Diabetic Retinopathy In Retinal Images Research Articles

Rapid detection of diabetic retinopathy in retinal images: a new approach using transfer learning and synthetic minority over-sampling technique

The challenge of early detection of diabetic retinopathy (DR), a leading cause of vision loss in working-age individuals in developed nations, was addressed in this study. Current manual analysis of digital color fundus photographs by clinicians, although thorough, suffers from slow result turnaround, delaying necessary treatment. To expedite detection and improve treatment timeliness, a novel automated detection system for DR was developed. This system utilized convolutional neural networks. Visual geometry group 16-layer network (VGG16), a pre-trained deep learning model, for feature extraction from retinal images and the synthetic minority over-sampling technique (SMOTE) to handle class imbalance in the dataset. The system was designed to classify images into five categories: normal, mild DR, moderate DR, severe DR, and proliferative DR (PDR). Assessment of the system using the Kaggle diabetic retinopathy dataset resulted in a promising 93.94% accuracy during the training phase and 88.19% during validation. These results highlight the system's potential to enhance DR diagnosis speed and efficiency, leading to improved patient outcomes. The study concluded that automation and artificial intelligence (AI) could play a significant role in timely and efficient disease detection and management.

General Deep Learning Model for Detecting Diabetic Retinopathy

Diabetic retinopathy (DR) is a common and potentially sight-threatening complication of diabetes. Early detection and accurate diagnosis of DR are crucial for effective treatment and prevention of vision loss. In recent years, deep learning techniques have shown remarkable success in various medical imaging tasks. This research paper presents a general deep learning model designed specifically for detecting diabetic retinopathy in retinal images. The proposed model leverages convolutional neural networks (CNNs) to automatically extract relevant features from retinal images and classify them into different stages of DR severity. Experimental results demonstrate the effectiveness and robustness of the proposed model in accurately detecting DR, showcasing its potential for clinical deployment.

Detecting and staging diabetic retinopathy in retinal images using multi-branch CNN

PurposeThis paper aims to propose a solution for detecting and grading diabetic retinopathy (DR) in retinal images using a convolutional neural network (CNN)-based approach. It could classify input retinal images into a normal class or an abnormal class, which would be further split into four stages of abnormalities automatically.Design/methodology/approachThe proposed solution is developed based on a newly proposed CNN architecture, namely, DeepRoot. It consists of one main branch, which is connected by two side branches. The main branch is responsible for the primary feature extractor of both high-level and low-level features of retinal images. Then, the side branches further extract more complex and detailed features from the features outputted from the main branch. They are designed to capture details of small traces of DR in retinal images, using modified zoom-in/zoom-out and attention layers.FindingsThe proposed method is trained, validated and tested on the Kaggle dataset. The regularization of the trained model is evaluated using unseen data samples, which were self-collected from a real scenario from a hospital. It achieves a promising performance with a sensitivity of 98.18% under the two classes scenario.Originality/valueThe new CNN-based architecture (i.e. DeepRoot) is introduced with the concept of a multi-branch network. It could assist in solving a problem of an unbalanced dataset, especially when there are common characteristics across different classes (i.e. four stages of DR). Different classes could be outputted at different depths of the network.

Novel Technique for Segmentation and Identification of Diabetic Retinopathy in Retinal Images Using GMM and Compare Accuracy with SVM

The main objective of this work is to detect blood vessel segmentation of diabetic retinopathy in low-resolution retinal images using two machine learning algorithms and perform accuracy comparison. Materials and methods: Gaussian Mixture Model (GMM) and Support Vector Machine (SVM) are implemented to detect and segment the blood vessel in retinal images dataset with 40 samples (20 per group). Results: From the MATLAB simulation result, GMM classified the image with better accuracy of 95% compared to SVM classifier accuracy 89%, attained a significant accuracy ratio (p=0.020) in statistical analysis. Conclusion: GMM provides better accuracy compared to SVM classifiers in segmentation and detection.

Hybrid multi-kernel SVM algorithm for detection of microaneurysm in color fundus images.

Diabetic retinopathy (DR) is a chronic disease that may cause vision loss in diabetic patients. Microaneurysms which are characterized by small red spots on the retina due to fluid or blood leakage from the weak capillary wall often occur during the early stage of DR, making screening at this stage is essential. In this paper, an automatic screening system for early detection of DR in retinal images is developed using a combined shape and texture features. Due to minimum number of hand-crafted features, the computational burden is much reduced. The proposed hybrid multi-kernel support vector machine classifier is constructed by learning a kernel model formed as a combination of the base kernels. This approach outperforms the recent deep learning techniques in terms of the evaluation metrics. The efficiency of the proposed scheme is experimentally validated on three public datasets - Retinopathy Online Challenge, DIARETdB1, MESSIDOR, and AGAR300 (developed for this study). Studies reveal that the proposed model produced the best results of 0.503 in ROC dataset, 0.481 in DIARETdB1, and 0.464 in the MESSIDOR dataset in terms of FROC score. The AGAR300 database outperforms the existing MA detection algorithm in terms of FROC, AUC, F1 score, precision, sensitivity, and specificity which guarantees the robustness of this system.

Euler characteristic surfaces

<p style='text-indent:20px;'>In this paper, we investigate the use of the Euler characteristic for the topological data analysis, particularly over higher dimensional parameter spaces. The Euler characteristic is a classical, well-understood topological invariant that has appeared in numerous applications, primarily in the context of random fields. The goal of this paper, is to present the extension of using the Euler characteristic in higher dimensional parameter spaces. The topological data analysis of higher dimensional parameter spaces using stronger invariants such as homology, has and continues to be the subject of intense research. However, as important theoretical and computational obstacles remain, the use of the Euler characteristic represents an important intermediary step toward multi-parameter topological data analysis. We show the usefulness of the techniques using generated examples as well as a real world dataset of detecting diabetic retinopathy in retinal images.</p>

Detection and Grading of Diabetic Retinopathy in Retinal Images Using Deep Intelligent Systems: A Comprehensive Review

Diabetic Retinopathy (DR) is an eye disease that mainly affects people with diabetes. People affected by DR start losing their vision from an early stage even though the symptoms are identified only at the later stage. Once the vision is lost, it cannot be regained but can be prevented from causing any further damage. Early diagnosis of DR is required for preventing vision loss, for which a trained ophthalmologist is required. The clinical practice is time-consuming and is not much successful in identifying DR at early stages. Hence, Computer-Aided Diagnosis (CAD) system is a suitable alternative for screening and grading of DR for a larger population. This paper addresses the different stages in CAD system and the challenges in identifying and grading of DR by analyzing various recently evolved techniques. The performance metrics used to evaluate the Computer-Aided Diagnosis system for clinical practice is also discussed.

An abnormality detection of retinal fundus images by deep convolutional neural networks

Identification of retinal diseases is a test for the ophthalmologists as the anomalies are just unmistakable at the beginning period. Early detection of these diseases can avoid lasting vision misfortune. Dealing with a lot of retinal images and location of variations from the norm because of these infections is difficult just as tedious. In this work, the deep learning algorithm has proposed to check the abnormality condition of retina with the help of retinal fundus images. In deep leaning a training set is produced with features of variations from the norm present in the retinal images and the infection the retina is experiencing. The deep Convolutional Neural Network (CNN) classifier predicts the infection for every retinal images in the wake of social event the learning from training the set. The rightness of desire is resolved to evaluate the viability of the classifier. The proposed technique was executed in MATLAB and assessed both normal and abnormal diabetic retinopathy retinal images of IDRID, ROC, and local datasets. The proposed technique has gotten better execution measurements, for example, sensitivity of 98.2%, Specificity of 98.45%, accuracy of 98.56% and average area under receiver operating characteristics of 0.9 when contrasted with different conditions of the workmanship strategies.

Automatic Grading System for Diabetic Retinopathy Diagnosis Using Deep Learning Artificial Intelligence Software

ABSTRACT Purposes: To describe the development and validation of an artificial intelligence–based, deep learning algorithm (DeepDR) for the detection of diabetic retinopathy (DR) in retinal fundus photographs. Methods: Five hundred fundus images, which had detailed labelling of DR lesions, were transmitted to be analysed, including localization of the optic disk and macular, vessel segmentation, detection of lesions, and grading of DR. The multi-level iterative method of convolutional neural network and the strategy of enhanced learning were used to improve the accuracy of the system (DeepDR) for grading DR. Three public data sets were used to further train the software. The final grading results were tested based on the fundus images provided by the hospitals. Results: For 6788 fundus images (both macular and disc centred) of two Hospital Eye Center, the detection of microaneurysm, haemorrhage and hard exudates had an accuracy of 99.7%, 98.4% and 98.1%, respectively. The current algorithm accuracy was 0.96. Another 20,000 fundus images from community screening were selected, and 7593 photos of poor quality were excluded according to quality standards. Accuracy for accurate staging of fundus photos: accuracy was 0.9179. The sensitivity, specificity and area under the curve (AUC) were 80.58%, 95.77% and 0.9327, respectively. Conclusions: This artificial intelligence–based DeepDR can be used with high accuracy for the detection of DR in retinal images. This technology offers the potential to increase the efficiency and accessibility of DR screening programs.

Improving Microaneurysm Detection from Non-dilated Diabetic Retinopathy Retinal Images using Feature Optimization

Diabetic retinopathy usually does not presents symptoms in an early stage until it gets to a severe stage. An early stage of diabetic retinopathy is associated with the presence of microaneurysms (MAs). The occurrence of blindness can be reduced significantly if MAs are detected. This paper presented an approach to improve automatic MAs detection using feature optimisation. Candidate MAs are detected using mathematic morphological techniques. Originally 20 features are presented. To verify the relevance of all original features, a feature optimisation process is performed. The optimal feature set is searched by a machine learning approach, like naive Bayes and support vector machine classifier. Hand-drawn ground-truth images from expert ophthalmologists are used to measure the performance evaluation. The results showed that the proposed optimal feature set could significantly improve MA detection.

Severity analysis of diabetic retinopathy in retinal images using hybrid structure descriptor and modified CNNs

Imaging which plays a central role in the diagnosis and treatment planning of diabetic retinopathy and severity is an important diagnostic indicator in treatment planning and results assessment. Retinal image classification is an increasing attention among researchers in the field of computer vision, as it plays an important role in disease diagnosis. Computer Aided Diagnosis (CAD) is in wide practice in clinical work for the location and anticipation of different kinds of variations; the automated image classification systems used for such applications must be significantly efficient in terms of accuracy since false detection may lead to fatal results. Another requirement is the high convergence rate which accounts for the practical feasibility of the system. The overall classification accuracy of the proposed HTF with MCNNs is 98.41%, but the existing methods HTF with SVM and HTF with CNNs produce 97.84% and 96.65% respectively.

An Automated Grading System for Detection of Vision-Threatening Referable Diabetic Retinopathy on the Basis of Color Fundus Photographs.

The goal of this study was to describe the development and validation of an artificial intelligence-based, deep learning algorithm (DLA) for the detection of referable diabetic retinopathy (DR). A DLA using a convolutional neural network was developed for automated detection of vision-threatening referable DR (preproliferative DR or worse, diabetic macular edema, or both). The DLA was tested by using a set of 106,244 nonstereoscopic retinal images. A panel of ophthalmologists graded DR severity in retinal photographs included in the development and internal validation data sets (n = 71,043); a reference standard grading was assigned once three graders achieved consistent grading outcomes. For external validation, we tested our DLA using 35,201 images of 14,520 eyes (904 eyes with any DR; 401 eyes with vision-threatening referable DR) from population-based cohorts of Malays, Caucasian Australians, and Indigenous Australians. Among the 71,043 retinal images in the training and validation data sets, 12,329 showed vision-threatening referable DR. In the internal validation data set, the area under the curve (AUC), sensitivity, and specificity of the DLA for vision-threatening referable DR were 0.989, 97.0%, and 91.4%, respectively. Testing against the independent, multiethnic data set achieved an AUC, sensitivity, and specificity of 0.955, 92.5%, and 98.5%, respectively. Among false-positive cases, 85.6% were due to a misclassification of mild or moderate DR. Undetected intraretinal microvascular abnormalities accounted for 77.3% of all false-negative cases. This artificial intelligence-based DLA can be used with high accuracy in the detection of vision-threatening referable DR in retinal images. This technology offers potential to increase the efficiency and accessibility of DR screening programs.

Retinal vessel feature extraction from fundus image using image processing techniques

Retinal Vessel detection for retinal images play crucial role in medical field for proper diagnosis and treatment of various diseases like diabetic retinopathy, hypertensive retinopathy etc. This paper deals with image processing techniques for automatic analysis of blood vessel detection of fundus retinal image using MATLAB tool. This approach uses intensity information and local phase based enhancement filter techniques and morphological operators to provide better accuracy.Objective: The effect of diabetes on the eye is called Diabetic Retinopathy. At the early stages of the disease, blood vessels in the retina become weakened and leak, forming small hemorrhages. As the disease progress, blood vessels may block, and sometimes leads to permanent vision loss. To help Clinicians in diagnosis of diabetic retinopathy in retinal images with an early detection of abnormalities with automated tools.Methods: Fundus photography is an imaging technology used to capture retinal images in diabetic patient through fundus camera. Adaptive Thresholding is used as pre-processing techniques to increase the contrast, and filters are applied to enhance the image quality. Morphological processing is used to detect the shape of blood vessels as they are nonlinear in nature.Results: Image features like, Mean and Standard deviation and entropy, for textural analysis of image with Gray Level Co-occurrence Matrix features like contrast and Energy are calculated for detected vessels.Conclusion: In diabetic patients eyes are affected severely compared to other organs. Early detection of vessel structure in retinal images with computer assisted tools may assist Clinicians for proper diagnosis and pathology.

Deep multiple instance learning for automatic detection of diabetic retinopathy in retinal images

As a weakly supervised learning technique, multiple instance learning (MIL) has shown an advantage over supervised learning methods for automatic detection of diabetic retinopathy (DR): only the image-level annotation is needed to achieve both detection of DR images and DR lesions, making more graded and de-identified retinal images available for learning. However, the performance of existing studies on this technique is limited by the use of handcrafted features. The authors propose a deep MIL method for DR detection, which jointly learns features and classifiers from data and achieves a significant improvement on detecting DR images and their inside lesions. Specifically, a pre-trained convolutional neural network is adapted to achieve the patch-level DR estimation, and then global aggregation is used to make the classification of DR images. Further, the authors propose an end-to-end multi-scale scheme to better deal with the irregular DR lesions. For detection of DR images, they achieve an area under the ROC curve of 0.925 on a subset of a Kaggle dataset, and 0.960 on Messidor. For detection of DR lesions, they achieve an F1-score of 0.924 with sensitivity 0.995 and precision 0.863 on DIARETDB1 using the connected component-level validation.

Segmentation and classification of bright lesions to diagnose diabetic retinopathy in retinal images.

In view of predicting bright lesions such as hard exudates, cotton wool spots, and drusen in retinal images, three different segmentation techniques have been proposed and their effectiveness is compared with existing segmentation techniques. The benchmark images with annotations present in the structured analysis of the retina (STARE) database is considered for testing the proposed techniques. The proposed segmentation techniques such as region growing (RG), region growing with background correction (RGWBC), and adaptive region growing with background correction (ARGWBC) have been used, and the effectiveness of the algorithms is compared with existing fuzzy-based techniques. Images of eight categories of various annotations and 10 images in each category have been used to test the consistency of the proposed algorithms. Among the proposed techniques, ARGWBC has been identified to be the best method for segmenting the bright lesions based on its sensitivity, specificity, and accuracy. Fifteen different features are extracted from retinal images for the purpose of identification and classification of bright lesions. Feedforward backpropagation neural network (FFBPNN) and pattern recognition neural network (PRNN) are used for the classification of normal/abnormal images. Probabilistic neural network (PNN), radial basis exact fit (RBE), radial basis fewer neurons (RB), and FFBPNN are used for further bright lesion classification and achieve 100% accuracy.

GFF Classifier for Detection of Diabetic Retinopathy in Retinal Images

The emerging situation in today’s world suggests diabetic retinopathy may be a major problem in the medical world. Diabetic retinopathy is dangerous because it cannot be identified in its earlier stages and leads to vision loss. Hence, detection of diabetic retinopathy in early stage is very much important. This paper focuses on Generalized Feed Forward Neural Network (GFFNN) to detect diabetic retinopathy in retinal images. In this paper the authors present the GFFNN as a classifier to classify retinal images as normal and abnormal. 64-point Discrete Cosine Transform (DCT) and 09 statistical parameters such as Entropy, Mean, Standard deviation, Average, Euler number, Contrast, Correlation, Energy and Homogeneity are extracted from fundus retinal images to form a feature vector. The feature vector is used to train and test the GFFNN. The training and cross validation recognition rate by the GFFNN are 100% and 95.45% respectively for detection of normal and abnormal retinal images. General Terms Neural Network, Classification of retinal images

Automated detection of diabetic retinopathy in retinal images.

Diabetic retinopathy (DR) is a disease with an increasing prevalence and the main cause of blindness among working-age population. The risk of severe vision loss can be significantly reduced by timely diagnosis and treatment. Systematic screening for DR has been identified as a cost-effective way to save health services resources. Automatic retinal image analysis is emerging as an important screening tool for early DR detection, which can reduce the workload associated to manual grading as well as save diagnosis costs and time. Many research efforts in the last years have been devoted to developing automatic tools to help in the detection and evaluation of DR lesions. However, there is a large variability in the databases and evaluation criteria used in the literature, which hampers a direct comparison of the different studies. This work is aimed at summarizing the results of the available algorithms for the detection and classification of DR pathology. A detailed literature search was conducted using PubMed. Selected relevant studies in the last 10 years were scrutinized and included in the review. Furthermore, we will try to give an overview of the available commercial software for automatic retinal image analysis.

A comparative study on preprocessing techniques in diabetic retinopathy retinal images: Illumination correction and contrast enhancement

To investigate the effect of preprocessing techniques including contrast enhancement and illumination correction on retinal image quality, a comparative study was carried out. We studied and implemented a few illumination correction and contrast enhancement techniques on color retinal images to find out the best technique for optimum image enhancement. To compare and choose the best illumination correction technique we analyzed the corrected red and green components of color retinal images statistically and visually. The two contrast enhancement techniques were analyzed using a vessel segmentation algorithm by calculating the sensitivity and specificity. The statistical evaluation of the illumination correction techniques were carried out by calculating the coefficients of variation. The dividing method using the median filter to estimate background illumination showed the lowest Coefficients of variations in the red component. The quotient and homomorphic filtering methods after the dividing method presented good results based on their low Coefficients of variations. The contrast limited adaptive histogram equalization increased the sensitivity of the vessel segmentation algorithm up to 5% in the same amount of accuracy. The contrast limited adaptive histogram equalization technique has a higher sensitivity than the polynomial transformation operator as a contrast enhancement technique for vessel segmentation. Three techniques including the dividing method using the median filter to estimate background, quotient based and homomorphic filtering were found as the effective illumination correction techniques based on a statistical evaluation. Applying the local contrast enhancement technique, such as CLAHE, for fundus images presented good potentials in enhancing the vasculature segmentation.

Development of Algorithm for Dual Stage Classification to Estimate Severity Level of Diabetic Retinopathy in Retinal Images using Soft Computing Techniques

Diabetic Retinopathy is a general origin of sight-threatening complication to which the condition occurring in persons with diabetes and which makes progressive damage to the retina. Retina is a back of eye with the light sensitive lining. The severity of this Diabetic Retinopathy in retina has four stages. The identification of the severity level of Diabetic Retinopathy in retina is a critical task. In order to make ease this task, a severity analysis method is proposed in this paper. The proposed method contains the 5 stages - (1) Pre-processing phase (2) Segmentation Phase (3) Feature Extraction Phase (4) Classification Phase I and (5) Classification Phase II. The retinal images are subjected to pre-processing phase for removing the noises from the image and make clear visible image of retina. Then the optic disks and the blood vessels in the retina are segmented using Modified Region Growing method and morphological operations, respectively. Before analyzing the severity in retinal images, it is necessary to classify the images into normal and abnormal images using Neural Network classifier. For this classification of images, the features mean, variance, entropy and area are extracted from the segmented optic disk of retinal images and also the features mean, variance, entropy, area, diameter and number of regions are extracted from the segmented blood vessels of retinal images. From the abnormal images, the severity of Diabetic Retinopathy can be evaluated by using SVM classifier based on area and intensity level of Hard Exudates and Hemorrhages. These techniques are implemented on publicly available database such as STARE and on real datasets using MATLAB 7.12. The performance of our proposed method is analyzed by Sensitivity, Specificity and Accuracy. From the results, it is proved that our work outperforms other works by providing very much better accuracy by classifying the severity level in Diabetic Retinopathy.

Simple hybrid method for fine microaneurysm detection from non-dilated diabetic retinopathy retinal images

Microaneurysms detection is an important task in computer aided diagnosis of diabetic retinopathy. Microaneurysms are the first clinical sign of diabetic retinopathy, a major cause of vision loss in diabetic patients. Early microaneurysm detection can help reduce the incidence of blindness. Automatic detection of microaneurysms is still an open problem due to their tiny sizes, low contrast and also similarity with blood vessels. It is particularly very difficult to detect fine microaneurysms, especially from non-dilated pupils and that is the goal of this paper. Simple yet effective methods are used. They are coarse segmentation using mathematic morphology and fine segmentation using naive Bayes classifier. A total of 18 microaneurysms features are proposed in this paper and they are extracted for naive Bayes classifier. The detected microaneurysms are validated by comparing at pixel level with ophthalmologists’ hand-drawn ground-truth. The sensitivity, specificity, precision and accuracy are 85.68, 99.99, 83.34 and 99.99%, respectively.