanced by applying a strong adaptive histogram equalization algorithm locally and globally. Morphological operations are implemented in designing a background image to generate a normalized retinal image. In order to enhance the vessels' contrast, mathematical and morphological operations are applied. Noise artifacts that look like small vessels is filtered by the proposed eight-direction network pixel tracking algorithm. The proposed method is evaluated on 20 images of well known public domain DRIVE database. We achieved an accuracy of 95.83%. This is the highest accuracy among the ruled-based methods reported for the DRIVE database.

Capillaries segmentation of NIR-II images and its application in ischemic stroke

The retina is the most important part of the eye. Early detection of retinal disease can be done through the passage of the blood vessels of the retina. Enhancement of the quality of retinal images that have both noise and noise is the first step in image processing to help improve the accuracy of the results for image segmentation and extraction. Images store a lot of information, but often there is a decrease in quality or image defects. So that images that have experienced interference or noise are easily interpreted, then the image can be manipulated into other images of better quality using image processing techniques or methods. The neural network-based method that is currently popular is deep learning. The segmentation process is currently a widely used method of deep learning that has grown rapidly used in various studies. One of the popular methods is Convolutional Neural Network (CNN). CNN can handle large-dimensional data such as images because the input to CNN is in the form of a matrix. Since the findings of retinal blood vessel segmentation are often inaccurate and there is always noise, this study will look at how to segment retinal images in blood vessels using CNN U-Net and LadderNet methods. Proper segmentation of retinal blood vessels can be the first step to detecting a disease. Segmentation and analysis of retinal blood vessels can assist medical personnel in detecting the severity of a disease. The stages of image enhancement used are Histogram Equalization and Clahe. Segmentation of blood vessels is done using CNN U-Net and LadderNet Methods. The results of the application of the enhancement and segmentation using the U-Net and LadderNet methods on training and on testing data were tested on the DRIVE dataset. The results of measurement of accuracy, specificity, sensitivity and F1 Score of blood vessel segmentation using the U-Net CNN method were 95.46%, 98.56%, 74.20%, and 80.63%, respectively. While the results of the CNN LadderNet method were 95.47%, 98.42%, 75.19%, and 80.86%, respectively. Based on the results of blood vessel segmentation from two proposed methods, the result of the CNN LaddetNet method is greater than the CNN U-Net method in accuracy, sensitivity, and F1 Score. The proposed approach will be further developed in the future, with the aim of increasing the value of the blood vessel segmentation process evaluation outcomes.

Blood vessel segmentation is a crucial aspect of medical image processing, aiding medical professionals in more accurate disease analysis and diagnosis. Manual blood vessel segmentation methods are time‐consuming and cumbersome, making the development of automatic segmentation methods essential. The rapid advancements in deep learning technology have introduced new tools and methods for vascular image segmentation. In this review, we provide a comprehensive overview of deep learning‐based blood vessel segmentation methods across various fields, including retinal vessel segmentation, cerebrovascular segmentation, and pulmonary vessel segmentation. Several prevalent diseases, such as retinal vascular diseases, cerebrovascular diseases, pulmonary vascular diseases, and tumors, have posed significant health challenges globally. This review also discusses the application of deep learning technology in disease diagnosis within these contexts. Finally, considering the current research landscape, we discuss existing challenges and potential future developments in blood vessel segmentation. We aim to assist researchers in gaining a comprehensive understanding and designing effective blood vessel segmentation models, ultimately offering opportunities for early disease diagnosis and treatment.

Pulmonary nodules may indicate the early stage of lung cancer, and the progress of lung cancer causes associated changes in the shape and number of pulmonary blood vessels. The automatic segmentation of pulmonary nodules and blood vessels is desirable for chest computer-aided diagnosis (CAD) systems. Since pulmonary nodules and blood vessels are often attached to each other, conventional nodule detection methods usually produce many false positives (FPs) in the blood vessel regions, and blood vessel segmentation methods may incorrectly segment the nodules that are attached to the blood vessels. A method to simultaneously and separately segment the pulmonary nodules and blood vessels was developed and tested. A line structure enhancement (LSE) filter and a blob-like structure enhancement (BSE) filter were used to augment initial selection of vessel regions and nodule candidates, respectively. A front surface propagation (FSP) procedure was employed for precise segmentation of blood vessels and nodules. By employing a speed function that becomes fast at the initial vessel regions and slow at the nodule candidates to propagate the front surface, the front surface can be propagated to cover the blood vessel region with suppressed nodules. Hence, the resultant region covered by the front surface indicates pulmonary blood vessels. The lung nodule regions were finally obtained by removing the nodule candidates that are covered by the front surface. A test data set was assembled including 20 standard-dose chest CT images obtained from a local database and 20 low-dose chest CT images obtained from lung image database consortium (LIDC). The average extraction rate of the pulmonary blood vessels was about 93%. The average TP rate of nodule detection was 95% with 9.8 FPs/case in standard-dose CT image, and 91.5% with 10.5 FPs/case in low-dose CT image, respectively. Pulmonary blood vessels and nodules segmentation method based on local intensity structure analysis and front surface propagation were developed. The method was shown to be feasible for nodule detection and vessel extraction in chest CAD.

An automated system for screening and diagnosis of diabetic retinopathy should segment blood vessels from colored retinal image to assist the ophthalmologists. We present a method for blood vessel enhancement and segmentation. This paper proposes a wavelet based method for vessel enhancement, piecewise threshold probing and adaptive thresholding for vessel localization and segmentation respectively. The method is tested on publicly available DRIVE and STARE databases of manually labeled images which has been established to facilitate comparative studies on segmentation of blood vessels in retinal images. The proposed method achieves an accuracy of 0.9469 on DRIVE database and of 0.9502 on STARE database.

Magnetic resonance angiography (MRA) or computed tomography angiography (CTA) images allow for a thorough analysis of the blood vessels. Vessel segmentation from MRA or CTA is thus the primary task in the diagnosis of vascular diseases such as stenosis and aneurysms. The wide architectural variability of the blood vessels, however, hinders the validation of vascular segmentation methods. The construction of synthetic realistic vascular architecture trees will aid in the validation of new vessel segmentation methodologies. This thesis describes a three-dimensional synthetic blood vessel generation methodology that employs stochastic Lindenmayer systems (L-systems). For this purpose, we implemented a parser and a generator of L-systems to create grammars that represent blood vessel architectures. The parameterization of the grammar allows one to simulate natural features of real vessels such as bifurcation angle, average length and diameter, and also accounts for vascular anomalies. The resulting expressions are used to create synthetic angiographic images that mimic real vessel intensity distributions in MRA and CTA. Blood vessel growth can also be delimited by arbitrary 3D surfaces that may represent organ geometries. The flexibility in the parameterization and stochastic nature of this methodology makes it an ideal tool for the validation of blood vessel segmentation algorithms from angiographic images.

This paper presents an improved blood vessel segmentation technique from color fundus images using morphology operation. More accurate blood vessel segmentation from fundus images plays key role for screening of diabetic retinopathy and glaucoma. This paper has made significant contributions by developing linear structuring element for blood vessel detection using OpenCV. The proposed method involves three stages namely; pre-processing, generation of linear structuring element and detection of blood vessels from fundus image, In first stage, color fundus images are pre-processed or enhanced as these images often suffer from uneven illumination, low contrast and noise. In second stage, twelve linear structuring elements are generated and finally, in the third stage, blood vessel segmentation algorithm is applied to improve the extraction of diagnostic features such as microaneurysms and hemorrhages, leading to more accurate detection of diabetic retinopathy.

Sparsity techniques in medical imaging

Retinal blood vessel segmentation using density-based fuzzy C-means clustering and vessel neighborhood connected component

A hybrid method for blood vessel segmentation in images

A new deep learning method for blood vessel segmentation in retinal images based on convolutional kernels and modified U-Net model