Diabetic Retinopathy Images Research Articles

An IoT-Cloud Based Intelligent Computer-aided Diagnosis of Diabetic Retinopathy Stage Classification Using Deep Learning Approach

Diabetic retinopathy (DR) is a disease with an increasing prevalence and the major reason for blindness among working-age population. The possibility of severe vision loss can be extensively reduced by timely diagnosis and treatment. An automated screening for DR has been identified as an effective method for early DR detection, which can decrease the workload associated to manual grading as well as save diagnosis costs and time. Several studies have been carried out to develop automated detection and classification models for DR. This paper presents a new IoT and cloud-based deep learning for healthcare diagnosis of Diabetic Retinopathy (DR). The proposed model incorporates different processes namely data collection, preprocessing, segmentation, feature extraction and classification. At first, the IoT-based data collection process takes place where the patient wears a head mounted camera to capture the retinal fundus image and send to cloud server. Then, the contrast level of the input DR image gets increased in the preprocessing stage using Contrast Limited Adaptive Histogram Equalization (CLAHE) model. Next, the preprocessed image is segmented using Adaptive Spatial Kernel distance measure-based Fuzzy C-Means clustering (ASKFCM) model. Afterwards, deep Convolution Neural Network (CNN) based Inception v4 model is applied as a feature extractor and the resulting feature vectors undergo classification in line with the Gaussian Naive Bayes (GNB) model. The proposed model was tested using a benchmark DR MESSIDOR image dataset and the obtained results showcased superior performance of the proposed model over other such models compared in the study.

Microaneurysms segmentation and diabetic retinopathy detection by learning discriminative representations

Deep learning techniques are recently being used in fundus image analysis and diabetic retinopathy detection. Microaneurysms are important indicators of diabetic retinopathy progression. The authors introduce a two-stage deep learning approach for microaneurysms segmentation using multiple scales of the input with selective sampling and embedding triplet loss. The proposed approach facilitates a region proposal fully convolutional neural network trained on segmented patches and a patch-wise refinement network for improving the results suggested by the first stage hypothesis. To enhance the discriminative power of the second stage refinement network, the authors use triplet embedding loss with a selective sampling routine that dynamically assigns sampling probabilities to the oversampled class patches. This approach introduces a 23.5 % relative improvement over the vanilla fully convolutional neural network on the Indian Diabetic Retinopathy Image Data set segmentation data set. The proposed segmentation is incorporated in a classification model to solve two downstream tasks for diabetic retinopathy detection and referable diabetic retinopathy detection. The classification tasks are trained on the Kaggle diabetic retinopathy challenge data set and evaluated on the Messidor data. The authors show that adding the segmentation enhances the classification performance and achieves comparable performance to the state-of-the-art models.

Performance analysis of automated lesion detection of diabetic retinopathy using morphological operation

Diabetic retinopathy is one of the most common complications of diabetes. Hemorrhages, micro-aneurysms, exudates are one of the earlier signs of diabetic retinopathy. This paper proposes an algorithm of matched filter with morphological operation for the detection of lesions in the fundus retinal image. Contrast limited adaptive histogram equalization method is used for the extraction of vessels. The noise is removed from the images using matched filter. After enhancement, the thresholding is applied for vessel extraction. The threshold of the image is done by the iterative self-organizing data analysis technique algorithm method. After removal of optic disk and the blood vessels from the retinal image, the morphology method is used to easily identify different types of lesions. The diabetic retinopathy images were collected from DIARETDB1; the morphology operation method is analyzed using the metrics of sensitivity, specificity and accuracy. The proposed method's detection accuracy value for the recognition of micro-aneurysms, exudates and hemorrhages was 98.43%, 98.06% and 98.68% compared with the results of the differential evolution algorithm. Detection of lesion such as micro-aneurysms, hemorrhages and exudates was possible. When compared with the differential evolution algorithm, morphological method achieved good accuracy for the detection of diabetic retinopathy.

Deep Learning Grading System for Diabetic Retinopathy using Fundus Images. (Dept. E)

Diabetic Retinopathy (DR) is one of the main causes of blindness that can be overcome, if it is early detected. This work proposes an automated early detection and grading of DR using fundus images. The proposed detection and grading system investigate different deep learning architectures (i.e., ResNet and AlexNet) that are applied to an augment data to extract deep compact features of the fundus images. The extracted features are input to a pixel-wise Neural Network (NN) classifier or a Support Vector Machine (SVM) classifier for automated DR grading. The performance of the proposed system is evaluated using a publically available fundus Indian Diabetic Retinopathy Image Dataset (IDRiD), collected for ISBI-2018 challenge. The IDRiD dataset consists of 516 retinal images of normal and different DR grades, i.e., mild, moderate, severe, and Proliferative Diabetic Retinopathy (PDR). Our system achieves an overall accuracy of 95.73%, sensitivity of 95.73%, and specificity of 98.51% utilizing an AlexNet-based architecture and a pixel-wise NN classifier. Compared to the previous related work, the proposed system shows promising DR grading performance.

Adaptive machine learning classification for diabetic retinopathy

Diabetic retinopathy is the main cause of the blindness worldwide. However, the diabetic retinopathy is hard to be detected in the initial stages, and the procedure of diagnostic can be time-consuming even for experienced-experts. The segment based learning approach has shown the benefits over learning technique for detection of diabetic retinopathy: only the annotation of image level is required get the lesions and detection of diabetic retinopathy. Anyways, the performance of existing methods are limited by the utilization of handcrafted features. This paper proposes the segment based learning approach for detection of diabetic retinopathy, which mutually learns classifiers and features from the data and gets significant development on recognizing the images of diabetic retinopathy and their inside the lesions. Specifically, the pre-trained CNN is adapted to get the segment level DRE (Diabetic retinopathy Estimation) and then Integrating all segment level of (DRM) is utilized to make the classification of diabetic retinopathy images. Lastly, an end-to-end segment based learning approach to deal with the irregular lesions of diabetic retinopathy. For detection of the diabetic retinopathy images obtain area under of ROC curve is 0.963 on the Kaggle dataset and also obtains sensitivity and specificity 96.37% and 96.37% on the higher specificity and sensitivity that outperforms much better than existing model.

An Integrated System for Detection Exudates and Severity Quantification for Diabetic Macular Edema

The prevalence of vision loss because of Diabetic macular edema (DME), which is a complication caused by diabetes mellitus, is increasing. Seven per cent of Indian diabetic population suffer from DME or damage to macula. The study proposes an integrated model to contribute to the prevention of loss of visual acuity. For detection of exudates and visualization of severity of DME image processing, machine learning and data analysis strategies are used. Experimentation on Indian population is done using Indian Diabetic Eye Diseases Dataset (IDEDD), acquired from metropolitan region of Mumbai and publicly available Indian Diabetic Retinopathy Image Dataset (IDRiD, Nanded) and a standard public database DIARETDB1- Standard Diabetic Retinopathy Database. To negate the effect of increase in the dimensionality and overfitting of the dataset parameters, a tree-based forward search algorithm for optimal feature subset identification is proposed. This provides global insight of effect of the statistical and spatial features on model behaviour. Machine learning algorithms of random forest and support vector machine are used for classification. The sensitivity and specificity of 97.1% and 100% is achieved for IDEDD data. Severity grading is done using image processing for segmenting the vessel mesh, optic disk, and macula from the abnormal retinal scans for detecting clinically significant macular edema by visualizing exudates. The distance between optic disc—fovea (OF) and the ratio of distance (OF) to that of disc diameter is formulated for localization of macula. Region-based and distance-based grading methods for quantification of the severity and visualization are implemented. The proposed algorithm enables the building of a predictive model for primordial and secondary prevention of DME with high classification accuracy and visualization of severity grading.

Retinal blood vessels detection for diabetic retinopathy with Ridgelet transform and convolution neural network

Applying machine learning in life sciences, especially diagnostics, has become a key area of focus for researchers. Combining machine learning with traditional algorithms provides a unique opportunity of providing better solutions for the patients. In this paper, we present study results of applying the Ridgelet Transform method on retina images to enhance the blood vessels, then using machine learning algorithms to identify cases of Diabetic Retinopathy (DR). The Ridgelet transform provides better results for line singularity of image function and, thus, helps to reduce artefacts along the edges of the image. The Ridgelet Transform method, when compared with earlier known methods of image enhancement, such as Wavelet Transform and Contourlet Transform, provided satisfactory results. The transformed image using the Ridgelet Transform method with pre-processing quantifies the amount of information in the dataset. It efficiently enhances the generation of features vectors in the convolution neural network (CNN). In this study, a sample of fundus photographs was processed, which was obtained from a publicly available dataset. In pre-processing, first, CLAHE was applied, followed by filtering and application of Ridgelet transform on the patches to improve the quality of the image. Then, this processed image was used for statistical feature detection and classified by deep learning method to detect DR images from the dataset. The successful classification ratio was 98.61%. This result concludes that the transformed image of fundus using the Ridgelet Transform enables better detection by leveraging a transform-based algorithm and the deep learning.

An efficient adaptive histogram based segmentation and extraction model for the classification of severities on diabetic retinopathy

Diabetic retinopathy (DR) is an important retinal disease, which occurs commonly among diabetic patients. This disease severely injures the basic vision of the eye and results in blindness in several cases, which could be eliminated by earlier detection and medication. The existence of many classes in DR makes the diagnosis process difficult. To resolve this process, this paper introduces a new segmentation based classification model to classify the DR images effectively. The proposed model involves three main processes, namely, preprocessing, segmentation, feature selection and classification. The proposed method undergoes preprocessing and contrast-limited adaptive histogram equalization (CLAHE) model is applied for segmentation. AlexNet architecture is applied as a feature extractor to extract the useful set of feature vectors. Finally, softmax layer is utilized to classify the images into different stages of DR. The validation takes place using the publicly available Kaggle dataset. The experimental outcome indicates that the presented model achieves maximum classification rate with an accuracy of 95.86%, sensitivity of 92.00%, and specificity of 97.86% respectively.

Leveraging Multimodal Deep Learning Architecture with Retina Lesion Information to Detect Diabetic Retinopathy.

PurposeTo improve disease severity classification from fundus images using a hybrid architecture with symptom awareness for diabetic retinopathy (DR).MethodsWe used 26,699 fundus images of 17,834 diabetic patients from three Taiwanese hospitals collected in 2007 to 2018 for DR severity classification. Thirty-seven ophthalmologists verified the images using lesion annotation and severity classification as the ground truth. Two deep learning fusion architectures were proposed: late fusion, which combines lesion and severity classification models in parallel using a postprocessing procedure, and two-stage early fusion, which combines lesion detection and classification models sequentially and mimics the decision-making process of ophthalmologists. Messidor-2 was used with 1748 images to evaluate and benchmark the performance of the architecture. The primary evaluation metrics were classification accuracy, weighted κ statistic, and area under the receiver operating characteristic curve (AUC).ResultsFor hospital data, a hybrid architecture achieved a good detection rate, with accuracy and weighted κ of 84.29% and 84.01%, respectively, for five-class DR grading. It also classified the images of early stage DR more accurately than conventional algorithms. The Messidor-2 model achieved an AUC of 97.09% in referral DR detection compared to AUC of 85% to 99% for state-of-the-art algorithms that learned from a larger database.ConclusionsOur hybrid architectures strengthened and extracted characteristics from DR images, while improving the performance of DR grading, thereby increasing the robustness and confidence of the architectures for general use.Translational RelevanceThe proposed fusion architectures can enable faster and more accurate diagnosis of various DR pathologies than that obtained in current manual clinical practice.

Hybrid machine learning architecture for automated detection and grading of retinal images for diabetic retinopathy.

Purpose: Diabetic retinopathy is the leading cause of blindness, affecting over 93million people. An automated clinical retinal screening process would be highly beneficial and provide a valuable second opinion for doctors worldwide. A computer-aided system to detect and grade the retinal images would enhance the workflow of endocrinologists. Approach: For this research, we make use of a publicly available dataset comprised of 3662 images. We present a hybrid machine learning architecture to detect and grade the level of diabetic retinopathy (DR) severity. We also present and compare simple transfer learning-based approaches using established networks such as AlexNet, VGG16, ResNet, Inception-v3, NASNet, DenseNet, and GoogLeNet for DR detection. For the grading stage (mild, moderate, proliferative, or severe), we present an approach of combining various convolutional neural networks with principal component analysis for dimensionality reduction and a support vector machine classifier. We study the performance of these networks under different preprocessing conditions. Results: We compare these results with various existing state-of-the-art approaches, which include single-stage architectures. We demonstrate that this architecture is more robust to limited training data and class imbalance. We achieve an accuracy of 98.4% for DR detection and an accuracy of 96.3% for distinguishing severity of DR, thereby setting a benchmark for future research efforts using a limited set of training images. Conclusions: Results obtained using the proposed approach serve as a benchmark for future research efforts. We demonstrate as a proof-of-concept that an automated detection and grading system could be developed with a limited set of images and labels. This type of independent architecture for detection and grading could be used in areas with a scarcity of trained clinicians based on the necessity.

Modified U-Net architecture for semantic segmentation of diabetic retinopathy images

Segmentation of lesions from fundus images is an essential prerequisite for accurate severity assessment of diabetic retinopathy. Due to variation in morphologies, number and size of lesions, the manual grading process becomes extremely challenging and time-consuming. This necessitates the need of an automatic segmentation system that can precisely define the region of interest boundaries and assist ophthalmologists in speedy diagnosis along with diabetic retinopathy severity grading. The paper presents a modified U-Net architecture based on residual network and employs periodic shuffling with sub-pixel convolution initialized to convolution nearest neighbour resize. The proposed architecture has been trained and validated for microaneurysm and hard exudate segmentation on two publicly available datasets namely IDRiD and e-ophtha. For IDRiD dataset, the network obtains 99.88% accuracy, 99.85% sensitivity, 99.95% specificity and dice score of 0.9998 for both microaneurysm and exudate segmentation. Further, when trained on e-ophtha and validated on IDRiD dataset, the network shows 99.98% accuracy, 99.88% sensitivity, 99.89% specificity and dice score of 0.9998 for microaneurysm segmentation. For exudates segmentation, the model obtained 99.98% accuracy, 99.88% sensitivity, 99.89% specificity and dice score of 0.9999, when trained on e-ophtha and validated on IDRiD dataset. In comparison to existing literature, the proposed model provides state-of-the-art results for retinal lesion segmentation.

Combining MF-DFA and LSSVM for retina images classification

Diabetic retinopathy is the main cause of blindness in adults. Early diagnosis of diabetic retinopathy is essential for avoiding deterioration of illness and vision loss. The use of computer technology to identify diabetic retinopathy images provides significant means to reduce the risk of deterioration. In this paper, we propose a new approach for retina images detection and classification by using a hybrid system which is constructed by two-dimensional multifractal detrended fluctuation analysis (2D MF-DFA) and least square support vector machines (LSSVM). In the proposed method, we applied 2D MF-DFA to compute the local generalized Hurst exponents which are the multifractal features of the diabetic retinopathy image, and these values are recorded as LHq. Then, the Hurst exponents are taken as the training input vector for the training in LSSVM. Finally, we classified a specific retina image as healthy or lesion image. We present experimental verification to investigate the efficiency and robustness of the proposed system. The results show that the proposed system yields a classification accuracy with 99.01% ± 0.0074, sensitivity with 99.03% ± 0.0051, and specificity with 97.73% ± 0.0075. When the performance was compared with state-of-the-arts, the solution indicated that the MF-DFA-LSSVM system outperforms most of others in terms of all the classification sensitivity, accuracy, and specificity. The proposed method will be useful for clinical medicine.

Automatic Detection of Diabetic Retinopathy with Statistical Method and Bayesian Classifier

Currently, the underlying medical conditions in China lag behind those in urban areas. There are some problems such as lack of resources of primary ophthalmologists and insufficient fundus image of diabetic retinopathy (DR) with markers. To solve the above questions, an automated detection model of diabetic retinopathy based on the statistical method and Naïve Bayesian (NB) classifier is proposed in this paper. Firstly, three sets of texture features are extracted, which are gray-level co-occurrence matrix texture features, different statistical texture features, and gray-level run-length matrix texture features. Secondly, the extracted texture features are used as input of the Naïve Bayesian classifier to classify the fundus images of diabetic retinopathy into three categories. The proposed automatic detection model for diabetic retinopathy is validated by a data set consisting of 568 images from China diabetic retinopathy screening project. The positive predictive accuracy of the system is 93.44%, the sensitivity and specificity are 91.94% and 88.24%, respectively.

Fuzzy Image Processing Based Architecture for Contrast Enhancement in Diabetic Retinopathy Images

Diabetic retinopathy” is damage to retina denotes one of the problems of diabetes which is a significant reason for visual infirmity and blindness. A comprehensive and routine eye check is important to early detection and rapid treatment. This study proposes a hardware system that can enhance the contrast in the diabetic retinopathy eye fundus images as a first step in different eye disease diagnoses. The fuzzy histogram equalization technique is proposed to increases the local contrast of Diabetic Retinopathy Images. First, a histogram construction hardware architecture for different image processing purposes has been built then modified with fuzzy techniques to create fuzzy histogram equalization architecture, which is used to enhance the original images. Both architectures are designed using a finite-state machine (FSM) technique and programmed with VHDL programming language. The first one is implemented using two (Spartan 3E-XC3S500 and Xilinx Artix-7 XC7A100T) kits, while the second architecture is implemented using (Spartan 3E-XC3S500) kit. The system consists also of a modified video graphics array (VGA) port to display the input and resulted images with a proper resolution. All the hardware outputs are compared to that results produce from MatLab for verification and the resulted images are tested by PSNR, MSE, ENTROPY ,and AMBE

Severity Level Detection in Retinal Fundus Images for Diabetic Retinopathy

Diabetic Retinopathy is the disease caused for diabetic people which doesn’t have symptoms in the first phase. As it progresses, it becomes symptomatic. This disease, sometimes, might lead to complete blindness. Red lesions contain microaneurysms, haemorrhages and exudates. This work focuses on detection of red lesions in fundus image. Ophthalmologists use pupil dilation of chemical solutions in order to detect the abnormality which takes time and also causes irritation to patients. Image processing techniques are used to avoid these limitations. Morphological operations are used to identify the pixels belonging to the red lesions. Gabor filter is used for separating the blood vessels. Some spots are formed near macular region because blood vessels become leaky which leads to exudates. The severity level of the disease is determined by finding the distance between lesions and macular region. The disease is considered as severe if the distance between them is closer and confirms as less if the distance is far.

Assessment of Training Outcomes of Nurse Readers for Diabetic Retinopathy Telescreening: Validation Study.

BackgroundWith the high prevalence of diabetic retinopathy and its significant visual consequences if untreated, timely identification and management of diabetic retinopathy is essential. Teleophthalmology programs have assisted in screening a large number of individuals at risk for vision loss from diabetic retinopathy. Training nonophthalmological readers to assess remote fundus images for diabetic retinopathy may further improve the efficiency of such programs.ObjectiveThis study aimed to evaluate the performance, safety implications, and progress of 2 ophthalmology nurses trained to read and assess diabetic retinopathy fundus images within a hospital diabetic retinopathy telescreening program.MethodsIn this retrospective interobserver study, 2 ophthalmology nurses followed a specific training program within a hospital diabetic retinopathy telescreening program and were trained to assess diabetic retinopathy images at 2 levels of intervention: detection of diabetic retinopathy (level 1) and identification of referable disease (level 2). The reliability of the assessment by level 1−trained readers in 266 patients and of the identification of patients at risk of vision loss from diabetic retinopathy by level 2−trained readers in 559 more patients were measured. The learning curve, sensitivity, and specificity of the readings were evaluated using a group consensus gold standard.ResultsAn almost perfect agreement was measured in identifying the presence of diabetic retinopathy in both level 1 readers (κ=0.86 and 0.80) and in identifying referable diabetic retinopathy by level 2 readers (κ=0.80 and 0.83). At least substantial agreement was measured in the level 2 readers for macular edema (κ=0.79 and 0.88) for all eyes. Good screening threshold sensitivities and specificities were obtained for all level readers, with sensitivities of 90.6% and 96.9% and specificities of 95.1% and 85.1% for level 1 readers (readers A and B) and with sensitivities of 86.8% and 91.2% and specificities of 91.7% and 97.0% for level 2 readers (readers A and B). This performance was achieved immediately after training and remained stable throughout the study.ConclusionsNotwithstanding the small number of trained readers, this study validates the screening performance of level 1 and level 2 diabetic retinopathy readers within this training program, emphasizing practical experience, and allows the establishment of an ongoing assessment clinic. This highlights the importance of supervised, hands-on experience and may help set parameters to further calibrate the training of diabetic retinopathy readers for safe screening programs.

Existential Methods on Diabetes Detection using Machine Learning

Nowadays, a lot of research is going on in healthcare. One of the significant diseases increased all over the world is Diabetes Mellitus (DM). In this paper, the literature review is done on diabetes prediction using Machine Learning and Deep Learning techniques. Various ML algorithms are used using PIDD (Pima Indian diabetes dataset), and improved k- means using logistic regression among all algorithms achieved the highest accuracy. DL algorithms like CNN and LMST used in diabetic retinopathy images.

Deep neural network with moth search optimization algorithm based detection and classification of diabetic retinopathy images

In recent days, progressive rate of diabetic retinopathy (DR) becomes high and it is needed to develop an automated model for effective diagnosis of DR. This paper presents a new deep neural network with moth search optimization (DNN-MSO) algorithm based detection and classification model for DR images. The presented DNN-MSO algorithm involves different processes namely preprocessing, segmentation, feature extraction and classification. Initially, the contrast level of the DR images is improved using contrast limited adaptive histogram equalization model. After that, the preprocessed images are segmented using histogram approach. Then, Inception-ResNet V2 model is applied for feature extraction. Finally, extracted feature vectors are given to the DNN-MSO based classifier model to classify the different stages of DR. An extensive series of experiments were carried out and the results are validated on Messidor DR dataset. The obtained experimental outcome stated the superior characteristics of the DNN-MSO model by attaining a maximum accuracy, sensitivity and specificity of 99.12%, 97.91% and 99.47% respectively.

Transfer Learning with Convolutional Neural Networks for Diabetic Retinopathy Image Classification. A Review

Diabetic retinopathy (DR) is a dangerous eye condition that affects diabetic patients. Without early detection, it can affect the retina and may eventually cause permanent blindness. The early diagnosis of DR is crucial for its treatment. However, the diagnosis of DR is a very difficult process that requires an experienced ophthalmologist. A breakthrough in the field of artificial intelligence called deep learning can help in giving the ophthalmologist a second opinion regarding the classification of the DR by using an autonomous classifier. To accurately train a deep learning model to classify DR, an enormous number of images is required, and this is an important limitation in the DR domain. Transfer learning is a technique that can help in overcoming the scarcity of images. The main idea that is exploited by transfer learning is that a deep learning architecture, previously trained on non-medical images, can be fine-tuned to suit the DR dataset. This paper reviews research papers that focus on DR classification by using transfer learning to present the best existing methods to address this problem. This review can help future researchers to find out existing transfer learning methods to address the DR classification task and to show their differences in terms of performance.

Automated detection and classification of fundus diabetic retinopathy images using synergic deep learning model

In recent days, the incidence of Diabetic Retinopathy (DR)has become high, affecting the eyes because of drastic increase in the glucose level in blood. Globally, almost half of the people under the age of 70 gets severely affected by diabetes. In the absence of earlier recognition and proper medication, the DR patients tend to lose their vision. When the warning signs are tracked down, the severity level of the disease has to be validated so to take decisions regarding appropriate treatment further. The current research paper focuses on the concept of classification of DR fundus images on the basis of severity level using a deep learning model. This paper proposes a deep learning-based automated detection and classification model for fundus DR images. The proposed method involves various processes namely preprocessing, segmentation and classification. The methods begins with preprocessing stage in which unnecessary noise that exists in the edges is removed. Next, histogram-based segmentation takes place to extract the useful regions from the image. Then, Synergic Deep Learning (SDL) model was applied to classify the DR fundus images to various severity levels. The justification for the presented SDL model was carried out on Messidor DR dataset. The experimentation results indicated that the presented SDL model offers better classification over the existing models.