Exudates In Retinal Images Research Articles

Screening diabetic retinopathy and exudates in retinal images using dual functional convolutional neural networks

Exudates are the abnormal pattern lesions in Diabetic Retinopathy (DR) images, which is the primary cause of DR in diabetic patients. Therefore, its detection process is essential for further severity estimation of DR images. Automated detection systems’ robustness can be hampered by training datasets that are not representative. In this paper, the DR image is detected and classified using the proposed Dual Functional Convolutional Neural Networks (DFCNN). This proposed system consists of a noise detection and removal subblock, enhancement subblock, Gabor transform subblock, Feature computation subblock, and the proposed CNN classification architecture subblock. This proposed methodology is divided into two modules: a training module and a testing module. In the training module, the proposed DFCNN classification architecture is used to train both the abnormal case (DR case) and the healthy case (HCA) retinal images. In the testing module, the test source retinal image is classified as either a beneficial or DR case retinal image. From the classified DR case retinal image, the exudates are identified through the segmentation process in this research work. This developed DR and exudates detection system stated in this paper are evaluated on DRIVE, and DIARETDB1 retinal images and the experimental results are conducted with respect to various performance metrics in this paper. Once the suggested methodology was compared to other classification approaches, the proposed method’s accuracy was found to be greater (99.4 %).

Semantic segmentation of retinal exudates using a residual encoder-decoder architecture in diabetic retinopathy.

Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time-consuming and requires intense effort due to the small size of the lesion and the low contrast of the images. Thus, computer-assisted diagnosis of retinal disease based on the detection of red lesions has been actively explored recently. In this paper, we present a comparison of deep convolutional neural network (CNN) architectures and propose a residual CNN with residual skip connections to reduce the parameter for the semantic segmentation of exudates in retinal images. A suitable image augmentation technique is used to improve the performance of network architecture. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. A comparative performance analysis of three benchmark databases: E-ophtha, DIARETDB1, and Hamilton Ophthalmology Institute's Macular Edema, is presented. The proposed method achieves a precision of 0.95, 0.92, 0.97, accuracy of 0.98, 0.98, 0.98, sensitivity of 0.97, 0.95, 0.95, specificity of 0.99, 0.99, 0.99, and area under the curve of 0.97, 0.94, and 0.96, respectively. RESEARCH HIGHLIGHTS: The research focuses on the detection and segmentation of exudates in diabetic retinopathy, a disease affecting the retina. Early detection of exudates is important to avoid vision problems and requires continuous screening and treatment. Currently, manual detection is time-consuming and requires intense effort. The authors compare qualitative results of the state-of-the-art convolutional neural network (CNN) architectures and propose a computer-assisted diagnosis approach based on deep learning, using a residual CNN with residual skip connections to reduce parameters. The proposed method is evaluated on three benchmark databases and demonstrates high accuracy and suitability for diabetic retinopathy screening.

Support vector machine and deep-learning object detection for localisation of hard exudates

Hard exudates are one of the main clinical findings in the retinal images of patients with diabetic retinopathy. Detecting them early significantly impacts the treatment of underlying diseases; therefore, there is a need for automated systems with high reliability. We propose a novel method for identifying and localising hard exudates in retinal images. To achieve fast image pre-scanning, a support vector machine (SVM) classifier was combined with a faster region-based convolutional neural network (faster R-CNN) object detector for the localisation of exudates. Rapid pre-scanning filtered out exudate-free samples using a feature vector extracted from the pre-trained ResNet-50 network. Subsequently, the remaining samples were processed using a faster R-CNN detector for detailed analysis. When evaluating all the exudates as individual objects, the SVM classifier reduced the false positive rate by 29.7% and marginally increased the false negative rate by 16.2%. When evaluating all the images, we recorded a 50% reduction in the false positive rate, without any decrease in the number of false negatives. The interim results suggested that pre-scanning the samples using the SVM prior to implementing the deep-network object detector could simultaneously improve and speed up the current hard exudates detection method, especially when there is paucity of training data.

A Data Mining Inspired Methodology towards the Identification of Diabetic Retinopathy

The Biomedical image analysis technique used in most of the clinical diagnosis activities, which is one of the explorative areas that appeal intense significance among scientists. The retinal fundus images are utilized in clinical diagnosis extensively for the treatment and to observe various eye diseases. Diabetic retinopathy is one of the foremost sources for blindness. The major diagnostic sign of diabetic retinopathy is the damage of blood vessels due to various reasons in the eye and then establishment of lesions in the retina. The screening and detection of Diabetic Retinopathy can be performed using retinal fundus images. The identification and analysis of diabetic retinopathy (DR) by means of color fundus images involves experienced practitioners to recognize the existence of many small topographies with a detailed grading system, makes this a complex and time-consuming mission. In this paper, a novel systematized method for the discovery of exudates in retinal images to diagnose diabetic retinopathy. The color fundus images are characterized and analyzed to find microaneurysms on the retina and provides the severity. The algorithm is tested on datasets provided by ophthalmologists and Messidor dataset, which gave excellent and promising results.

FPGA and MATLAB Based Solution for Retinal Exudate Detection

Now-a-days, image processing is extensively used for analysis of several biomedical images to identify the complications in one’s health. Most of the solutions offered are based on application software. Since these solutions are expensive, an embedded system approach is being explored in the recent years, considering its cost-effectiveness. This paper propounds an embedded system approach to identify exudates in retinal images. These exudates are often identified as indicators of a medical disorder known as Diabetic Retinopathy, which is one of the medical complications that arise due to high blood sugar levels. The algorithm employs statistical analysis using histogram to enhance the contrast of the images, thus assisting in extracting exudates by utilising the elementary concepts of image processing. Since the pixel characteristics of exudates and optic disk match, it becomes inevitable to first eliminate optic disk from retinal images, and then extract exudates. The prototype has been developed on MATLAB and is downloaded on an Artix 7 FPGA with minimal usage of its resources. The system proposed in this paper results in an accuracy of 90%.

Detection and classification of hard exudates in retinal images

Detection and classification of hard exudates in retinal images

RETRACTED: Detection of exudates using neuro-fuzzy technique

Diabetic retinopathy is a common condition of an ailment where the retina is harmed on the grounds that fluid breaks away from the walls of blood vessels into the retina. The large population is affected by diabetic retinopathy and hence research in the area of automated screening has acquired major research interest in the scientific community. The diagnosing features for diabetic retinopathy comprises of identifying deformations of minute blood vessel in form of exudates and its features occurring in and around the regions of fundus which will result into exudes, hemorrhages, or microaneurysms. This feature is often hard to be classified by naked eyes and need trained personnel for close inspection before making diagnosis. Therefore, a comprehensive machine learning tool is in the demand for automated diabetic retinopathy detection. Neural networks have given promising results in the field of classification. Therefore, we present a hybrid neural network-based method with realistic clinical potential. In this study, we present a neuro-fuzzy technique, which is developed for identification of exudates in retinal images and is utilized for the extraction of essential features from the retinal images of patient’s eyeballs. We trained this hybrid neural network base technique over a set of 25,600 training images for color retinal images and tested it over 12,000 testing image set for binocular model. The method achieves an accuracy of 95.4% recognition on non-noisy images and 93% on noisy images; thereby giving a consistency rate of 91% in correspondence with the ophthalmologist.

An Improved Method for Automated Identification of Hard Exudates in Diabetic Retinopathy Disease

The presence of Hard Exudates in retinal images is one of the significant indications of Diabetic Retinopathy disease. Early detection of Hard Exudates obviously prevents the vision loss very effectively. Today, the development of appropriate Pre-processing stages for Hard Exudate identification through automated screening is an open issue. In this research article, a mathematical morphology based image processing technique is presented for the identification of Hard Exudates in retinal images. The analysis of noisy and low-contrast retinal images shows the importance of this method. In this research work, 570 input images collected from Hospital are examined by the k-fold cross-validation technique. The sensitivity and specificity, two important parameters for performance analysis of Hard Exudate screening, are 97.36% and 99.31%, respectively. In Receiver Operating Characteristics the Area Under Curve (AUC) is 0.93 (average for k folds). Public datasets e_Ophtha_EX and DIARETDB1 are used here to compare the screening performance with existing algorithms and AUC is 0.97 and 0.98, respectively. Thus, the screening result on both Hospital dataset and Public dataset reflects the effectiveness of the proposed method.

Use of Convolutional Neural Network for Fully Automated Segmentation of Hard Exudates in Retinal Images

Diabetic retinopathy (DR), is a complication with diabetes caused by damaged blood vessels in the back of the retina. DR affects 126.6 million people around the world and is the leading cause of blindness. Hard exudates are a type of lesion caused by the damaged blood vessels and are an early marker for DR. In this research, a fully automatic deep learning method has been developed that is able to delineate hard exudate lesions in retinal images. This allows the lesion volume to be calculated and thus determine DR severity. This technology would remove the need for doctors in the diagnosis process, therefore making the diagnosis faster and more accessible to people around the world. Our dataset consisted of 58 images and was used to train a fully convolutional neural network with a U-net architecture. The U-net consists of a contracting path followed by a symmetric expansive path that was used to learn features of the images. These features were then used to differentiate hard exudates from regular tissue allowing them to be segmented. After creating the model 26 images were used for testing. Results of the U-net model showed a Dice similarity coefficient of 67.23 ± 13.60%, a specificity of 99.74 ± 0.25%, and precision of 75.87 ± 18.14% when comparing the algorithm generated images to the manually segmented ground truths. These results show that the model is precisely delineating the hard exudates and therefore is a viable way to diagnose the severity of DR.

Computational Methods for Exudates Detection and Macular Edema Estimation in Retinal Images: A Survey

Automated retinal image analysis has been widey adopted for diagnosing ophthalmic and systemic diseases which includes macular edema, diabetic and hypertensive retinopathy. Automatic assessment of retinal images can assist clinicians in screening patients with early diagnosis and in turn provide timely treatment to prevent vision loss. The appearance of exudates in retinal images is one of the early symptom of macular edema and diabetic retinopathy. This paper presents a review of image analysis/computer vision techniques utilized for exudate detection and segmentation in retinal images. The objectives of this paper are to categorize different techniques for exudate detection and provide a critical analysis on the effectiveness of each technique. Besides comparative analysis a detailed overview of quantifiable performance measures of reviewed techniques is also presented. A anatomical structures and disease manifestation in retinal images are also provided for new researchers. We have also presented a summary of publicly available datasets for exudata detection. Moreover, the current trends, open problems and future research direction in automated screening of macular edema has been discussed.

Automatic Detection of Exudates in Retinal Images using Region-Based, Neighborhood and Block Operation

Exudates detection is one of the research areas attracting great attention of physicians and scientists. A region-based, neighborhood, block operation and optimal global thresholding are proposed as new methods to exudates detection. The exudates are coarse and fine segmentation following preprocessing steps, i.e., color mapping, image contrast enhancement, fuzzy filtering and optic disc localization. To classify the retinal images into non-exudates and exudates, a set of features such as texture, color, size and the edge is extracted. The exudates procedure succeeded in an overall generalization accuracy of 98.62% with 98.18% sensitivity and 98.32% specificity in local databases. Moreover, the results are presented to show the advantage of the proposed method in a public database with an accuracy of 92.14.

Assessing the importance of features for detection of hard exudates in retinal images

Assessing the importance of features for detection of hard exudates in retinal images

Hard Limiting and Soft Computing Techniques for Detection of Exudates in Retinal Images: A Futuristic Review

Hard Limiting and Soft Computing Techniques for Detection of Exudates in Retinal Images: A Futuristic Review

Improving the performance of an ensemble-based exudate detection system using stochastic parameter optimization.

In this paper, we propose an efficient way to determine the optimal parameter setting of an ensemble based system dedicated to the detection of exudates in retinal images. We show that the optimal parameter settings of an individual detector may be different, when it becomes a member of an ensemble. We consider a stochastic search algorithm to solve this optimization problem. However, since the computational demand is extremely high, we introduce a specific speed-up by sampling the test dataset in every search step. We show that this approach is equivalent to the noisy evaluation of the energy function and fits the corresponding theoretical results to our case. Experimental results showing improvement with respect to the member exudate detectors and individually optimal parameter settings are presented for publicly available datasets.

FPGA Based Design Implementation forDetection of Exudates Using XSG

A methodology for implementing DSP applications on Field programmable gate arrays employing Xilinx System Generator (XSG) is presented. This paper outlines efficient hardware architecture for detection of exudates in retinal images. The proposed design comprises architecture for Sobel and Prewitt edge detection algorithms. The egde map image obtained is enhanced for its perception using contrast stretching. Further the image is segmented to detect the exudates. This design has been implemented on Virtex-II Pro (xc2vp30-7ff896 platform). The code is synthesized within ISE 9.2 development suite. The results obtained via hardware software co-simulation use limited FPGA resources at higher maximum frequency.

Automatic detection of exudates in retinal images based on threshold moving average models

Since exudate diagnostic procedures require the attention of an expert ophthalmologist as well as regular monitoring of the disease, the workload of expert ophthalmologists will eventually exceed the current screening capabilities. Retinal imaging technology is a current practice screening capability providing a great potential solution. In this paper, a fast and robust automatic detection of exudates based on moving average histogram models of the fuzzy image was applied, and then the better histogram was derived. After segmentation of the exudate candidates, the true exudates were pruned based on Sobel edge detector and automatic Otsu's thresholding algorithm that resulted in the accurate location of the exudates in digital retinal images. To compare the performance of exudate detection methods we have constructed a large database of digital retinal images. The method was trained on a set of 200 retinal images, and tested on a completely independent set of 1220 retinal images. Results show that the exudate detection method performs overall best sensitivity, specificity, and accuracy of 90.42%, 94.60%, and 93.69%, respectively.

Identifying Abnormalities in the Retinal Images using SVM Classifiers

early detection of exudates in retinal images is a challenging task. With the global diabetic population increasing at an alarming rate, there is need for development of automated systems for detection of exudates. The main obstacle in exudates detection is extreme variability of color and contrast in retinal images that depends on the degree of pigmentation, size of the pupil and illumination. The aim of this paper is to develop and validate systems for detection of hard exudates and classify the input image as normal or diseased one. The authors have proposed and implemented novel method based on color and texture features. Performance analysis of SVM and KNN classifiers is presented. Images classified by these classifiers are validated by expert opthamalagists. . KeywordsRetinopathy, SVM classifier, KNN classifier Exudates.

Diagnosis of diabetic retinopathy by employing image processing technique to detect exudates in retinal images

Diabetic retinopathy (DR) is a microvascular complication of long-term diabetes and it is the major cause of visual impairment because of changes in blood vessels of the retina. Major vision loss because of DR is highly preventable with regular screening and timely intervention at the earlier stages. The presence of exudates is one of the primitive signs of DR and the detection of these exudates is the first step in automated screening for DR. Hence, exudates detection becomes a significant diagnostic task, in which digital retinal imaging plays a vital role. In this study, the authors propose an algorithm to detect the presence of exudates automatically and this helps the ophthalmologists in the diagnosis and follow-up of DR. Exudates are normally detected by their high grey-level variations and they have used an artificial neural network to perform this task by applying colour, size, shape and texture as the features. The performance of the authors algorithm has been prospectively tested by using DIARETDB1 database and evaluated by comparing the results with the ground-truth images annotated by expert ophthalmologists. They have obtained illustrative results of mean sensitivity 96.3%, mean specificity 99.8%, using lesion-based evaluation criterion and achieved a classification accuracy of 99.7%.

Neural network based detection of hard exudates in retinal images

Diabetic retinopathy (DR) is an important cause of visual impairment in developed countries. Automatic recognition of DR lesions in fundus images can contribute to the diagnosis of the disease. The aim of this study is to automatically detect one of these lesions, hard exudates (EXs), in order to help ophthalmologists in the diagnosis and follow-up of the disease. We propose an algorithm which includes a neural network (NN) classifier for this task. Three NN classifiers were investigated: multilayer perceptron (MLP), radial basis function (RBF) and support vector machine (SVM). Our database was composed of 117 images with variable colour, brightness, and quality. 50 of them (from DR patients) were used to train the NN classifiers and 67 (40 from DR patients and 27 from healthy retinas) to test the method. Using a lesion-based criterion, we achieved a mean sensitivity (SE l ) of 88.14% and a mean positive predictive value (PPV l ) of 80.72% for MLP. With RBF we obtained SE l = 88.49% and PPV l = 77.41%, while we reached SE l = 87.61% and PPV l = 83.51% using SVM. With an image-based criterion, a mean sensitivity (SE i ) of 100%, a mean specificity (SP i ) of 92.59% and a mean accuracy (AC i ) of 97.01% were obtained with MLP. Using RBF we achieved SE i = 100%, SP i = 81.48% and AC i = 92.54%. With SVM the image-based results were SE i = 100%, SP i = 77.78% and AC i = 91.04%.

Automated detection of exudates for diabetic retinopathy screening

Automated image analysis is being widely sought to reduce the workload required for grading images resulting from diabetic retinopathy screening programmes. The recognition of exudates in retinal images is an important goal for automated analysis since these are one of the indicators that the disease has progressed to a stage requiring referral to an ophthalmologist. Candidate exudates were detected using a multi-scale morphological process. Based on local properties, the likelihoods of a candidate being a member of classes exudate, drusen or background were determined. This leads to a likelihood of the image containing exudates which can be thresholded to create a binary decision. Compared to a clinical reference standard, images containing exudates were detected with sensitivity 95.0% and specificity 84.6% in a test set of 13 219 images of which 300 contained exudates. Depending on requirements, this method could form part of an automated system to detect images showing either any diabetic retinopathy or referable diabetic retinopathy.