Diabetic Retinopathy Grading Research Articles

An efficient automatic diabetic retinopathy grading using a two-way cascaded convolution neural network

High blood sugar levels lead to an eye disease called diabetic retinopathy. This disease causes vision loss from adults to children. Early detection and proper treatment can reduce vision loss. This research suggests computer-aided diagnosis-based early detection of diabetic retinopathy. The main goal of this study is to automatically detect non-proliferative diabetic retinopathy in any retinal imaging. The proposed model consists of two main stages namely, pre-processing and classification. The first stage is to collect the images from the dataset, after which they are pre-processed using the techniques of image enhancement, noise removal, blurring effects, etc. For classification, a two-way cascaded convolution neural network is developed. To improve the effectiveness of the classifier, the handcrafted features are extracted from the image and fused with the proposed classifier. The suggested system divides images of diabetic retinopathy into four categories such as none, mild, moderate, and severe diabetic retinopathy. The effectiveness of the suggested technique is evaluated using a variety of criteria. The diagnostic efficacy of the proposed model is demonstrated through a comparative analysis with state-of-the-art methodologies, showcasing its performance against established approaches.

Lesion classification and diabetic retinopathy grading by integrating softmax and pooling operators into vision transformer.

Diabetic retinopathy grading plays a vital role in the diagnosis and treatment of patients. In practice, this task mainly relies on manual inspection using human visual system. However, the human visual system-based screening process is labor-intensive, time-consuming, and error-prone. Therefore, plenty of automated screening technique have been developed to address this task. Among these techniques, the deep learning models have demonstrated promising outcomes in various types of machine vision tasks. However, most of the medical image analysis-oriented deep learning approaches are built upon the convolutional operations, which might neglect the global dependencies between long-range pixels in the medical images. Therefore, the vision transformer models, which can unveil the associations between global pixels, have been gradually employed in medical image analysis. However, the quadratic computation complexity of attention mechanism has hindered the deployment of vision transformer in clinical practices. Bearing the analysis above in mind, this study introduces an integrated self-attention mechanism with both softmax and linear modules to guarantee efficiency and expressiveness, simultaneously. To be specific, a portion of query and key tokens, which are much less than the original query and key tokens, are adopted in the attention module by adding a set of proxy tokens. Note that the proxy tokens can fully utilize both the advantages of softmax and linear attention. To evaluate the performance of the presented approach, the comparison experiments between state-of-the-art algorithms and the proposed approach are conducted. Experimental results demonstrate that the proposed approach achieves superior outcome over the state-of-the-art algorithms on the publicly available datasets. Accordingly, the proposed approach can be taken as a potentially valuable instrument in clinical practices.

A Novel Approach for Early Detection and Grading of Diabetic Retinopathy by using Ensemble Model

A Novel Approach for Early Detection and Grading of Diabetic Retinopathy by using Ensemble Model

Diabetic retinopathy grading using curvelet CNN with optimized SSO activations and wavelet-based image enhancement

Diabetic retinopathy grading using curvelet CNN with optimized SSO activations and wavelet-based image enhancement

Robust Diabetic Retinopathy Detection and Grading using Neutrosophic Topological Vector Space on Fundus Imaging

Diabetic retinopathy (DR) is an eye disorder triggered by diabetes that might result in loss of sight. Earlier diagnosis of DR is critical since it might cause loss of sight. Manual diagnoses of DR severity by ophthalmologists are time-consuming and challenging. As a result, there has been considerable attention on designing an automatic technique for DR detection using fundus photographs. In medical science, prognosis and diagnosis are the most challenging tasks due to the presence of fuzziness in medical images and the restricted subjectivity of the experts. Neutrosophic Set (NS) in medical image analysis provides an understanding of the NS concepts, together with knowledge of how to collect, handle, interpret, and analyze clinical images using NS techniques. The neutrosophic set (NS), which is a generality of fuzzy set, provides the overcoming prospect of the restriction of fuzzy-based models for the analysis of medical images. This manuscript develops a Robust Diabetic Retinopathy Detection and Grading using Neutrosophic Topological Vector Space (DRDG-NSTVS) technique on fundus images. The DRDG-NSTVS technique begins with Median Filter (MF) noise removal to optimize the clarity of fundus photographs by successfully eliminating noises. Later, the InceptionV3 is used to perform feature extraction for identifying complicated features and patterns related to DR. The parameter tuning is performed by the moth flame optimization (MFO) technique to ensure superior performance of the model. The final diagnoses and classification of DR are accomplished utilizing the NSTVS classifiers that easily perform the uncertainties inherent in medicinal statistics. The simulation was conducted on a benchmark dataset to examine the proposed model performance. This combined method gives a greatly reliable and accurate solution for the earlier diagnosis and detection of DR

C2x-FNet: Cascaded Dense Block With Twofold Cross-Feature Enhancement Module for Diabetic Retinopathy Grading

C2x-FNet: Cascaded Dense Block With Twofold Cross-Feature Enhancement Module for Diabetic Retinopathy Grading

Classification of diabetic retinopathy grades using CNN feature extraction to segment the lesion

Diabetes's microvascular aftereffect, diabetic retinopathy (DR), is the primary cause of eyesight loss in the globe. In order to prevent vision impairment and to intervene promptly, early detection and precise classification of DR severity are essential. Using standard methods for diagnosing DR requires ophthalmologists to grade cases by hand, a process that can be laborious, subjective, and subject to observer error. In supervised learning task of classification, data instances are classified into predefined classes based on features. The relation between the traits and the classes can be found from the labelled data. After the training is completed, the classes of the unseen data. The frequent reason found for the loss of vision in diabetic retinopathy (DR) is found to be diabetes. Visual damage can be prevented by identifying the degree of DR at right time. For the grading of the DR, deep learning techniques are found to be very effective with maximum possible accuracy. The proposed model is useful in accurately classifying the DR images using the feature extraction with lesion segmentation, by implementing the patterns in the DR images. ReLU activation function is used in the proposed model. CNN feature extraction is used for the important feature extraction by applying the Convolution layers, and edges, textures, and forms are identified. As the model proceeds layer by layer, complicated patterns in the photos can be learned by the model, and can be analysed better. The features of the photos were extracted and found useful in segmentation and classification. ReLU is helpful in improving the convergence and also found useful in learning the patterns. Among the other activation functions, ReLU has higher computational efficiency and therefore is used in the model, which suits well for the DR application. A strong framework is proposed for the classification of the DR grade, for the lesion segmentation and CNN feature extraction. DR categorization using the proposed model is evaluated by data visualization of the important calculated metrics and found to be very effective.

Deep learning-based binocular system for automated diabetic retinopathy grading with prior clinical knowledge integration

Deep learning-based binocular system for automated diabetic retinopathy grading with prior clinical knowledge integration

The protective role of gamma zone peripapillary atrophy in diabetic retinopathy: insights from deep learning and SS-OCT angiography.

To explore the relationship between peripapillary atrophy (PPA) and diabetic retinopathy (DR), and to uncover potential mechanisms using swept-source optical coherence tomography (SS-OCT) angiography. This cross-sectional study included 845 patients with type 2 diabetes (T2DM), who underwent detailed systemic and ophthalmic evaluations. A state-of-the-art deep learning method was employed to precisely identify the parapapillary beta and gamma zones. Based on PPA characteristics, eyes were categorized into four groups: without beta or gamma zone (Group A), isolated beta zone (Group B), isolated gamma zone (Group C), and with both beta and gamma zone (Group D). Digital fundus photography was utilized to diagnose and stage DR severity, while SS-OCT angiography quantified retinal and choroidal vasculature. Participants had a mean age of 66 ± 8.8years, with 437 (51.7%) male. Beta and gamma PPA zones were observed in 574 (67.9%) and 256 (30.3%) eyes, respectively. Beta zone PPA was associated with older age, whereas gamma zone PPA was correlated with longer axial length (AL), lower vessel density, and reduced choroidal thickness. Adjusted analyses revealed that eyes with isolated (Group C) or concurrent (Group D) gamma zone PPA conferred significantly lower DR grade, independent of known risk factors including systemic diabetes risk factors and AL. This study finds that gamma zone PPA is linked to a reduced risk of developing DR. These results imply that the gamma zone may reflect progressive myopia-associated thinning and microvascular depletion in posterior ocular tissues, potentially contributing to structural resilience against DR. This novel insight offers a promising avenue for understanding the interplay between PPA and DR.

Automatic grading diabetic retinopathy in color fundus image: Cascaded hybrid attention network

Deep learning techniques have been introduced to automatically assess Diabetic Retinopathy (DR), a prevalent vision-impairing condition, aiding ophthalmologists in formulating personalized treatment strategies for patients. However, most Artificial Intelligence (AI) for grading DR are constrained by their limited capacity to discern lesion details or necessitate manual lesion labeling, leading to suboptimal assessment outcomes or increased workload. To enhance both efficiency and precision in grading, this paper proposes a Cascaded Hybrid Attention Network (CHAN) for DR grading. Residual Hybrid Attention Modules (RHAM) is designed to extract features, incorporating several cascaded Hybrid Attention Module (HAM) and a convolution layer with a residual connection. The approach integrates channel attention with multi-head self-attention, leveraging their combined strengths: global statistical analysis and robust local adaptation. The grading score is derived by integrating DR features across various layers, from shallow to deep. The CHAN model, tested on the MESSIDOR dataset, demonstrates superior accuracy in DR grading, consistently surpassing current leading methods across evaluation metrics.

Diabetic retinopathy grading based on multi-scale residual network and cross-attention module

Diabetic retinopathy (DR) is a severe effect of diabetes mellitus that mainly impacts the retinal tissue and carries a high risk of blindness. Ophthalmologists face challenges in assessing the severity of DR due to its complexity and time constraints. Consequently, there is an urgent need for the development of automated methods that employ retinal fundus images to detect DR. This study introduces a novel deep learning architecture that utilizes a multi-scale residual attention block (MSRAB) and a cross-attention block (CrAB) for DR grading. The proposed MSRAB employs a convolutional neural network (CNN) with diverse dilation rates to expand its field of view. MSRAB adaptively concentrate on pertinent features and incorporates a residual attention network to improve grading performance. Integrating the residual attention network enables MSRAB to prioritize critical characteristics in retinal fundus images and enhance performance. Similarly, the CrAB integrates channel and spatial attention mechanisms to capture inter-channel interactions and spatial dependencies within the input features. This comprehensive methodology enables the model to concentrate more efficiently on critical regions to discriminate irrelevant features and to capture interrelations across different channels and spatial regions. The proposed model employs a pre-trained backbone network to extract local and global features to capture complex features for precisely identifying DR. This process enhances model efficiency, which is helpful in methods with limited data and processing limitations. The suggested methodology surpasses the existing methodologies in accuracy, recall, precision, and Area Under the Curve.

Diagnostic accuracy of a smartphone-based device (VistaView) for detection of diabetic retinopathy: A prospective study.

Diabetic retinopathy (DR) is a leading cause of blindness globally. The gold standard for DR screening is stereoscopic colour fundus photography with tabletop cameras. VistaView is a novel smartphone-based retinal camera which offers mydriatic retinal imaging. This study compares the diagnostic accuracy of the smartphone-based VistaView camera compared to a traditional desk mounted fundus camera (Triton Topcon). We also compare the agreement between graders for DR screening between VistaView images and Topcon images. This prospective study took place between December 2021 and June 2022 in Pakistan. Consecutive diabetic patients were imaged following mydriasis using both VistaView and Topcon cameras at the same sitting. All images were graded independently by two graders based on the International Classification of Diabetic Retinopathy (ICDR) criteria. Individual grades were assigned for severity of DR and maculopathy in each image. Diagnostic accuracy was calculated using the Topcon camera as the gold standard. Agreement between graders for each device was calculated as intraclass correlation coefficient (ICC) (95% CI) and Cohen's weighted kappa (k). A total of 1428 images were available from 371 patients with both cameras. After excluding ungradable images, a total of 1231 images were graded. The sensitivity of VistaView for any DR was 69.9% (95% CI 62.2-76.6%) while the specificity was 92.9% (95% CI 89.9-95.1%), and PPV and NPV were 80.5% (95% CI 73-86.4%) and 88.1% (95% CI 84.5-90.9) respectively. The sensitivity of VistaView for RDR was 69.7% (95% CI 61.7-76.8%) while the specificity was 94.2% (95% CI 91.3-96.1%), and PPV and NPV were 81.5% (95% CI 73.6-87.6%) and 89.4% (95% CI 86-92%) respectively. The sensitivity for detecting maculopathy in VistaView was 71.2% (95% CI 62.8-78.4%), while the specificity was 86.4% (82.6-89.4%). The PPV and NPV of detecting maculopathy were 63% (95% CI 54.9-70.5%) and 90.1% (95% CI 86.8-92.9%) respectively. For VistaView, the ICC of DR grades was 78% (95% CI, 75-82%) between the two graders and that of maculopathy grades was 66% (95% CI, 59-71%). The Cohen's kappa for retinopathy grades of VistaView images was 0.61 (95% CI, 0.55-0.67, p<0.001), while that for maculopathy grades was 0.49 (95% CI 0.42-0.57, p<0.001). For images from the Topcon desktop camera, the ICC of DR grades was 85% (95% CI, 83-87%), while that of maculopathy grades was 79% (95% CI, 75-82%). The Cohen's kappa for retinopathy grades of Topcon images was 0.68 (95% CI, 0.63-0.74, p<0.001), while that for maculopathy grades was 0.65 (95% CI, 0.58-0.72, p<0.001). The VistaView offers moderate diagnostic accuracy for DR screening and may be used as a screening tool in LMIC.

Multi-lesion segmentation guided deep attention network for automated detection of diabetic retinopathy

Accurate multi-lesion segmentation together with automated grading on fundus images played a vital role in diagnosing and treating diabetic retinopathy (DR). Nevertheless, the intrinsic patterns of fundus lesions aggravated challenges in DR detection process. Therefore, we proposed a novel multi-lesion segmentation guided deep attention network (MSGDA-Net) for accurate and automated DR detection, consisting of a DR lesion segmentation pathway as an auxiliary task to produce a lesion regional prior knowledge and a DR grading pathway to extract local fine-grained features and long-range dependency. In DR lesion segmentation pathway, we designed a Multi-Scale Attention Block (MSAB) and a Lesion-Aware Relation Block (LARB) to allow interactions among multi-lesion features for alleviating ambiguity in lesion segmentation, generating lesion regional prior knowledge. As for DR grading pathway, we presented a Spatial-Fusion Block (SFB) to enhance the lesion-related local fine-grained feature representations and eliminate irrelevant noise information under the guidance of the resulting lesion regional priors, while constructed an Enhanced Self-Attention Block (ESAB) to optimally fuse fine-grained features from SFB with long-range global-context information for grading DR. The experimental results showed that our MSGDA-Net not only achieved state-of-the-art performance in the tasks of multi-lesion segmentation and DR grading, reaching up to 49.21 % Dice, 38.05 % IoU and 51.15 % AUPR for DR lesion segmentation on the DDR dataset, as well as accuracy values of 75.00 % and 87.18 % for DR grading on local newly-built VisionDR and publicly available APTOS datasets, but also manifested good generalization and robustness on cross-data evaluation. It could serve as a promising tool for computer aided DR screening and diagnosis.

Coinciding Diabetic Retinopathy and Diabetic Macular Edema Grading With Rat Swarm Optimization Algorithm for Enhanced Capsule Generation Adversarial Network.

In the worldwide working-age population, visual disability and blindness are common conditions caused by diabetic retinopathy (DR) and diabetic macular edema (DME). Nowadays, due to diabetes, many people are affected by eye-related issues. Among these, DR and DME are the two foremost eye diseases, the severity of which may lead to some eye-related problems and blindness. Early detection of DR and DME is essential to preventing vision loss. Therefore, an enhanced capsule generation adversarial network (ECGAN) optimized with the rat swarm optimization (RSO) approach is proposed in this article to coincide with DR and DME grading (DR-DME-ECGAN-RSO-ISBI 2018 IDRiD). The input images are obtained from the ISBI 2018 unbalanced DR grading data set. Then, the input fundus images are preprocessed using the Savitzky-Golay (SG) filter filtering technique, which reduces noise from the input image. The preprocessed image is fed to the discrete shearlet transform (DST) for feature extraction. The extracting features of DR-DME are given to the ECGAN-RSO algorithm to categorize the grading of DR and DME disorders. The proposed approach is implemented in Python and achieves better accuracy by 7.94%, 36.66%, and 4.88% compared to the existing models, such as the combined DR with DME grading for the cross-disease attention network (DR-DME-CANet-ISBI 2018 IDRiD), category attention block for unbalanced grading of DR (DR-DME-HDLCNN-MGMO-ISBI 2018 IDRiD), combined DR-DME classification with a deep learning-convolutional neural network-based modified gray-wolf optimizer with variable weights (DR-DME-ANN-ISBI 2018 IDRiD).

A Novel Preprocessing Unit for Effective Deep Learning based Classification and Grading of Diabetic Retinopathy

A Novel Preprocessing Unit for Effective Deep Learning based Classification and Grading of Diabetic Retinopathy

Grading of diabetic retinopathy using a pre-segmenting deep learning classification model: Validation of an automated algorithm.

To validate the performance of autonomous diabetic retinopathy (DR) grading by comparing a human grader and a self-developed deep-learning (DL) algorithm with gold-standard evaluation. We included 500, 6-field retinal images graded by an expert ophthalmologist (gold standard) according to the International Clinical Diabetic Retinopathy Disease Severity Scale as represented with DR levels 0-4 (97, 100, 100, 103, 100, respectively). Weighted kappa was calculated to measure the DR classification agreement for (1) a certified human grader without, and (2) with assistance from a DL algorithm and (3) the DL operating autonomously. Using any DR (level 0 vs. 1-4) as a cutoff, we calculated sensitivity, specificity, as well as positive and negative predictive values (PPV and NPV). Finally, we assessed lesion discrepancies between Model 3 and the gold standard. As compared to the gold standard, weighted kappa for Models 1-3 was 0.88, 0.89 and 0.72, sensitivities were 95%, 94% and 78% and specificities were 82%, 84% and 81%. Extrapolating to a real-world DR prevalence of 23.8%, the PPV were 63%, 64% and 57% and the NPV were 98%, 98% and 92%. Discrepancies between the gold standard and Model 3 were mainly incorrect detection of artefacts (n = 49), missed microaneurysms (n = 26) and inconsistencies between the segmentation and classification (n = 51). While the autonomous DL algorithm for DR classification only performed on par with a human grader for some measures in a high-risk population, extrapolations to a real-world population demonstrated an excellent 92% NPV, which could make it clinically feasible to use autonomously to identify non-DR patients.

HFF-Net: A hybrid convolutional neural network for diabetic retinopathy screening and grading

Diabetic Retinopathy (DR) is a leading cause of vision loss among diabetic patients, necessitating effective screening and grading for timely intervention. Regular screening significantly increases the workload of ophthalmologists, and accurate grading into stages—mild, moderate, severe, and proliferative—is crucial for monitoring disease progression. While Computer-Aided Diagnosis (CAD) systems can alleviate this burden, existing Convolutional Neural Network (CNN)-based frameworks use fixed-size kernels in a linear feed-forward manner. This approach can lead to information loss in the initial stages due to limited feature utilization across adjacent layers. To address this limitation, we propose a Hierarchical Features Fusion Convolutional Neural Network (HFF-Net) within a Diabetic Retinopathy Screening and Grading (DRSG) framework. The framework includes preprocessing to extract regions of interest from fundus images (FIs), enhancement using Contrast Limited Adaptive Histogram Equalization (CLAHE), and data augmentation for class balancing and overfitting mitigation. HFF-Net extracts multiscale features that fused at multiple levels within the network, utilizing the swish activation function for improved learning stability. We evaluated HFF-Net against several state-of-the-art CNN classifiers within the DRSG framework. Experimental results demonstrate that HFF-Net achieves a grading accuracy of 73.77 ​%, surpassing the second-best model by 3.51 percentage points (a relative improvement of approximately 5 ​%), and attains a screening accuracy of 98.70 ​% using only 1.18 million parameters. These findings highlight HFF-Net's potential as an efficient and effective tool in CAD systems for DR screening and grading.

SDRG-Net: Secure DR grading network for Real-Time decision support in IoMT environments

Diabetic Retinopathy (DR) affects approximately 463 million individuals globally, with predictions indicating a rise to 700 million by 2045. Despite advancements, traditional DR detection methods face significant challenges, including limited diagnostic accuracy and the labour-intensive nature of manual image analysis. This work proposes the Secure DR Grading Network (SDRG-Net), which integrates Multi-Level Color Transformation (MLCT) for image encryption to ensure data security and privacy in Internet of Medical Things (IoMT) applications. The SDRG-Net employs the Minority Oversampling by Synthetic Data (MOSD) to address class imbalance, enhancing data quality and model robustness. The DR Class Specific-Graph Correlation Network (DRCS-GCN) is utilized for disease-specific feature extraction, effectively identifying and leveraging complex relationships within the data. The Gradient Decision Weights Optimization based Extreme Gradient Boosting (GDWO-EGB) classifier is then applied to these refined features for accurate DR grading. The performance of SDRG-Net is evaluated using the EyePACS and Messidor datasets, demonstrating significant improvements in classification accuracy and reliability compared to existing methods.

A wavelet CNN with appropriate feed-allocation and PSO optimized activations for diabetic retinopathy grading

This work modifies the architecture of conventional CNN with the integration of Multi-resolution Analysis (MRA) in a CNN framework for Diabetic Retinopathy (DR) diagnosis and grading. Here, the HF sub-bands are subjected to optimized activations and are directly fed to the fully connected layers, as it encompasses edge features. Unlike FD-Relu, the proposed function preserves significant negative coefficients, compared to the S-Relu, the proposed third-order S-Relu is optimized such that it sustains the activations in the range suitable for the wavelet coefficients. The coefficients of higher-order terms of the proposed 3rd-order S-Relu are optimized with PSO, fitting the maximum energy of the wavelet sub-bands to ensure High Frequency (HF) edge preservation. The authors re-architecture 3 different CNNs published in the Retinal Image analysis field, with spatial and wavelet inputs with optimized activations. The highest accuracy of 96% is attained with the AlexNet re-architecture, with 35,126 fundus images secured from the Kaggle dataset. As we can infer the proposed re-architecture wavelet CNN outperformed the multiscale shallow CNNs, multiscale attention net, and stacked CNNs with a 6.6, 0.3, 0.7 per cent increase in accuracy. The entire implementation of the wavelet CNN is made available under source code.

Looking into Concept Explanation Methods for Diabetic Retinopathy Classification

Diabetic retinopathy is a common complication of diabetes, and monitoring the progression of retinal abnormalities using fundus imaging is crucial. Because the images must be interpreted by a medical expert, it is infeasible to screen all individuals with diabetes for diabetic retinopathy. Deep learning has shown impressive results for automatic analysis and grading of fundus images. One drawback is, however, the lack of interpretability, which hampers the implementation of such systems in the clinic. Explainable artificial intelligence methods can be applied to explain the deep neural networks. Explanations based on concepts have shown to be intuitive for humans to understand, but have not yet been explored in detail for diabetic retinopathy grading. This work investigates and compares two concept-based explanation techniques for explaining deep neural networks developed for automatic diagnosis of diabetic retinopathy: Quantitative Testing with Concept Activation Vectors and Concept Bottleneck Models. We found that both methods have strengths and weaknesses, and choice of method should take the available data and the end user’s preferences into account. Our code is available at &lt;a href='https://github.com/AndreaStoraas/ConceptExplanations_DR_grading'&gt;https://github.com/AndreaStoraas/ConceptExplanations_DR_grading&lt;/a&gt;