Retinal Blood Vessel Detection Research Articles

Comparison of Performances of Different Image Processing Methods in Detection of Prematurity Retinal Blood Vessels

Prematüre retinopatisi (ROP) hastalığının teşhisinde, retinadaki kan damarlarının özellikleri oldukça önemlidir. Erken doğan bebeklerde retina kan damarları büyümesini tamamlayamaz. Doğum sonrası, bazı tetikleyici durumlar düzenli damarların oluşumunun durmasına ve anormal kan damarlarının anormal doku oluşturarak genişlemeye başlamasına neden olur. Bu durumunun derecesinin artması ile retina hasarları oluşabilir. Özellikle prematüre doğan bebeklerin, prematüre retinopatisi hastalığı kapsamında olduğu için, damar ağlarında gelişmeleri takip ederek hastalığın seyrini takip etmek önemlidir. Bu çalışmada amacımız, prematüre bebeklerin retina görüntüleri üzerine görüntü işleme yöntemleri uygulayarak ROP görüntülerindeki damar yollarının tespiti ve segmentasyonu için yöntemler geliştirmektir. Uygulanan bu yöntemler, ROP görüntülerine uygulanarak sonuçlar sayısal olarak karşılaştırılmıştır. Sonuç olarak, en uygun görüntü işleme yönteminin, Tepe sinyalinin gürültüye oranı (PSNR) değerlerine göre; eşikleme yönteminde OTSU, filtreleme algoritmasında ise Gaussian filtresinin olduğu saptanmıştır.

A new approach for sensitivity improvement of retinal blood vessel segmentation in high-resolution fundus images based on phase stretch transform

The eye-fundus photograph is widely used for eye examinations. Accurate identification of retinal blood vessels could reveal information that is helpful for clinical diagnoses of many health disorders. Although several methods have been proposed to segment images of retinal blood vessels, the sensitivity of these methods is plausible to be improved. The algorithm’s sensitivity refers to the algorithm’s ability to identify retinal vessel pixels correctly. Furthermore, the resolution and quality of retinal images are improving rapidly. Consequently, new segmentation methods are in demand to overcome issues from high-resolution images. This study presented improved performance of retinal vessel segmentation using a novel edge detection scheme based on the phase stretch transform (PST) function as its kernel. Before applying the edge detection stage, the input retinal images were pre-processed. During the pre-processing step, non-local means filtering on the green channel image, followed by contrast limited adaptive histogram equalization (CLAHE) and median filtering, were applied to enhance the retinal image. After applying the edge detection stage, the post-processing steps, including the CLAHE, median filtering, thresholding, morphological opening, and closing, were implemented to obtain the segmented image. The proposed method was evaluated using images from the high-resolution fundus (HRF) public database and yielded promising results for sensitivity improvement of retinal blood vessel detection. The proposed approach contributes to a better segmentation performance with an average sensitivity of 0.813, representing a clear improvement over several benchmark techniques

Automatic Method for Blood Vessel Diameter Measurement on Color Retinal Images

Automatic detection of retinal blood vessels and measurement of blood vessel diameter has become very useful in medical applications, including the diagnosis and monitoring of vascular therapy. This paper present a new method for the detection of retinal blood vessels from fundus images. In addition, it accurately determines the blood vessels diameter. The proposed system consists of several stages starting from the detection of a complete blood vessel network (retinal images), a segmentation process, an extraction of blood vessel centerlines, and a new approach for the measurement of the blood vessel diameters utilizing the circle diameter approach. The application of the proposed method is based on three publicly available databases (DRIVE, STARE, CHASE_DB and HRF), which has been conducted and compared to recently reported measurement techniques. Numerical results demonstrate the efficacy of the proposed method achieving a success rate of 100% with 2.2454×10−4 as mean and 4.5833×10−5 as standard deviation differences. This could be harnessed in the future blood vessel measurement techniques.

A high accuracy segmentation method for retinal blood vessel detection based on hybrid filters and an adaptive thresholding

A high accuracy segmentation method for retinal blood vessel detection based on hybrid filters and an adaptive thresholding

U-shaped Retinal Vessel Segmentation Based on Adaptive Aggregation of Feature Information.

Detection and analysis of retinal blood vessels contribute to the clinical diagnosis of many ophthalmic diseases. In this paper, aiming on achieving more accurate segmentation of retinal vessels and enhance the ability of the algorithm to identify microvessels, we propose a U-shaped network based on adaptive aggregation of feature information. The introduced feature selection module, which could strengthen feature transmission and selectively emphasize feature information. To effectively capture the characteristics of vessels at different scales, generate richer and denser context information, and DenseASPP is embedded at the bottom of the network. Meanwhile, we propose an adaptive aggregation module to aggregate the semantic information in each layer of the encoder part and transmit it to subsequent layers, which is beneficial to the spatial reconstruction of retinal vessels. A joint loss function is also introduced to facilitate network training. The proposed network is evaluated on three public datasets. The sensitivity, accuracy, and area under curve(AUC) are 83.48%/83.16/85.86, 95.67%/96.67%/96.52%, and 98.11%/98.69%/98.60% on DRIVE, STARE and CHASE_DB1, respectively. In order to achieve more accurate retinal blood vessel segmentation and improve the ability of the algorithm to identify microvessels. We propose a U-shaped network based on adaptive aggregation of feature information. The introduction of the adaptive aggregation module aggregates the semantic information of each level of the encoder part, which improves the robustness of the model to segment blood vessels.

Fast and efficient retinal blood vessel segmentation method based on deep learning network.

The segmentation of the retinal vascular tree presents a major step for detecting ocular pathologies. The clinical context expects higher segmentation performance with a reduced processing time. For higher accurate segmentation, several automated methods have been based on Deep Learning (DL) networks. However, the used convolutional layers bring to a higher computational complexity and so for execution times. For such need, this work presents a new DL based method for retinal vessel tree segmentation. Our main contribution consists in suggesting a new U-form DL architecture using lightweight convolution blocks in order to preserve a higher segmentation performance while reducing the computational complexity. As a second main contribution, preprocessing and data augmentation steps are proposed with respect to the retinal image and blood vessel characteristics. The proposed method is tested on DRIVE and STARE databases, which can achieve a better trade-off between the retinal blood vessel detection rate and the detection time with average accuracy of 0.978 and 0.98 in 0.59 s and 0.48 s per fundus image on GPU NVIDIA GTX 980 platforms, respectively for DRIVE and STARE database fundus images.

Diagnosis of alzheimer disease through detection of eyes retinal blood vessels

Diagnosis of alzheimer disease through detection of eyes retinal blood vessels

Retinal vasculature segmentation and measurement framework for color fundus and SLO images

The change in vascular geometry is an indicator of various health issues linked with vision and cardiovascular risk factors. Early detection and diagnosis of these changes can help patients to select an appropriate treatment option when the disease is in its primary phase. Automatic segmentation and quantification of these vessels would decrease the cost and eliminate inconsistency related to manual grading. However, automatic detection of the vessels is challenging in the presence of retinal pathologies and non-uniform illumination, two common occurrences in clinical settings. This paper presents a novel framework to address the issue of retinal blood vessel detection and width measurement under these challenging circumstances and also on two different imaging modalities: color fundus imaging and Scanning Laser Ophthalmoscopy (SLO). In this framework, initially, vessel enhancement is done using linear recursive filtering. Then, a unique combination of morphological operations, background estimation, and iterative thresholding are applied to segment the blood vessels. Further, vessel diameter is estimated in two steps: firstly, vessel centerlines are extracted using the graph-based algorithm. Then, vessel edges are localized from the image profiles, by utilizing spline fitting to obtain vascular orientations and then finding the zero-crossings. Extensive experiments have been carried out on several publicly accessible datasets for vessel segmentation and diameter measurement, i.e., DRIVE, STARE, IOSTAR, RC-SLO and REVIEW dataset. Results demonstrate the competitive and comparable performance than earlier methods. The encouraging quantitative and visual performance of the proposed framework makes it an important component of a decision support system for retinal images.

Calibre fuzzy c-means algorithm applied for retinal blood vessel detection

Calibre fuzzy c-means algorithm applied for retinal blood vessel detection

Automated Segmentation of Retinal Blood Vessels using Fast Marching Method and local mathematical analysis

In this work, Fast Marching Method (FMM) has been suggested for Retinal blood vessels segmentation. FMM is an optimization technique; and the main advantage of the FMM is its ability to deal with branches and bifurcations without any additional computational cost. This advantage had been used in robotics to find the optimal path for the robot to move from the starting point to the goal with no collisions. Considereing the tree structure of blood vessel, I will use FMM to find the shortest bath between the optic disk and the blood vessels ends to draw the tree of the blood vessels.This method has been implemented using the M language in MATLAB R2016b. In this work local mathematical analysis has been implemented so that we can have an initial estimation of blood vessels distribution in an image in order to minimize the huge amount of noise included in retinal images and to make FMM implementing easier. FMM performance had been compared to other techniques used for retinal blood vessel detection like “Matched Filters”. The results showed that the FMM performance overcame some of those techniques and close to other high resolution methods. The FMM algorithm has been validated using the well-known “DRIVE” database and the resulting resolution ranged between 80% to 93% (depending on the noise amount in image) with iteration number between 500 to 1000 (according to the optic disk position in the image) with an average time of 0.57 seconds for each iteration which mean that the total running time is 5-10 minutes. FMM had also been validated using STARE data set and achieved a TPR of 90% for 700x605 STARE images in 15 minutes, and a TPR of 86% in 2.6 minutes when reducing image size to 350x303.

Enhancing detection of retinal blood vessels by combined approach of DWT, Tyler Coye and Gamma correction

Retinal imaging plays the most significant roles among all the medical imaging technology, because of its ability to derive various features that is related to various eye diseases. Thus, precise extraction is highly required for the blood vessels that lead to accurate identification of the diseases. Because of some instabilities in the retinal images such as noise, non-uniform illumination etc. it may motivate towards a false detection. This paper suggests an automated method to extract the blood vessels from fundus by integrating discrete wavelet transform (DWT) with Tyler Coye algorithm. Furthermore, in the retinal blood vessel segmentation methods the most vital step is to enhance the contrast. The authenticity of the segmentation is purely subjected to the uniformity of the contrast over the image. Thus, an illumination normalization technique known as Gamma correction is also utilized for the contrast enhancement. Three different types of experiments are carried out: original Tyler Coye algorithm, DWT with different wavelet filters integrated with Tyler Coye, and Gamma correction normalization applied to the integrated model. The approaches are tested with DRIVE dataset. The performance of the normalization-integrated model is found superior to the other two approaches.

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.

Caliber fuzzy c-means algorithm applied for retinal blood vessel detection

Retinal blood vessel detection employs a vital role in finding of retinal diseases like diabetic retinopathy and glaucoma. This paper presents an innovative unsupervised retinal blood vessel detection technique. First step is to generate a vessel enhanced image, then using calibre fuzzy c-means (CFCM) technique, first cluster the retinal image; next the clustered image is passed to the canny edge operator and finally post process the retinal image. CFCM clustering method for blood vessel detection is based on the choice of the number of clusters value. By using CFCM clustering function, compute the cluster centre, which commonly divides the image into four clusters. The proposed technique is obviously forceful into the modification of fuzzy c-means with canny algorithm. The proposed algorithm accomplishes an accuracy of about 95% of retinal images from three datasets DRIVE, STARE, and CHASE_DB1.

A review on computer-aided recent developments for automatic detection of diabetic retinopathy

Diabetic retinopathy is a serious microvascular disorder that might result in loss of vision and blindness. It seriously damages the retinal blood vessels and reduces the light-sensitive inner layer of the eye. Due to the manual inspection of retinal fundus images on diabetic retinopathy to detect the morphological abnormalities in Microaneurysms (MAs), Exudates (EXs), Haemorrhages (HMs), and Inter retinal microvascular abnormalities (IRMA) is very difficult and time consuming process. In order to avoid this, the regular follow-up screening process, and early automatic Diabetic Retinopathy detection are necessary. This paper discusses various methods of analysing automatic retinopathy detection and classification of different grading based on the severity levels. In addition, retinal blood vessel detection techniques are also discussed for the ultimate detection and diagnostic procedure of proliferative diabetic retinopathy. Furthermore, the paper elaborately discussed the systematic review accessed by authors on various publicly available databases collected from different medical sources. In the survey, meta-analysis of several methods for diabetic feature extraction, segmentation and various types of classifiers have been used to evaluate the system performance metrics for the diagnosis of DR. This survey will be helpful for the technical persons and researchers who want to focus on enhancing the diagnosis of a system that would be more powerful in real life.

Retinal blood vessel segmentation based on heuristic image analysis

Automatic analysis of retinal fundus images is becoming increasingly present today, and diseases such as diabetic retinopathy and age-related macular degeneration are getting a higher chance of being discovered in the early stages of their development. In order to focus on discovering those diseases, researchers commonly preprocess retinal fundus images in order to detect the retinal landmarks - blood vessels, fovea and the optic disk. A large number of methods for the automatic detection of retinal blood vessels from retinal fundus images already exists, but many of them are using unnecessarily complicated approaches. In this paper we demonstrate that a reliable retinal blood vessel segmentation can be achieved with a cascade of very simple image processing methods. The proposed method puts higher emphasis on high specificity (i.e. high probability that the segmented pixels actually belong to retinal blood vessels and are not false positive detections) rather than on high sensitivity. The proposed method is based on heuristically determined parametric edge detection and shape analysis, and is evaluated on the publicly available DRIVE and STARE datasets on which it achieved the average accuracy of 96.33% and 96.10%, respectively.

Impact of Image Enhancement Technique on CNN Model for Retinal Blood Vessels Segmentation

In this paper, we have developed a new method of accurate detection of retinal blood vessels based on a deep convolutional neural network (CNN) model. This method plays an important role in the observation of many eye diseases. Retinal Images have many issues that make the process of vessels segmentation very hard. We treat each issue of the retina image with the greatest observation to obtain a well-segmented image. The first step is to apply a pre-processing method based on fuzzy logic and image processing tactics. In a second step, in order to generate the segmented images, we propose a strided encoder-decoder CNN model. This network is trained and optimized using the Dice Loss function that supports the class imbalance problem that is in the database. The proposed model has a U-Net shape, but it is deeper and the pooling layers are replaced with strided convolutional layers in the encoder. This modification allows for a more precise segmentation of vessels and accelerates the training process. The last step is post-processing for removing the noisy pixels as well as the shadow of the optic disc. The performance of the proposed method was evaluated on DRIVE and STARE databases. The proposed method gives a sensitivity of 0.802 and 0.801 respectively on DRIVE and STARE, with an accuracy of 0.959 and 0.961 respectively. We focused on sensitivity and accuracy measurements that represent the accuracy of the model, especially tiny vessels. According to the results, the model outperforms many other proposed methods, especially in the above-mentioned measures.

Retinal Blood Vessels and Optical Disc Segmentation in Branch Retinal Vein Occluded Fundus Images Using Digital Image Processing Techniques

The segmentation of retinal blood vessels and optical disc is the most vital and challenging task to investigate the rigorousness of the various retinal diseases such as branch retinal vein occlusion. There are lot of methods and algorithms are developed to address this issue i.e., for the precise segmentation of optical disc and blood vessels. However, every method has its own pros and cons. Retinal vein occlusion (RVO) happens due to the obstruction (blockage) of veins transporting blood with required nutrients and oxygen to the nerve cells in the eye's retina. An obstruction in any one of the four smaller branch veins is referred to as a branch retinal vein occlusion (BRVO). It is one of the main retinal illnesses next only to diabetic retinopathy. Our proposed approach is a simple image processing based detection of optical disc and retinal blood vessels of branch retinal vein occluded fundus images.

Segmenting Retinal Blood Vessels with Gabor Filter and Automatic Binarization

For timely diagnosis of retinal disease, routine retinal monitoring of people with high risk should be put in place. To assist the ophthalmologists in performing retinal analysis efficiently and accurately, numerous studies have been conducted to propose an automated retinal diagnosis system. One of the crucial steps for such a system is accurate detection of retinal blood vessels from retinal image. In this paper, we investigated the use of automatic binarization methods on pre-processed fundus image to detect retinal blood vessels. Three methods for binarization were investigated in this study, namely Otsu’s method, ISODATA and K-means clustering method. The resulting binarized output indicated good detection of large vessels but most of the smaller vessels were left undetected. To address this issue, Gabor wavelet filter was used to enhance the small blood vessel structures before binarization of the filter output. Combining the binary images from both binarization with and without Gabor filter resulted in significant improvement of the overall detection rate of the retinal blood vessels. The proposed method proved to be comparable to other unsupervised techniques in the literature when validated using the publicly available fundus image database, DRIVE.

Retinal vascular segmentation using superpixel-based line operator and its application to vascular topology estimation.

Automatic methods of analyzing of retinal vascular networks, such as retinal blood vessel detection, vascular network topology estimation, and arteries/veins classification are of great assistance to the ophthalmologist in terms of diagnosis and treatment of a wide spectrum of diseases. We propose a new framework for precisely segmenting retinal vasculatures, constructing retinal vascular network topology, and separating the arteries and veins. A nonlocal total variation inspired Retinex model is employed to remove the image intensity inhomogeneities and relatively poor contrast. For better generalizability and segmentation performance, a superpixel-based line operator is proposed as to distinguish between lines and the edges, thus allowing more tolerance in the position of the respective contours. The concept of dominant sets clustering is adopted to estimate retinal vessel topology and classify the vessel network into arteries and veins. The proposed segmentation method yields competitive results on three public data sets (STARE, DRIVE, and IOSTAR), and it has superior performance when compared with unsupervised segmentation methods, with accuracy of 0.954, 0.957, and 0.964, respectively. The topology estimation approach has been applied to five public databases (DRIVE,STARE, INSPIRE, IOSTAR, and VICAVR) and achieved high accuracy of 0.830, 0.910, 0.915, 0.928, and 0.889, respectively. The accuracies of arteries/veins classification based on the estimated vascular topology on three public databases (INSPIRE, DRIVE and VICAVR) are 0.90.9, 0.910, and 0.907, respectively. The experimental results show that the proposed framework has effectively addressed crossover problem, a bottleneck issue in segmentation and vascular topology reconstruction. The vascular topology information significantly improves the accuracy on arteries/veins classification.

Hybrid Algorithm of Retinal Blood Vessel Detection, Health Estimation, Optic Disc Segmentation and Glaucoma Detection

Hybrid Algorithm of Retinal Blood Vessel Detection, Health Estimation, Optic Disc Segmentation and Glaucoma Detection