Retinal Fundus Images Research Articles

IGWAS: Image-based genome-wide association of self-supervised deep phenotyping of retina fundus images.

Existing imaging genetics studies have been mostly limited in scope by using imaging-derived phenotypes defined by human experts. Here, leveraging new breakthroughs in self-supervised deep representation learning, we propose a new approach, image-based genome-wide association study (iGWAS), for identifying genetic factors associated with phenotypes discovered from medical images using contrastive learning. Using retinal fundus photos, our model extracts a 128-dimensional vector representing features of the retina as phenotypes. After training the model on 40,000 images from the EyePACS dataset, we generated phenotypes from 130,329 images of 65,629 British White participants in the UK Biobank. We conducted GWAS on these phenotypes and identified 14 loci with genome-wide significance (p<5×10-8 and intersection of hits from left and right eyes). We also did GWAS on the retina color, the average color of the center region of the retinal fundus photos. The GWAS of retina colors identified 34 loci, 7 are overlapping with GWAS of raw image phenotype. Our results establish the feasibility of this new framework of genomic study based on self-supervised phenotyping of medical images.

Age-Related Macular Degeneration Detection in Retinal Fundus Images by a Deep Convolutional Neural Network

Computer-based pre-diagnosis of diseases through medical imaging is a task worked on for many years. The so-called fundus images stand out since they do not have uniform illumination and are highly sensitive to noise. One of the diseases that can be pre-diagnosed through fundus images is age-related macular degeneration, which initially manifests as the appearance of lesions called drusen. Several ways of pre-diagnosing macular degeneration have been proposed, methods based entirely on the segmentation of drusen with prior image processing have been designed and applied, and methods based on image pre-processing and subsequent conversion to feature vectors, or patterns, to be classified by a Machine-Learning model have also been developed. Finally, in recent years, the use of Deep-Learning models, particularly Convolutional Networks, has been proposed and used in classification problems where the data are only images. The latter has allowed the so-called transfer learning, which consists of using the learning achieved in the solution of one problem to solve another. In this paper, we propose the use of transfer learning through the Xception Deep Convolutional Neural Network to detect age-related macular degeneration in fundus images. The performance of the Xception model was compared against six other state-of-the-art models with a dataset created from images available in public and private datasets, which were divided into training/validation and test; with the training/validation set, the training was made using 10-fold cross-validation. The results show that the Xception neural network obtained a validation accuracy that surpasses other models, such as the VGG-16 or VGG-19 networks, and had an accuracy higher than 80% in the test set. We consider that the contributions of this work include the use of a Convolutional Neural Network model for the detection of age-related macular degeneration through the classification of fundus images in those affected by AMD (drusen) and the images of healthy patients. The performance of this model is compared against other methods featured in the state-of-the-art approaches, and the best model is tested on a test set outside the training and validation set.

An Artificial Intelligence Driven Approach for Classification of Ophthalmic Images using Convolutional Neural Network: An Experimental Study.

Early disease detection is emphasized within ophthalmology now more than ever, and as a result, clinicians and innovators turn to deep learning to expedite accurate diagnosis and mitigate treatment delay. Efforts concentrate on the creation of deep learning systems that analyze clinical image data to detect disease-specific features with maximum sensitivity. Moreover, these systems hold promise of early accurate diagnosis and treatment of patients with common progressive diseases. DenseNet, ResNet, and VGG-16 are among a few of the deep learning Convolutional Neural Network (CNN) algorithms that have been introduced and are being investigated for potential application within ophthalmology. In this study, the authors sought to create and evaluate a novel ensembled deep learning CNN model that analyzes a dataset of shuffled retinal color fundus images (RCFIs) from eyes with various ocular disease features (cataract, glaucoma, diabetic retinopathy). Our aim was to determine (1) the relative performance of our finalized model in classifying RCFIs according to disease and (2) the diagnostic potential of the finalized model to serve as a screening test for specific diseases (cataract, glaucoma, diabetic retinopathy) upon presentation of RCFIs with diverse disease manifestations. We found adding convolutional layers to an existing VGG-16 model, which was named as a proposed model in this article that, resulted in significantly increased performance with 98% accuracy (p<0.05), including good diagnostic potential for binary disease detection in cataract, glaucoma, diabetic retinopathy. The proposed model was found to be suitable and accurate for a decision support system in Ophthalmology Clinical Framework.

Pathologic myopia diagnosis and localization from retinal fundus images using custom CNN

Pathologic myopia diagnosis and localization from retinal fundus images using custom CNN

Colour Image Enhancement Model of Retinal Fundus Image for Diabetic Retinopathy Recognition

Diabetic retinopathy (DR) features are typically identified through ophthalmologist eye examinations, but these images often facechallenges like low contrast, non-uniform illumination, and colour inconsistency, affecting the diagnosis accuracy. Therefore, this studyintroduces two novel techniques to improve image quality. One is applying colour image processing techniques to original retinalfundus images, overcoming existing algorithm limitations. Firstly, a new colour correction algorithm was proposed based on TunedBrightness Controlled Single-Scale Retinex (TBCSSR) named Fuzzy TBCSSR Histogram Matching (fTBCSSRhm) to address the issue of colour inconsistency in the dataset. Secondly, based on hybrid particle swarm optimisation-contrast stretch (HPSOCS), the hybridof TBCSSR and HPSOCS named eTBCSSR-HPSOCS algorithm is introduced to tackle the limitations of the standard Particle SwarmOptimisation (PSO) algorithm in HPSOCS, which is prone to local optima and exhibits low convergence rates. This technique combinesthe L-component of the LAB colour model with an enhanced velocity mechanism in PSO and contrast stretching (lavHPSOCS). Its goalis to fine-tune parameters automatically, reduce over-enhancement, avoid unwanted artefacts, and preserve intricate details. This approach improves optimisation by balancing exploration and exploitation and refining velocity control. The proposed algorithm underwent both qualitative and quantitative evaluations. Tests on 100 retinal fundus images from primary datasets were performed to benchmark the algorithm against three existing approaches. The results show that the qualitative performance of the proposed enhancement is more favourable to ophthalmologist specialists than other images. Quantitatively, eTBCSSR-HPSOCS outperforms others with the lowest mean squared error (MSE) of 42.72859, the highest peak signal-to-noise ratio (PSNR) of 32.768, and entropy of 0.977.

A Multi-Stage Approach for Cardiovascular Risk Assessment from Retinal Images Using an Amalgamation of Deep Learning and Computer Vision Techniques.

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide. Early detection and effective risk assessment are crucial for implementing preventive measures and improving patient outcomes for CVDs. This work presents a novel approach to CVD risk assessment using fundus images, leveraging the inherent connection between retinal microvascular changes and systemic vascular health. This study aims to develop a predictive model for the early detection of CVDs by evaluating retinal vascular parameters. This methodology integrates both handcrafted features derived through mathematical computation and retinal vascular patterns extracted by artificial intelligence (AI) models. By combining these approaches, we seek to enhance the accuracy and reliability of CVD risk prediction in individuals. The methodology integrates state-of-the-art computer vision algorithms and AI techniques in a multi-stage architecture to extract relevant features from retinal fundus images. These features encompass a range of vascular parameters, including vessel caliber, tortuosity, and branching patterns. Additionally, a deep learning (DL)-based binary classification model is incorporated to enhance predictive accuracy. A dataset comprising fundus images and comprehensive metadata from the clinical trials conducted is utilized for training and validation. The proposed approach demonstrates promising results in the early prediction of CVD risk factors. The interpretability of the approach is enhanced through visualization techniques that highlight the regions of interest within the fundus images that are contributing to the risk predictions. Furthermore, the validation conducted in the clinical trials and the performance analysis of the proposed approach shows the potential to provide early and accurate predictions. The proposed system not only aids in risk stratification but also serves as a valuable tool for identifying vascular abnormalities that may precede overt cardiovascular events. The approach has achieved an accuracy of 85% and the findings of this study underscore the feasibility and efficacy of leveraging fundus images for cardiovascular risk assessment. As a non-invasive and cost-effective modality, fundus image analysis presents a scalable solution for population-wide screening programs. This research contributes to the evolving landscape of precision medicine by providing an innovative tool for proactive cardiovascular health management. Future work will focus on refining the solution's robustness, exploring additional risk factors, and validating its performance in additional and diverse clinical settings.

CDAM-Net: Channel shuffle dual attention based multi-scale CNN for efficient glaucoma detection using fundus images

Glaucoma is a typical eye disorder that induces damage to the optic nerve due to increased intraocular pressure. It ultimately leads to partial or complete blindness without clinical reversal. Hence, it is of utmost importance to screen and detect glaucoma at an early stage. Most of the earlier glaucoma diagnosis methods rely on manual feature engineering, which is time-consuming and requires domain experts. Although recent methods, particularly, convolutional neural networks (CNNs) facilitate learning high-level feature representations from fundus images, they need extensive parameters and pose overfitting issues due to insufficient training samples. Further, conventional CNNs often ignore the minute changes in the lesion region. To overcome these issues, we propose a lightweight multi-scale CNN architecture called as CDAM-Net for effective glaucoma identification from retinal fundus images. Additionally, we introduce an attention module called channel shuffle dual attention (CSDA), comprising of a channel attention block, a spatial attention block and a channel shuffle unit, to focus on important regions in the fundus images, thereby extracting class-specific features. The CDAM-Net mainly consists of multi-scale feature representation (MFR) blocks that enable the extraction of multi-scale features from fundus images. Each MFR block is followed by a CSDA module, which further helps enrich the feature representation. The CDAM-Net is evaluated on a retinal fundus image (RFI) dataset containing 1426 fundus images (837 glaucoma and 589 normal), and the results indicate that CDAM-Net yields promising classification performance compared to existing techniques. Also, ablation studies are carried out to test the effectiveness of each component of the CDAM-Net.

Diabetic Retinopathy Lesion Segmentation Method Based on Multi-Scale Attention and Lesion Perception

The early diagnosis of diabetic retinopathy (DR) can effectively prevent irreversible vision loss and assist ophthalmologists in providing timely and accurate treatment plans. However, the existing methods based on deep learning have a weak perception ability of different scale information in retinal fundus images, and the segmentation capability of subtle lesions is also insufficient. This paper aims to address these issues and proposes MLNet for DR lesion segmentation, which mainly consists of the Multi-Scale Attention Block (MSAB) and the Lesion Perception Block (LPB). The MSAB is designed to capture multi-scale lesion features in fundus images, while the LPB perceives subtle lesions in depth. In addition, a novel loss function with tailored lesion weight is designed to reduce the influence of imbalanced datasets on the algorithm. The performance comparison between MLNet and other state-of-the-art methods is carried out in the DDR dataset and DIARETDB1 dataset, and MLNet achieves the best results of 51.81% mAUPR, 49.85% mDice, and 37.19% mIoU in the DDR dataset, and 67.16% mAUPR and 61.82% mDice in the DIARETDB1 dataset. The generalization experiment of MLNet in the IDRiD dataset achieves 59.54% mAUPR, which is the best among other methods. The results show that MLNet has outstanding DR lesion segmentation ability.

RLeU-Net: Segmentation of blood vessels in retinal fundus images for Diabetic Retinopathy Screening

RLeU-Net: Segmentation of blood vessels in retinal fundus images for Diabetic Retinopathy Screening

A novel vector field analysis for quantitative structure changes after macular epiretinal membrane surgery.

The aim of this study was to introduce novel vector field analysis for the quantitative measurement of retinal displacement after epiretinal membrane (ERM) removal. We developed a novel framework to measure retinal displacement from retinal fundus images as follows: (1) rigid registration of preoperative retinal fundus images in reference to postoperative retinal fundus images, (2) extraction of retinal vessel segmentation masks from these retinal fundus images, (3) non-rigid registration of preoperative vessel masks in reference to postoperative vessel masks, and (4) calculation of the transformation matrix required for non-rigid registration for each pixel. These pixel-wise vector field results were summarized according to predefined 24 sectors after standardization. We applied this framework to 20 patients who underwent ERM removal to obtain their retinal displacement vector fields between retinal fundus images taken preoperatively and at postoperative 1, 4, 10, and 22months. The mean direction of displacement vectors was in the nasal direction. The mean standardized magnitudes of retinal displacement between preoperative and postoperative 1month, postoperative 1 and 4, 4 and 10, and 10 and 22months were 38.6, 14.9, 7.6, and 5.4, respectively. In conclusion, the proposed method provides a computerized, reproducible, and scalable way to analyze structural changes in the retina with a powerful visualization tool. Retinal structural changes were mostly concentrated in the early postoperative period and tended to move nasally.

Artificial intelligence based glaucoma and diabetic retinopathy detection using MATLAB - retrained AlexNet convolutional neural network.

Glaucoma and diabetic retinopathy (DR) are the leading causes of irreversible retinal damage leading to blindness. Early detection of these diseases through regular screening is especially important to prevent progression. Retinal fundus imaging serves as the principal method for diagnosing glaucoma and DR. Consequently, automated detection of eye diseases represents a significant application of retinal image analysis. Compared with classical diagnostic techniques, image classification by convolutional neural networks (CNN) exhibits potential for effective eye disease detection. This paper proposes the use of MATLAB - retrained AlexNet CNN for computerized eye diseases identification, particularly glaucoma and diabetic retinopathy, by employing retinal fundus images. The acquisition of the database was carried out through free access databases and access upon request. A transfer learning technique was employed to retrain the AlexNet CNN for non-disease (Non_D), glaucoma (Sus_G) and diabetic retinopathy (Sus_R) classification. Moreover, model benchmarking was conducted using ResNet50 and GoogLeNet architectures. A Grad-CAM analysis is also incorporated for each eye condition examined. Metrics for validation accuracy, false positives, false negatives, precision, and recall were reported. Validation accuracies for the NetTransfer (I-V) and netAlexNet ranged from 89.7% to 94.3%, demonstrating varied effectiveness in identifying Non_D, Sus_G, and Sus_R categories, with netAlexNet achieving a 93.2% accuracy in the benchmarking of models against netResNet50 at 93.8% and netGoogLeNet at 90.4%. This study demonstrates the efficacy of using a MATLAB-retrained AlexNet CNN for detecting glaucoma and diabetic retinopathy. It emphasizes the need for automated early detection tools, proposing CNNs as accessible solutions without replacing existing technologies.

Enhancing Retinal Fundus Image Quality Assessment With Swin-Transformer-Based Learning Across Multiple Color-Spaces.

The assessment of retinal image (RI) quality holds significant importance in both clinical trials and large datasets, because suboptimal images can potentially conceal early signs of diseases, thereby resulting in inaccurate medical diagnoses. This study aims to develop an automatic method for Retinal Image Quality Assessment (RIQA) that incorporates visual explanations, aiming to comprehensively evaluate the quality of retinal fundus images (RIs). We developed an automatic RIQA system, named Swin-MCSFNet, utilizing 28,792 RIs from the EyeQ dataset, as well as 2000 images from the EyePACS dataset and an additional 1,000 images from the OIA-ODIR dataset. After preprocessing, including cropping black regions, data augmentation, and normalization, a Swin-MCSFNet classifier based on the Swin-Transformer for multiple color-space fusion was proposed to grade the quality of RIs. The generalizability of Swin-MCSFNet was validated across multiple data centers. Additionally, for enhanced interpretability, a Score-CAM-generated heatmap was applied to provide visual explanations. Experimental results reveal that the proposed Swin-MCSFNet achieves promising performance, yielding a micro-receiver operating characteristic (ROC) of 0.93 and ROC scores of 0.96, 0.81, and 0.96 for the "Good," "Usable," and "Reject" categories, respectively. These scores underscore the accuracy of RIQA based on Swin-MCSF in distinguishing among the three categories. Furthermore, heatmaps generated across different RIQA classification scores and various color spaces suggest that regions in the retinal images from multiple color spaces contribute significantly to the decision-making process of the Swin-MCSFNet classifier. Our study demonstrates that the proposed Swin-MCSFNet outperforms other methods in experiments conducted on multiple datasets, as evidenced by the superior performance metrics and insightful Score-CAM heatmaps. This study constructs a new retinal image quality evaluation system, which will contribute to the subsequent research of retinal images.

Trish: an efficient activation function for CNN models and analysis of its effectiveness with optimizers in diagnosing glaucoma

Glaucoma is an eye disease that spreads over time without showing any symptoms at an early age and can result in vision loss in advanced ages. The most critical issue in this disease is to detect the symptoms of the disease at an early age. Various researches are carried out on machine learning approaches that will provide support to the expert for this diagnosis. The activation function plays a pivotal role in deep learning models, as it introduces nonlinearity, enabling neural networks to learn complex patterns and relationships within data, thus facilitating accurate predictions and effective feature representations. In this study, it is focused on developing an activation function that can be used in CNN architectures using glaucoma disease datasets. The developed function (Trish) was compared with ReLU, LReLU, Mish, Swish, Smish, and Logish activation functions using SGD, Adam, RmsProp, AdaDelta, AdaGrad, Adamax, and Nadam optimizers in CNN architectures. Datasets consisting of retinal fundus images named ACRIMA and HRF were used within the scope of the experiments. These datasets are widely known and currently used in the literature. To strengthen the test validity, the proposed function was also tested on the CIFAR-10 dataset. As a result of the study, 97.22% validation accuracy performance was obtained. It should be stated that the acquired performance value is at a significant level for the detection of glaucoma.

DIABETIC RETINOPATHY SEVERITY CLASSIFICATION USING CUSTOMIZED CNN

Diabetic retinopathy (DR) is caused by diabetes, and could lead to permanent blindness. Diabetes causes damage to the arteries and veins of eye and further results in the loss of vision. Detection of DR is challenging as there are not many symptoms of the disease at the early stage. Opthalmologists can detect the DR, and analyze the severity by visual analysis of the fundus images. The population of diabetes-affected people is large and hence the manual detection and analysis is tedious and expensive. The automated screening and severity detection systems are therefore needed. In this paper, the experiments with CNN for classifying the DR images into five classes (NO DR, mild, moderate, severe and PDR) are conducted on the 2015 and 2019 Blindness Detection Kaggle dataset. Customized CNN model is designed in order to provide accurate severity classification. The CNN model consists of two convolutional layers, two max-pooling layers, one flattening layer and two dense layers. The retinal fundus images present structural and impulsive noise. Gaussian blur technique is applied as preprocessing to reduce the noise. We experimented with Adam’s optimizer as well as SGD optimizer and observed that the best classification results obtained using Adam’s optimizer (89% accuracy) are promising but warrant further investigation. Moreover, our approach has been able to have good and consistent AUC for all the classes, and particularly worked better than the existing approaches for the detection of class 3 (severe DR).

Res-Unet based blood vessel segmentation and cardio vascular disease prediction using chronological chef-based optimization algorithm based deep residual network from retinal fundus images

Res-Unet based blood vessel segmentation and cardio vascular disease prediction using chronological chef-based optimization algorithm based deep residual network from retinal fundus images

A Siamese ResNeXt network for predicting carotid intimal thickness of patients with T2DM from fundus images.

To develop and validate an artificial intelligence diagnostic model based on fundus images for predicting Carotid Intima-Media Thickness (CIMT) in individuals with Type 2 Diabetes Mellitus (T2DM). In total, 1236 patients with T2DM who had both retinal fundus images and CIMT ultrasound records within a single hospital stay were enrolled. Data were divided into normal and thickened groups and sent to eight deep learning models: convolutional neural networks of the eight models were all based on ResNet or ResNeXt. Their encoder and decoder modes are different, including the standard mode, the Parallel learning mode, and the Siamese mode. Except for the six unimodal networks, two multimodal networks based on ResNeXt under the Parallel learning mode or the Siamese mode were embedded with ages. Performance of eight models were compared via the confusion matrix, precision, recall, specificity, F1 value, and ROC curve, and recall was regarded as the main indicator. Besides, Grad-CAM was used to visualize the decisions made by Siamese ResNeXt network, which is the best performance. Performance of various models demonstrated the following points: 1) the RexNeXt showed a notable improvement over the ResNet; 2) the structural Siamese networks, which extracted features parallelly and independently, exhibited slight performance enhancements compared to the traditional networks. Notably, the Siamese networks resulted in significant improvements; 3) the performance of classification declined if the age factor was embedded in the network. Taken together, the Siamese ResNeXt unimodal model performed best for its superior efficacy and robustness. This model achieved a recall rate of 88.0% and an AUC value of 90.88% in the validation subset. Additionally, heatmaps calculated by the Grad-CAM algorithm presented concentrated and orderly mappings around the optic disc vascular area in normal CIMT groups and dispersed, irregular patterns in thickened CIMT groups. We provided a Siamese ResNeXt neural network for predicting the carotid intimal thickness of patients with T2DM from fundus images and confirmed the correlation between fundus microvascular lesions and CIMT.

PKSEA-Net: A prior knowledge supervised edge-aware multi-task network for retinal arteriolar morphometry

Retinal fundus images serve as a non-invasive modality to obtain information pertaining to retinal vessels through fundus photography, thereby offering insights into cardiovascular and cerebrovascular diseases. Retinal arteriolar morphometry has emerged as the most convenient and fundamental clinical methodology in the realm of patient screening and diagnosis. Nevertheless, the analysis of retinal arterioles is challenging attributable to imaging noise, stochastic fuzzy characteristics, and blurred boundaries proximal to blood vessels. In response to these limitations, we introduce an innovative methodology, named PKSEA-Net, which aims to improve segmentation accuracy by enhancing the perception of edge information in retinal fundus images. PKSEA-Net employs the universal architecture PVT-v2 as the encoder, complemented by a novel decoder architecture consisting of an Edge-Aware Block (EAB) and a Pyramid Feature Fusion Module (PFFM). The EAB block incorporates prior knowledge for supervision and multi-query for multi-task learning, with supervision information derived from an enhanced Full Width at Half Maximum (FWHM) algorithm and gradient map. Moreover, PFFM efficiently integrates multi-scale features through a novel attention fusion method. Additionally, we have collected a Retinal Cross-Sectional Vessel (RCSV) dataset derived from approximately 200 patients in Quzhou People’s Hospital to serve as the benchmark dataset. Comparative evaluations with several state-of-the-art (SOTA) networks confirm that PKSEA-Net achieves exceptional experimental performance, thereby establishing its status as a SOTA approach for precise boundary delineation and retinal vessel segmentation.

Vision transformer with masked autoencoders for referable diabetic retinopathy classification based on large-size retina image.

Computer-aided diagnosis systems based on deep learning algorithms have shown potential applications in rapid diagnosis of diabetic retinopathy (DR). Due to the superior performance of Transformer over convolutional neural networks (CNN) on natural images, we attempted to develop a new model to classify referable DR based on a limited number of large-size retinal images by using Transformer. Vision Transformer (ViT) with Masked Autoencoders (MAE) was applied in this study to improve the classification performance of referable DR. We collected over 100,000 publicly fundus retinal images larger than 224×224, and then pre-trained ViT on these retinal images using MAE. The pre-trained ViT was applied to classify referable DR, the performance was also compared with that of ViT pre-trained using ImageNet. The improvement in model classification performance by pre-training with over 100,000 retinal images using MAE is superior to that pre-trained with ImageNet. The accuracy, area under curve (AUC), highest sensitivity and highest specificity of the present model are 93.42%, 0.9853, 0.973 and 0.9539, respectively. This study shows that MAE can provide more flexibility to the input image and substantially reduce the number of images required. Meanwhile, the pretraining dataset scale in this study is much smaller than ImageNet, and the pre-trained weights from ImageNet are not required also.

A novel approach for intelligent diagnosis and grading of diabetic retinopathy

Diabetic retinopathy (DR) is a severe ocular complication of diabetes that can lead to vision damage and even blindness. Currently, traditional deep convolutional neural networks (CNNs) used for DR grading tasks face two primary challenges: (1) insensitivity to minority classes due to imbalanced data distribution, and (2) neglecting the relationship between the left and right eyes by utilizing the fundus image of only one eye for training without differentiating between them. To tackle these challenges, we proposed the DRGCNN (DR Grading CNN) model. To solve the problem caused by imbalanced data distribution, our model adopts a more balanced strategy by allocating an equal number of channels to feature maps representing various DR categories. Furthermore, we introduce a CAM-EfficientNetV2-M encoder dedicated to encoding input retinal fundus images for feature vector generation. The number of parameters of our encoder is 52.88 M, which is less than RegNet_y_16gf (80.57 M) and EfficientNetB7 (63.79 M), but the corresponding kappa value is higher. Additionally, in order to take advantage of the binocular relationship, we input fundus retinal images from both eyes of the patient into the network for features fusion during the training phase. We achieved a kappa value of 86.62% on the EyePACS dataset and 86.16% on the Messidor-2 dataset. Experimental results on these representative datasets for diabetic retinopathy (DR) demonstrate the exceptional performance of our DRGCNN model, establishing it as a highly competitive intelligent classification model in the field of DR. The code is available for use at https://github.com/Fat-Hai/DRGCNN.

The classification of eye diseases from fundus images based on CNN and pretrained models

Visual impairment affects more than a billion people worldwide due to insufficient care or inadequate vision screening. Computer-aided diagnosis using deep neural networks is a promising approach, it can analyse and process retinal fundus images, providing valuable reference data for doctors in clinical diagnosis or screening. This study aims to achieve an accurate classification of fundus images, including images of healthy patients as well as those with diabetic retinopathy, cataracts, and glaucoma, using a convolutional neural network (CNN) architecture and several pretrained models (AlexNet, GoogleNet, ResNet18, ResNet50, YOLOv3, and VGG 19). To enhance the training process, a mirror effect technique was applied to augment the volume of data. The experimental study resulted in very satisfactory outcomes, with the GoogleNet model paired with the SGDM optimiser achieving the highest accuracy (92.7 %).