scholarly journals Dilated Deep Neural Architectures for Improving Retinal Vessel Extraction

2021 ◽  
Author(s):  
Sathananthavathi V ◽  
Indumathi G
Keyword(s):  
Neural Network ◽  
Blood Vessels ◽  
Network Performance ◽  
Retinal Vessel ◽  
Large Field ◽  
Feature Maps ◽  
Retinal Blood Vessel ◽  
Low Contrast ◽  
Retinal Blood Vessels ◽  
Vessel Extraction

Abstract Human eye is an absolute sensory organ for vision. Eye sight is entirely accomplished by the blood flow in retinal vessels in eye. Diseases such as diabetes retinopathy, hypertension and arteriosclerosis cause change in branching pattern and diameter of retinal blood vessels leading to blindness. These changes can be analyzed by segmenting retinal blood vessel. Hence the retinal vasculature is recognized as the promising anatomical region for the diagnosis of several commonly seen diseases including cardiovascular related and diabetes. In this paper we propose two novel deep neural architectures named as Dilated fully convolved convolutional neural network (FCNN) and dilated depth concatenated neural network (DCNN) to segment the retinal blood vessels. The feature maps of fundus images are extracted by multiple dilated convolutional layers and due to the large field of view by dilation, pixel classification gets improved. The proposed work is evaluated for both the proposed architectures with and without dilation. It is observed from the obtained results that dilation enhances the network performance. To eliminate the non-uniform illumination and low contrast differences effect the preprocessed images are used for training the architectures. The proposed methodologies are experimented on the two publicly available databases DRIVE and STARE database.

scholarly journals Retinal Vessel Segmentation by Deep Residual Learning with Wide Activation

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Yuliang Ma ◽  
Xue Li ◽  
Xiaopeng Duan ◽  
Yun Peng ◽  
Yingchun Zhang
Keyword(s):  
Blood Vessel ◽  
Blood Vessels ◽  
Area Under The Curve ◽  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Superior Performance ◽  
Retinal Blood Vessel ◽  
Low Contrast ◽  
Blood Vessel Segmentation ◽  
Small Vessels

Purpose. Retinal blood vessel image segmentation is an important step in ophthalmological analysis. However, it is difficult to segment small vessels accurately because of low contrast and complex feature information of blood vessels. The objective of this study is to develop an improved retinal blood vessel segmentation structure (WA-Net) to overcome these challenges. Methods. This paper mainly focuses on the width of deep learning. The channels of the ResNet block were broadened to propagate more low-level features, and the identity mapping pathway was slimmed to maintain parameter complexity. A residual atrous spatial pyramid module was used to capture the retinal vessels at various scales. We applied weight normalization to eliminate the impacts of the mini-batch and improve segmentation accuracy. The experiments were performed on the DRIVE and STARE datasets. To show the generalizability of WA-Net, we performed cross-training between datasets. Results. The global accuracy and specificity within datasets were 95.66% and 96.45% and 98.13% and 98.71%, respectively. The accuracy and area under the curve of the interdataset diverged only by 1%∼2% compared with the performance of the corresponding intradataset. Conclusion. All the results show that WA-Net extracts more detailed blood vessels and shows superior performance on retinal blood vessel segmentation tasks.

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

2019 ◽  
Vol 2 (3) ◽  
pp. 43-67
Author(s):  
Sanyukta Chetia ◽  
SR Nirmala
Keyword(s):  
Image Processing ◽  
Blood Vessel ◽  
Blood Vessels ◽  
Retinal Vessel ◽  
Hypertensive Retinopathy ◽  
Retinal Diseases ◽  
Retinal Blood Vessel ◽  
Vessel Segment ◽  
Retinal Blood Vessels ◽  
Vessel Tortuosity

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.  

scholarly journals A detailed and comparative work for retinal vessel segmentation based on the most effective heuristic approaches

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Mehmet Bahadır Çetinkaya ◽  
Hakan Duran
Keyword(s):  
Blood Vessels ◽  
Retinal Image ◽  
Heuristic Algorithms ◽  
Mean Squared Error ◽  
Harmony Search ◽  
Retinal Vessel ◽  
Convergence Speed ◽  
Low Contrast ◽  
Squared Error ◽  
Retinal Blood Vessels

AbstractComputer based imaging and analysis techniques are frequently used for the diagnosis and treatment of retinal diseases. Although retinal images are of high resolution, the contrast of the retinal blood vessels is usually very close to the background of the retinal image. The detection of the retinal blood vessels with low contrast or with contrast close to the background of the retinal image is too difficult. Therefore, improving algorithms which can successfully distinguish retinal blood vessels from the retinal image has become an important area of research. In this work, clustering based heuristic artificial bee colony, particle swarm optimization, differential evolution, teaching learning based optimization, grey wolf optimization, firefly and harmony search algorithms were applied for accurate segmentation of retinal vessels and their performances were compared in terms of convergence speed, mean squared error, standard deviation, sensitivity, specificity. accuracy and precision. From the simulation results it is seen that the performance of the algorithms in terms of convergence speed and mean squared error is close to each other. It is observed from the statistical analyses that the algorithms show stable behavior and also the vessel and the background pixels of the retinal image can successfully be clustered by the heuristic algorithms.

scholarly journals Impact of Novel Image Preprocessing Techniques on Retinal Vessel Segmentation

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2297
Author(s):  
Toufique A. Soomro ◽  
Ahmed Ali ◽  
Nisar Ahmed Jandan ◽  
Ahmed J. Afifi ◽  
Muhammad Irfan ◽  
...  
Keyword(s):  
Blood Vessels ◽  
Retinal Disease ◽  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Low Contrast ◽  
The Public ◽  
Retinal Blood Vessels ◽  
Retinal Vessel Segmentation ◽  
Automated Screening ◽  
Traditional Image

Segmentation of retinal vessels plays a crucial role in detecting many eye diseases, and its reliable computerized implementation is becoming essential for automated retinal disease screening systems. A large number of retinal vessel segmentation algorithms are available, but these methods improve accuracy levels. Their sensitivity remains low due to the lack of proper segmentation of low contrast vessels, and this low contrast requires more attention in this segmentation process. In this paper, we have proposed new preprocessing steps for the precise extraction of retinal blood vessels. These proposed preprocessing steps are also tested on other existing algorithms to observe their impact. There are two steps to our suggested module for segmenting retinal blood vessels. The first step involves implementing and validating the preprocessing module. The second step applies these preprocessing stages to our proposed binarization steps to extract retinal blood vessels. The proposed preprocessing phase uses the traditional image-processing method to provide a much-improved segmented vessel image. Our binarization steps contained the image coherence technique for the retinal blood vessels. The proposed method gives good performance on a database accessible to the public named DRIVE and STARE. The novelty of this proposed method is that it is an unsupervised method and offers an accuracy of around 96% and sensitivity of 81% while outperforming existing approaches. Due to new tactics at each step of the proposed process, this blood vessel segmentation application is suitable for computer analysis of retinal images, such as automated screening for the early diagnosis of eye disease.

A New Deeply Convolutional Neural Network Architecture for Retinal Blood Vessel Segmentation

2020 ◽  
pp. 2157001
Author(s):  
Mali Mohammedhasan ◽  
Harun Uğuz
Keyword(s):  
Neural Network ◽  
Blood Vessel ◽  
Convolutional Neural Network ◽  
Blood Vessels ◽  
Network Architecture ◽  
Vessel Segmentation ◽  
Retinal Blood Vessel ◽  
Low Level ◽  
Blood Vessel Segmentation ◽  
Retinal Blood Vessels

This paper proposes an incoming Deep Convolutional Neural Network (CNN) architecture for segmenting retinal blood vessels automatically from fundus images. Automatic segmentation performs a substantial role in computer-aided diagnosis of retinal diseases; it is of considerable significance as eye diseases as well as some other systemic diseases give rise to perceivable pathologic changes. Retinal blood vessel segmentation is challenging because of the excessive changes in the morphology of the vessels on a noisy background. Previous deep learning-based supervised methods suffer from the insufficient use of low-level features which is advantageous in semantic segmentation tasks. The proposed architecture makes use of both high-level features and low-level features to segment retinal blood vessels. The major contribution of the proposed architecture concentrates on two important factors; the first in its supplying of extremely modularized network architecture of aggregated residual connections which enable us to copy the learned layers from the shallower model and developing additional layers to identity mapping. The second is to improve the utilization of computing resources within the network. This is achieved through a skillfully crafted design that allows for increased depth and width of the network while maintaining the stability of its computational budget. Experimental results show the effectiveness of using aggregated residual connections in segmenting retinal vessels more accurately and clearly. Compared to the best existing methods, the proposed method outperformed other existing methods in different measures, comprised less false positives at fine vessels, and caressed more clear lines with sufficient details like the human annotator.

Retinal Blood Vessel Extraction Using a New Enhancement Technique of Modified Convolution Filters and Sauvola Thresholding

2021 ◽  
Author(s):  
Erwin ◽  
Hadrians Kesuma Putra ◽  
Bambang Suprihatin ◽  
Fathoni
Keyword(s):  
Blood Vessel ◽  
Blood Vessels ◽  
Retinal Image ◽  
Histogram Equalization ◽  
Retinal Blood Vessel ◽  
Retinal Blood Vessels ◽  
Convolution Filter ◽  
Image Improvement ◽  
Vessel Extraction ◽  
Convolution Filters

The retinal blood vessels in humans are major components with different shapes and sizes. The extraction of the blood vessels from the retina is an important step to identify the type or nature of the pattern of the diseases in the retina. Furthermore, the retinal blood vessel was also used for diagnosis, detection, and classification. The most recent solution in this topic is to enable retinal image improvement or enhancement by a convolution filter and Sauvola threshold. In image enhancement, gamma correction is applied before filtering the retinal fundus. After that, the image should be transformed to a gray channel to enhance pictorial clarity using contrast-limited histogram equalization. For filter, this paper combines two convolution filters, namely sharpen and smooth filters. The Sauvola threshold, the morphology, and the medium filter are applied to extract blood vessels from the retinal image. This paper uses DRIVE and STARE datasets. The accuracies of the proposed method are 95.37% for DRIVE with a runtime of 1.77[Formula: see text]s and 95.17% for STARE with 2.05[Formula: see text]s runtime. Based on the result, it concludes that the proposed method is good enough to achieve average calculation parameters of a low time quality, quick, and significant.

scholarly journals Retinal blood vessels segmentation using classical edge detection filters and the neural network

2021 ◽  
Vol 23 ◽  
pp. 100521
Author(s):  
Beaudelaire Saha Tchinda ◽  
Daniel Tchiotsop ◽  
Michel Noubom ◽  
Valerie Louis-Dorr ◽  
Didier Wolf
Keyword(s):  
Neural Network ◽  
Edge Detection ◽  
Blood Vessels ◽  
The Neural Network ◽  
Retinal Blood Vessels

Classification and grading of diabetic retinopathy images using mixture of ensemble classifiers

2021 ◽  
pp. 1-13
Author(s):  
R. Bhuvaneswari ◽  
S. Ganesh Vaidyanathan
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Network ◽  
Blood Vessels ◽  
Support Vector ◽  
Network Architectures ◽  
Ensemble Classifiers ◽  
Feature Maps ◽  
Class Labels ◽  
Hierarchical Features

Diabetic Retinopathy (DR) is one of the most common diabetic diseases that affect the retina’s blood vessels. Too much of the glucose level in blood leads to blockage of blood vessels in the retina, weakening and damaging the retina. Automatic classification of diabetic retinopathy is a challenging task in medical research. This work proposes a Mixture of Ensemble Classifiers (MEC) to classify and grade diabetic retinopathy images using hierarchical features. We use an ensemble of classifiers such as support vector machine, random forest, and Adaboost classifiers that use the hierarchical feature maps obtained at every pooling layer of a convolutional neural network (CNN) for training. The feature maps are generated by applying the filters to the output of the previous layer. Lastly, we predict the class label or the grade for the given test diabetic retinopathy image by considering the class labels of all the ensembled classifiers. We have tested our approaches on the E-ophtha dataset for the classification task and the Messidor dataset for the grading task. We achieved an accuracy of 95.8% and 96.2% for the E-ophtha and Messidor datasets, respectively. A comparison among prominent convolutional neural network architectures and the proposed approach is provided.

scholarly journals Multiloss Function Based Deep Convolutional Neural Network for Segmentation of Retinal Vasculature into Arterioles and Venules

2019 ◽  
Vol 2019 ◽  
pp. 1-17 ◽  
Author(s):  
Sufian A. Badawi ◽  
Muhammad Moazam Fraz
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Retinal Vessel ◽  
Automated System ◽  
Retinal Vasculature ◽  
Disease Prognosis ◽  
Learning Techniques ◽  
Retinal Blood Vessels

The arterioles and venules (AV) classification of retinal vasculature is considered as the first step in the development of an automated system for analysing the vasculature biomarker association with disease prognosis. Most of the existing AV classification methods depend on the accurate segmentation of retinal blood vessels. Moreover, the unavailability of large-scale annotated data is a major hindrance in the application of deep learning techniques for AV classification. This paper presents an encoder-decoder based fully convolutional neural network for classification of retinal vasculature into arterioles and venules, without requiring the preliminary step of vessel segmentation. An optimized multiloss function is used to learn the pixel-wise and segment-wise retinal vessel labels. The proposed method is trained and evaluated on DRIVE, AVRDB, and a newly created AV classification dataset; and it attains 96%, 98%, and 97% accuracy, respectively. The new AV classification dataset is comprised of 700 annotated retinal images, which will offer the researchers a benchmark to compare their AV classification results.

Sign in / Sign up

Export Citation Format

Share Document