Retinal Fundus Images Research Articles

Retinal artery/vein vessel segmentation and measurement for hypertension based on multi-level edge-guided network

Hypertension is a primary risk factor for the onset of cardiocerebrovascular diseases, leading to increased mortality. In the early stages of hypertension, changes in the diameter of the retinal arteries and veins are closely observed. Therefore, the automatic segmentation of these arteries and veins in retinal fundus images is crucial for hypertension monitoring. However, current deep learning based methods still fail to generate semantically consistent segmentation result, especially for narrow blood vessel segments. Moreover, the pixels near the vessel edge are prone to be missclassified by current methods, struggling to obtain edge-preserving segmentation results. These critical issues severely hinder downstream applications, which require accurate measurement of artery/vein diameter. First, to alleviate the issue of lacking semantic consistency for vessel segments, we propose a long-range spatial dependency modeling module to learn to model the long-range spatial dependency. On this basis, a multi-level edge guided spatial aggregation module is further presented to enhance the ability to accurately classify the edge pixels, generating edge-preserving results. Extensive experimental results on the widely used DRIVE dataset and our constructed dataset (HFC-50) show the superiority of the proposed model over state-of-the-art methods. Our method achieves balanced accuracy of 95.7% on DRIVE dataset, outperforming all state-of-art methods. Finally, in order to directly demonstrate the benefit of more accurate retinal artery/vein vessel segmentation for the measurement of the ratio of artery and vein, we quantitatively evaluate the computed artery/vein ratio for hypertension patients, with the artery/vein segmentation results generated by our proposed method.

Detection of Diabetic Retinopathy Using VGG19 and ResNet 50 Models

Diabetic Retinopathy (DR) is an ocular condition that can manifest in individuals living with Diabetes Mellitus (DM). Retinal fundus examinations must be conducted on DM individuals as early identification and treatment of DR can reduce the risk of impaired vision or blindness. The manual diagnosis of DR conducted by eye-care professionals can be tedious and time-consuming, especially during mass screenings. Deep learning (DL) techniques are being used to provide automated diagnosis of DR. This study adopted two CNN (VGG 19 and ResNet50) models for the binary classification of DR (Non-referable DR and Referable DR). Both models were trained and validated with retinal fundus images from publicly available datasets. After training with Kaggle dataset, VGG 19 and ResNet50 models achieved accuracies of 94.3% and 96.9% respectively. For external validation, varying levels of accuracy, sensitivity and specificity were obtained for the two models on different datasets. The sensitivity of the VGG 19 model for the Messidor 2 dataset was 78.8% while the sensitivity of the ResNet50 model for the Indian Diabetic Retinopathy Image Dataset (IDRiD) was 85.7%. Findings in this study have shown that DR detection with deep learning techniques can serve as an assistive tool for eye-care professionals in the future.

A Retinal Fundus Image Segmentation Approach Based on the Segment Anything Model

A Retinal Fundus Image Segmentation Approach Based on the Segment Anything Model

Deep Learning-based Method in Multimodal Data for Diabetic Retinopathy Detection

Diabetic retinopathy (DR) is a complex condition, and incorporating information from multiple sources, such as patient history, laboratory results, or genetic data, can enhance understanding. An ophthalmologist or an automated system can identify DR through manual examination. The automatic detection of diabetic retinopathy has become a preferred choice for patients and healthcare providers due to its cost-effectiveness and time efficiency. The novelty of this research lies in developing a model for predicting diabetic retinopathy using multimodal data fusion, incorporating fundus retinal images, optical coherence tomography (OCT), and electronic health records (EHR) through an early fusion technique implemented in a Long Short-Term Memory (LSTM) network. Our model, which utilizes an early fusion of multimodal data with Local Binary Pattern (LBP), has demonstrated the best performance, achieving an AUC value of 0.99. This high accuracy indicates that integrating information from various data sources can significantly improve the capability of the model in detecting both positive and negative cases of diabetic retinopathy, instilling confidence in the reliability of our findings.

Clinical Utility of Deep Learning Assistance for Detecting Various Abnormal Findings in Color Retinal Fundus Images: A Reader Study.

To evaluate the clinical usefulness of a deep learning-based detection device for multiple abnormal findings on retinal fundus photographs for readers with varying expertise. Fourteen ophthalmologists (six residents, eight specialists) assessed 399 fundus images with respect to 12 major ophthalmologic findings, with or without the assistance of a deep learning algorithm, in two separate reading sessions. Sensitivity, specificity, and reading time per image were compared. With algorithmic assistance, readers significantly improved in sensitivity for all 12 findings (P < 0.05) but tended to be less specific (P < 0.05) for hemorrhage, drusen, membrane, and vascular abnormality, more profoundly so in residents. Sensitivity without algorithmic assistance was significantly lower in residents (23.1%∼75.8%) compared to specialists (55.1%∼97.1%) in nine findings, but it improved to similar levels with algorithmic assistance (67.8%∼99.4% in residents, 83.2%∼99.5% in specialists) with only hemorrhage remaining statistically significantly lower. Variances in sensitivity were significantly reduced for all findings. Reading time per image decreased in images with fewer than three findings per image, more profoundly in residents. When simulated based on images acquired from a health screening center, average reading time was estimated to be reduced by 25.9% (from 16.4 seconds to 12.1 seconds per image) for residents, and by 2.0% (from 9.6 seconds to 9.4 seconds) for specialists. Deep learning-based computer-assisted detection devices increase sensitivity, reduce inter-reader variance in sensitivity, and reduce reading time in less complicated images. This study evaluated the influence that algorithmic assistance in detecting abnormal findings on retinal fundus photographs has on clinicians, possibly predicting its influence on clinical application.

DFC-Net: a dual-path frequency-domain cross-attention fusion network for retinal image quality assessment.

Retinal image quality assessment (RIQA) is crucial for diagnosing various eye diseases and ensuring the accuracy of diagnostic analyses based on retinal fundus images. Traditional deep convolutional neural networks (CNNs) for RIQA face challenges such as over-reliance on RGB image brightness and difficulty in differentiating closely ranked image quality categories. To address these issues, we introduced the Dual-Path Frequency-domain Cross-attention Network (DFC-Net), which integrates RGB images and contrast-enhanced images using contrast-limited adaptive histogram equalization (CLAHE) as dual inputs. This approach improves structure detail detection and feature extraction. We also incorporated a frequency-domain attention mechanism (FDAM) to focus selectively on frequency components indicative of quality degradations and a cross-attention mechanism (CAM) to optimize the integration of dual inputs. Our experiments on the EyeQ and RIQA-RFMiD datasets demonstrated significant improvements, achieving a precision of 0.8895, recall of 0.8923, F1-score of 0.8909, and a Kappa score of 0.9191 on the EyeQ dataset. On the RIQA-RFMiD dataset, the precision was 0.702, recall 0.6729, F1-score 0.6869, and Kappa score 0.7210, outperforming current state-of-the-art approaches.

Deep Learning-Based Detection of Diabetic Retinopathy using Retina Images

The early detection of retinal diseases, such as diabetic retinopathy, is essential to prevent irreversible vision loss. In this study, we propose an automated system for the detection of retinal diseases using deep learning techniques, specifically Convolutional Neural Networks (CNN) and pre-trained models like MobileNet and VGG16. These models are applied to retinal fundus images to identify abnormalities, such as microaneurysms and hemorrhages, that are indicative of retinal diseases. The use of CNN allows for efficient feature extraction, while MobileNet and VGG16, known for their strong performance in image classification tasks, enable accurate disease classification across different stages. The system is trained and evaluated on publicly available datasets, ensuring robust performance across diverse retinal images. The study compares the performance of both MobileNet and VGG16 models, with a focus on achieving high accuracy, sensitivity, and specificity in detecting retinal abnormalities. MobileNet, with its lightweight architecture, proves advantageous for real-time applications on mobile devices, offering fast and efficient disease detection. On the other hand, VGG16 delivers higher precision but at a greater computational cost. Experimental results demonstrate the system’s potential to assist healthcare professionals by automating the diagnostic process, enabling early detection and timely treatment of retinal diseases. This approach significantly reduces the reliance on manual screening, leading to more accessible and scalable diagnostic solutions

Artificial intelligence in assessing cardiovascular diseases and risk factors via retinal fundus images: A review of the last decade

AbstractCardiovascular diseases (CVDs) are the leading cause of death globally. The use of artificial intelligence (AI) methods—in particular, deep learning (DL)—has been on the rise lately for the analysis of different CVD‐related topics. The use of fundus images and optical coherence tomography angiography (OCTA) in the diagnosis of retinal diseases has also been extensively studied. To better understand heart function and anticipate changes based on microvascular characteristics and function, researchers are currently exploring the integration of AI with noninvasive retinal scanning. There is great potential to reduce the number of cardiovascular events and the financial strain on healthcare systems by utilizing AI‐assisted early detection and prediction of cardiovascular diseases on a large scale. A comprehensive search was conducted across various databases, including PubMed, Medline, Google Scholar, Scopus, Web of Sciences, IEEE Xplore, and ACM Digital Library, using specific keywords related to cardiovascular diseases and AI. The study included 87 English‐language publications selected for relevance, and additional references were considered. This article provides an overview of the recent developments and difficulties in using AI and retinal imaging to diagnose cardiovascular diseases. It provides insights for further exploration in this field. Researchers are trying to develop precise disease prognosis patterns in response to the aging population and the growing global burden of CVD. AI and DL are revolutionizing healthcare by potentially diagnosing multiple CVDs from a single retinal image. However, swifter adoption of these technologies in healthcare systems is required.This article is categorized under: Application Areas &gt; Health Care Technologies &gt; Artificial Intelligence

Retinal fundus image super-resolution based on generative adversarial network guided with vascular structure prior

Many ophthalmic and systemic diseases can be screened by analyzing retinal fundus images. The clarity and resolution of retinal fundus images directly determine the effectiveness of clinical diagnosis. Deep learning methods based on generative adversarial networks are used in various research fields due to their powerful generative capabilities, especially image super-resolution. Although Real-ESRGAN is a recently proposed method that excels in processing real-world degraded images, it suffers from structural distortions when super-resolving retinal fundus images are rich in structural information. To address this shortcoming, we first process the input image using a pre-trained U-Net model to obtain a structural segmentation map of the retinal vessels and use the segmentation map as the structural prior. The spatial feature transform layer is then used to better integrate the structural prior into the generation process of the generator. In addition, we introduce channel and spatial attention modules into the skip connections of the discriminator to emphasize meaningful features and accordingly enhance the discriminative power of the discriminator. Based on the original loss functions, we introduce the L1 loss function to measure the pixel-level differences between the segmentation maps of retinal vascular structures in the high-resolution images and the super-resolution images to further constrain the super-resolution images. Simulation results on retinal image datasets show that our improved algorithm results have a better visual performance by suppressing structural distortions in the super-resolution images.

Erratum — Optimized Improved Random Forest-Fostered Glaucoma Detection from Fundus Retinal Images

Erratum — Optimized Improved Random Forest-Fostered Glaucoma Detection from Fundus Retinal Images

A Foundation Language-Image Model of the Retina (FLAIR): encoding expert knowledge in text supervision

Foundation vision-language models are currently transforming computer vision, and are on the rise in medical imaging fueled by their very promising generalization capabilities. However, the initial attempts to transfer this new paradigm to medical imaging have shown less impressive performances than those observed in other domains, due to the significant domain shift and the complex, expert domain knowledge inherent to medical-imaging tasks. Motivated by the need for domain-expert foundation models, we present FLAIR, a pre-trained vision-language model for universal retinal fundus image understanding. To this end, we compiled 38 open-access, mostly categorical fundus imaging datasets from various sources, with up to 101 different target conditions and 288,307 images. We integrate the expert’s domain knowledge in the form of descriptive textual prompts, during both pre-training and zero-shot inference, enhancing the less-informative categorical supervision of the data. Such a textual expert’s knowledge, which we compiled from the relevant clinical literature and community standards, describes the fine-grained features of the pathologies as well as the hierarchies and dependencies between them. We report comprehensive evaluations, which illustrate the benefit of integrating expert knowledge and the strong generalization capabilities of FLAIR under difficult scenarios with domain shifts or unseen categories. When adapted with a lightweight linear probe, FLAIR outperforms fully-trained, dataset-focused models, more so in the few-shot regimes. Interestingly, FLAIR outperforms by a wide margin larger-scale generalist image-language models and retina domain-specific self-supervised networks, which emphasizes the potential of embedding experts’ domain knowledge and the limitations of generalist models in medical imaging. The pre-trained model is available at: https://github.com/jusiro/FLAIR.

Eye disease detection using transfer learning based on retinal fundus image data

Eye disease detection using transfer learning based on retinal fundus image data

Concept-based AI interpretability in physiological time-series data: Example of abnormality detection in electroencephalography

Background and ObjectiveDespite recent performance advancements, deep learning models are not yet adopted in clinical practice on a wide scale. The intrinsic intransparency of such systems is commonly cited as one major reason for this reluctance. This has motivated methods that aim to provide explanations of model functioning. Known limitations of feature-based explanations have led to an increased interest in concept-based interpretability. Testing with Concept Activation Vectors (TCAV) employs human-understandable, abstract concepts to explain model behavior. The method has previously been applied to the medical domain in the context of electronic health records, retinal fundus images and magnetic resonance imaging. MethodsWe explore the usage of TCAV for building interpretable models on physiological time series, using an example of abnormality detection in electroencephalography (EEG). For this purpose, we adopt the XceptionTime model, which is suitable for multi-channel physiological data of variable sizes. The model provides state-of-the-art performance on raw EEG data and is publically available. We propose and test several ideas regarding concept definition through metadata mining, using additional labeled EEG data and extracting interpretable signal characteristics in the form of frequencies. By including our own hospital data with analog labeling, we further evaluate the robustness of our approach. ResultsThe tested concepts show a TCAV score distribution that is in line with the clinical expectations, i.e. concepts known to have strong links with EEG pathologies (such as epileptiform discharges) received higher scores than the neutral concepts (e.g. sex). The scores were consistent across the applied concept generation strategies. ConclusionsTCAV has the potential to improve interpretability of deep learning applied to multi-channel signals as well as to detect possible biases in the data. Still, further work on developing the strategies for concept definition and validation on clinical physiological time series is needed to better understand how to extract clinically relevant information from the concept sensitivity scores.

Retinal Imaging-Based Oculomics: Artificial Intelligence as a Tool in the Diagnosis of Cardiovascular and Metabolic Diseases.

Cardiovascular diseases (CVDs) are a major cause of mortality globally, emphasizing the need for early detection and effective risk assessment to improve patient outcomes. Advances in oculomics, which utilize the relationship between retinal microvascular changes and systemic vascular health, offer a promising non-invasive approach to assessing CVD risk. Retinal fundus imaging and optical coherence tomography/angiography (OCT/OCTA) provides critical information for early diagnosis, with retinal vascular parameters such as vessel caliber, tortuosity, and branching patterns identified as key biomarkers. Given the large volume of data generated during routine eye exams, there is a growing need for automated tools to aid in diagnosis and risk prediction. The study demonstrates that AI-driven analysis of retinal images can accurately predict cardiovascular risk factors, cardiovascular events, and metabolic diseases, surpassing traditional diagnostic methods in some cases. These models achieved area under the curve (AUC) values ranging from 0.71 to 0.87, sensitivity between 71% and 89%, and specificity between 40% and 70%, surpassing traditional diagnostic methods in some cases. This approach highlights the potential of retinal imaging as a key component in personalized medicine, enabling more precise risk assessment and earlier intervention. It not only aids in detecting vascular abnormalities that may precede cardiovascular events but also offers a scalable, non-invasive, and cost-effective solution for widespread screening. However, the article also emphasizes the need for further research to standardize imaging protocols and validate the clinical utility of these biomarkers across different populations. By integrating oculomics into routine clinical practice, healthcare providers could significantly enhance early detection and management of systemic diseases, ultimately improving patient outcomes. Fundus image analysis thus represents a valuable tool in the future of precision medicine and cardiovascular health management.

Revolutionizing diabetic eye disease detection: retinal image analysis with cutting-edge deep learning techniques

Globally, glaucoma is a leading cause of visual impairment and vision loss, emphasizing the critical need for early diagnosis and intervention. This research explores the application of deep learning for automated glaucoma diagnosis using retinal fundus photographs. We introduce a novel cross-sectional optic nerve head (ONH) feature derived from optical coherence tomography (OCT) images to enhance existing diagnostic procedures. Our approach leverages deep learning to automatically detect key optic disc characteristics, eliminating the need for manual feature engineering. The deep learning classifier then categorizes images as normal or abnormal, streamlining the diagnostic process. Deep learning techniques have proven effective in classifying and segmenting retinal fundus images, enabling the analysis of a growing number of images. This study introduces a novel mixed loss function that combines the strengths of focal loss and correntropy loss to handle complex biomedical data with class imbalance and outliers, particularly in OCT images. We further refine a multi-task deep learning model that capitalizes on similarities across major eye-fundus activities and metrics for glaucoma detection. The model is rigorously evaluated on a real-world ophthalmic dataset, achieving impressive accuracy, specificity, and sensitivity of 100%, 99.8%, and 99.2%, respectively, surpassing state-of-the-art methods. These promising results underscore the potential of our deep learning algorithm for automated glaucoma diagnosis, with significant implications for clinical applications. By simultaneously addressing segmentation and classification challenges, our approach demonstrates its effectiveness in accurately identifying ocular diseases, paving the way for improved glaucoma diagnosis and early intervention.

Detection and diagnosis of diabetic eye diseases using two phase transfer learning approach.

Early diagnosis and treatment of diabetic eye disease (DED) improve prognosis and lessen the possibility of permanent vision loss. Screening of retinal fundus images is a significant process widely employed for diagnosing patients with DED or other eye problems. However, considerable time and effort are required to detect these images manually. Deep learning approaches in machine learning have attained superior performance for the binary classification of healthy and pathological retinal fundus images. In contrast, multi-class retinal eye disease classification is still a difficult task. Therefore, a two-phase transfer learning approach is developed in this research for automated classification and segmentation of multi-class DED pathologies. In the first step, a Modified ResNet-50 model pre-trained on the ImageNet dataset was transferred and learned to classify normal diabetic macular edema (DME), diabetic retinopathy, glaucoma, and cataracts. In the second step, the defective region of multiple eye diseases is segmented using the transfer learning-based DenseUNet model. From the publicly accessible dataset, the suggested model is assessed using several retinal fundus images. Our proposed model for multi-class classification achieves a maximum specificity of 99.73%, a sensitivity of 99.54%, and an accuracy of 99.67%.

Fundus-DANet: Dilated Convolution and Fusion Attention Mechanism for Multilabel Retinal Fundus Image Classification

The difficulty of classifying retinal fundus images with one or more illnesses present or missing is known as fundus multi-lesion classification. The challenges faced by current approaches include the inability to extract comparable morphological features from images of different lesions and the inability to resolve the issue of the same lesion, which presents significant feature variances due to grading disparities. This paper proposes a multi-disease recognition network model, Fundus-DANet, based on the dilated convolution. It has two sub-modules to address the aforementioned issues: the interclass learning module (ILM) and the dilated-convolution convolutional block attention module (DA-CBAM). The DA-CBAM uses a convolutional block attention module (CBAM) and dilated convolution to extract and merge multiscale information from images. The ILM uses the channel attention mechanism to map the features to lower dimensions, facilitating exploring latent relationships between various categories. The results demonstrate that this model outperforms previous models in classifying fundus multilocular lesions in the OIA-ODIR dataset with 93% accuracy.

Assessment of Clinical Metadata on the Accuracy of Retinal Fundus Image Labels in Diabetic Retinopathy in Uganda: Case-Crossover Study Using the Multimodal Database of Retinal Images in Africa.

Labeling color fundus photos (CFP) is an important step in the development of artificial intelligence screening algorithms for the detection of diabetic retinopathy (DR). Most studies use the International Classification of Diabetic Retinopathy (ICDR) to assign labels to CFP, plus the presence or absence of macular edema (ME). Images can be grouped as referrable or nonreferrable according to these classifications. There is little guidance in the literature about how to collect and use metadata as a part of the CFP labeling process. This study aimed to improve the quality of the Multimodal Database of Retinal Images in Africa (MoDRIA) by determining whether the availability of metadata during the image labeling process influences the accuracy, sensitivity, and specificity of image labels. MoDRIA was developed as one of the inaugural research projects of the Mbarara University Data Science Research Hub, part of the Data Science for Health Discovery and Innovation in Africa (DS-I Africa) initiative. This is a crossover assessment with 2 groups and 2 phases. Each group had 10 randomly assigned labelers who provided an ICDR score and the presence or absence of ME for each of the 50 CFP in a test image with and without metadata including blood pressure, visual acuity, glucose, and medical history. Specificity and sensitivity of referable retinopathy were based on ICDR scores, and ME was calculated using a 2-sided t test. Comparison of sensitivity and specificity for ICDR scores and ME with and without metadata for each participant was calculated using the Wilcoxon signed rank test. Statistical significance was set at P<.05. The sensitivity for identifying referrable DR with metadata was 92.8% (95% CI 87.6-98.0) compared with 93.3% (95% CI 87.6-98.9) without metadata, and the specificity was 84.9% (95% CI 75.1-94.6) with metadata compared with 88.2% (95% CI 79.5-96.8) without metadata. The sensitivity for identifying the presence of ME was 64.3% (95% CI 57.6-71.0) with metadata, compared with 63.1% (95% CI 53.4-73.0) without metadata, and the specificity was 86.5% (95% CI 81.4-91.5) with metadata compared with 87.7% (95% CI 83.9-91.5) without metadata. The sensitivity and specificity of the ICDR score and the presence or absence of ME were calculated for each labeler with and without metadata. No findings were statistically significant. The sensitivity and specificity scores for the detection of referrable DR were slightly better without metadata, but the difference was not statistically significant. We cannot make definitive conclusions about the impact of metadata on the sensitivity and specificity of image labels in our study. Given the importance of metadata in clinical situations, we believe that metadata may benefit labeling quality. A more rigorous study to determine the sensitivity and specificity of CFP labels with and without metadata is recommended.

Prediction of Cardiovascular Markers and Diseases Using Retinal Fundus Images and Deep Learning: A Systematic Scoping Review

Abstract Background Rapid development in deep learning for image analysis inspired studies to focus on predicting cardiovascular risk using retinal fundus images. This scoping review aimed to identify and describe studies using retinal fundus images and deep learning to predict cardiovascular risk markers and diseases. Methods We searched MEDLINE and Embase on 17/11/2023. Abstracts and relevant full-text articles were independently screened by two reviewers. We included studies that used deep learning for the analysis of retinal fundus images to predict cardiovascular risk markers or cardiovascular diseases and excluded studies only using predefined characteristics of retinal fundus images were not considered. Study characteristics were presented using descriptive statistics. Results We included 24 articles published between 2018 and 2023. Among these, 23 (96%) were cross-sectional studies and eight (33%) were follow-up studies with clinical CVD outcomes. Seven studies included a combination of both designs. Most studies (96%) used convolutional neural networks to process images. We found nine (38%) studies that incorporated clinical risk factors in the prediction and four (17%) that compared the results to commonly used clinical risk scores in a prospective setting. Three of these reported improved discriminative performance. External validation of models was rare (21%). Conclusions There is increasing interest in using retinal fundus images in cardiovascular risk assessment with some studies demonstrating some improvements in prediction. However, more prospective studies, comparisons of results to clinical risk scores, and models augmented with traditional risk factors can strengthen further research in the field.

Automatic retinal image analysis methods using colour fundus images for screening glaucomatous optic neuropathy

ObjectivesTrain an automatic retinal image analysis (ARIA) method to screen glaucomatous optic neuropathy (GON) on non-mydriatic retinal images labelled with the additional results of optical coherence tomography (OCT) and assess...