Automated Diabetic Retinopathy Screening Research Articles

Deep Learning for Early Detection of Diabetic Retinopathy: A Colour Fundus Image-based Approach with VGG16 and VGG19

Diabetic retinopathy (DR) is a prevalent complication of diabetes, posing a significant threat to vision. Early detection and intervention are critical to prevent vision loss. However, manual screening of retinal images for DR is time-consuming and susceptible to human error. This study investigates the application of deep learning models, specifically VGG16 and VGG19, for automated DR diagnosis in Colour Fundus images. We evaluate their performance in classifying images as either Diabetic Retinopathy or No Diabetic Retinopathy. Our results demonstrate high testing accuracy with VGG16 achieving 93.96%, suggesting a promising approach for automated DR screening and aiding healthcare professionals in early and accurate diagnosis. Keywords : Convolutional Neural Network, Diabetic Retinopathy, Visual Geometry Group 16 (VGG16), Visual Geometry Group 19 (VGG19), Transfer Learning, Deep Learning.

Deep Learning for Early Detection of Diabetic Retinopathy: A Colour Fundus Image-based Approach with VGG16 and VGG19

Diabetic retinopathy (DR) is a prevalent complication of diabetes, posing a significant threat to vision. Early detection and intervention are critical to prevent vision loss. However, manual screening of retinal images for DR is time-consuming and susceptible to human error. This study investigates the application of deep learning models, specifically VGG16 and VGG19, for automated DR diagnosis in Colour Fundus images. We evaluate their performance in classifying images as either Diabetic Retinopathy or No Diabetic Retinopathy. Our results demonstrate high testing accuracy with VGG16 achieving 93.96%, suggesting a promising approach for automated DR screening and aiding healthcare professionals in early and accurate diagnosis. Keywords : Convolutional Neural Network, Diabetic Retinopathy, Visual Geometry Group 16 (VGG16), Visual Geometry Group 19 (VGG19), Transfer Learning, Deep Learning.

Acceleration of convolutional neural network based diabetic retinopathy diagnosis system on field programmable gate array

Diabetic retinopathy (DR) is one of the most common causes of blindness. The necessity for a robust and automated DR screening system for regular examination has long been recognized in order to identify DR at an early stage. In this paper, an embedded DR diagnosis system based on convolutional neural networks (CNNs) has been proposed to assess the proper stage of DR. We coupled the power of CNN with transfer learning to design our model based on state-of-the-art architecture. We preprocessed the input data, which is color fundus photography, to reduce undesirable noise in the image. After training many models on the dataset, we chose the adopted ResNet50 because it produced the best results, with a 92.90% accuracy. Extensive experiments and comparisons with other research work show that the proposed method is effective. Furthermore, the CNN model has been implemented on an embedded target to be a part of a medical instrument diagnostic system. We have accelerated our model inference on a field programmable gate array (FPGA) using Xilinx tools. Results have confirmed that a customized FPGA system on chip (SoC) with hardware accelerators is a promising target for our DR detection model with high performance and low power consumption.

Micro-segmentation of retinal image lesions in diabetic retinopathy using energy-based fuzzy C-Means clustering (EFM-FCM).

Diabetic retinopathy (DR) is a prevalent cause of global visual impairment, contributing to approximately 4.8% of blindness cases worldwide as reported by the World Health Organization (WHO). The condition is characterized by pathological abnormalities in the retinal layer, including microaneurysms, vitreous hemorrhages, and exudates. Microscopic analysis of retinal images is crucial in diagnosing and treating DR. This article proposes a novel method for early DR screening using segmentation and unsupervised learning techniques. The approach integrates a neural network energy-based model into the Fuzzy C-Means (FCM) algorithm to enhance convergence criteria, aiming to improve the accuracy and efficiency of automated DR screening tools. The evaluation of results includes the primary dataset from the Shiva Netralaya Centre, IDRiD, and DIARETDB1. The performance of the proposed method is compared against FCM, EFCM, FLICM, and M-FLICM techniques, utilizing metrics such as accuracy in noiseless and noisy conditions and average execution time. The results showcase auspicious performance on both primary and secondary datasets, achieving accuracy rates of 99.03% in noiseless conditions and 93.13% in noisy images, with an average execution time of 16.1 s. The proposed method holds significant potential in medical image analysis and could pave the way for future advancements in automated DR diagnosis and management. RESEARCH HIGHLIGHTS: A novel approach is proposed in the article, integrating a neural network energy-based model into the FCM algorithm to enhance the convergence criteria and the accuracy of automated DR screening tools. By leveraging the microscopic characteristics of retinal images, the proposed method significantly improves the accuracy of lesion segmentation, facilitating early detection and monitoring of DR. The evaluation of the method's performance includes primary datasets from reputable sources such as the Shiva Netralaya Centre, IDRiD, and DIARETDB1, demonstrating its effectiveness in comparison to other techniques (FCM, EFCM, FLICM, and M-FLICM) in terms of accuracy in both noiseless and noisy conditions. It achieves impressive accuracy rates of 99.03% in noiseless conditions and 93.13% in noisy images, with an average execution time of 16.1 s.

Prevalence of glaucomatous-appearing discs in patients undergoing artificial intelligence screening for diabetic retinopathy

PurposeTo determine the prevalence of optic disc changes suspicious for glaucoma (OCSG) which may be overlooked by artificial intelligence-based diabetic retinopathy (DR) screening systems in place of in-person dilated screening exams. MethodsThis was a retrospective cross-sectional study. High-resolution images were retrieved for 677 consecutive automated DR screening exams performed in adult patients. These were reviewed by two blinded readers for evidence of OCSG, which included increased vertical cup-to-disc ratio (VCDR), beta-zone peripapillary atrophy, optic disc hemorrhage, vessel bayoneting, rim thinning, and/or central vessel nasalization. The prevalence of OCSG was reported and compared between subjects designated as referable versus non-referable for DR. ResultsIn total, 823 eyes of 413 subjects were included. The total OCSG prevalence was 4.8% to 20.6%, with no statistically significant difference between patients designated referable versus non-referable on artificial intelligence-based DR screening. The combined classification reliability of the image readers was moderate to substantial compared to a glaucoma specialist. ConclusionsOCSG were detected in 4.8% to 20.6% of adult diabetic patients who underwent AI-based DR screening in our cohort. This represents a significant prevalence of optic disc findings which, if detected on manual screening, would have prompted referral for a glaucoma workup. Such findings illustrate the need for artificial intelligence-based screening platforms which cover multiple high-prevalence ophthalmic conditions. Replacing manual dilated screening exams with systems optimized for a single disease may increase the risk of missing comorbid ocular disease.

A Novel Approach for Diabetic Retinopathy Screening Using Asymmetric Deep Learning Features

Automatic screening of diabetic retinopathy (DR) is a well-identified area of research in the domain of computer vision. It is challenging due to structural complexity and a marginal contrast difference between the retinal vessels and the background of the fundus image. As bright lesions are prominent in the green channel, we applied contrast-limited adaptive histogram equalization (CLAHE) on the green channel for image enhancement. This work proposes a novel diabetic retinopathy screening technique using an asymmetric deep learning feature. The asymmetric deep learning features are extracted using U-Net for segmentation of the optic disc and blood vessels. Then a convolutional neural network (CNN) with a support vector machine (SVM) is used for the DR lesions classification. The lesions are classified into four classes, i.e., normal, microaneurysms, hemorrhages, and exudates. The proposed method is tested with two publicly available retinal image datasets, i.e., APTOS and MESSIDOR. The accuracy achieved for non-diabetic retinopathy detection is 98.6% and 91.9% for the APTOS and MESSIDOR datasets, respectively. The accuracies of exudate detection for these two datasets are 96.9% and 98.3%, respectively. The accuracy of the DR screening system is improved due to the precise retinal image segmentation.

Automatic Screening of Diabetic Retinopathy Using Fundus Images and Machine Learning Algorithms.

Diabetic Retinopathy is a vision impairment caused by blood vessel degeneration in the retina. It is becoming more widespread as it is linked to diabetes. Diabetic retinopathy can lead to blindness. Early detection of diabetic retinopathy by an ophthalmologist can help avoid vision loss and other complications. Diabetic retinopathy is currently diagnosed by visually recognizing irregularities on fundus pictures. This procedure, however, necessitates the use of ophthalmic imaging technologies to acquire fundus images as well as a detailed visual analysis of the stored photos, resulting in a costly and time-consuming diagnosis. The fundamental goal of this project is to create an easy-to-use machine learning model tool that can accurately predict diabetic retinopathy using pre-recorded digital fundus images. To create the suggested classifier model, we gathered annotated fundus images from publicly accessible data repositories and used two machine learning methods, support vector machine (SVM) and deep neural network (DNN). On test data, the proposed SVM model had a mean area under the receiver operating characteristic curve (AUC) of 97.11%, whereas the DNN model had a mean AUC of 99.15%.

Multicenter, Head-to-Head, Real-World Validation Study of Seven Automated Artificial Intelligence Diabetic Retinopathy Screening Systems.

OBJECTIVEWith rising global prevalence of diabetic retinopathy (DR), automated DR screening is needed for primary care settings. Two automated artificial intelligence (AI)–based DR screening algorithms have U.S. Food and Drug Administration (FDA) approval. Several others are under consideration while in clinical use in other countries, but their real-world performance has not been evaluated systematically. We compared the performance of seven automated AI-based DR screening algorithms (including one FDA-approved algorithm) against human graders when analyzing real-world retinal imaging data.RESEARCH DESIGN AND METHODSThis was a multicenter, noninterventional device validation study evaluating a total of 311,604 retinal images from 23,724 veterans who presented for teleretinal DR screening at the Veterans Affairs (VA) Puget Sound Health Care System (HCS) or Atlanta VA HCS from 2006 to 2018. Five companies provided seven algorithms, including one with FDA approval, that independently analyzed all scans, regardless of image quality. The sensitivity/specificity of each algorithm when classifying images as referable DR or not were compared with original VA teleretinal grades and a regraded arbitrated data set. Value per encounter was estimated.RESULTSAlthough high negative predictive values (82.72–93.69%) were observed, sensitivities varied widely (50.98–85.90%). Most algorithms performed no better than humans against the arbitrated data set, but two achieved higher sensitivities, and one yielded comparable sensitivity (80.47%, P = 0.441) and specificity (81.28%, P = 0.195). Notably, one had lower sensitivity (74.42%) for proliferative DR (P = 9.77 × 10−4) than the VA teleretinal graders. Value per encounter varied at $15.14–$18.06 for ophthalmologists and $7.74–$9.24 for optometrists.CONCLUSIONSThe DR screening algorithms showed significant performance differences. These results argue for rigorous testing of all such algorithms on real-world data before clinical implementation.

Performance of deep neural network-based artificial intelligence method in diabetic retinopathy screening: a systematic review and meta-analysis of diagnostic test accuracy.

Automatic diabetic retinopathy screening system based on neural networks has been used to detect diabetic retinopathy (DR). However, there is no quantitative synthesis of performance of these methods. We aimed to estimate the sensitivity and specificity of neural networks in DR grading. Medline, Embase, IEEE Xplore, and Cochrane Library were searched up to 23 July 2019. Studies that evaluated performance of neural networks in detection of moderate or worse DR or diabetic macular edema using retinal fundus images with ophthalmologists' judgment as reference standard were included. Two reviewers extracted data independently. Risk of bias of eligible studies was assessed using QUDAS-2 tool. Twenty-four studies involving 235 235 subjects were included. Quantitative random-effects meta-analysis using the Rutter and Gatsonis hierarchical summary receiver operating characteristics (HSROC) model revealed a pooled sensitivity of 91.9% (95% CI: 89.6% to 94.3%) and specificity of 91.3% (95% CI: 89.0% to 93.5%). Subgroup analyses and meta-regression did not provide any statistically significant findings for the heterogeneous diagnostic accuracy in studies with different image resolutions, sample sizes of training sets, architecture of convolutional neural networks, or diagnostic criteria. State-of-the-art neural networks could effectively detect clinical significant DR. To further improve diagnostic accuracy of neural networks, researchers might need to develop new algorithms rather than simply enlarge sample sizes of training sets or optimize image quality.

Fine-tuning of pre-trained convolutional neural networks for diabetic retinopathy screening: a clinical study

Diabetic retinopathy is a serious complication of diabetes, and if not controlled, may cause blindness. Automated screening of diabetic retinopathy helps physicians to diagnose and control the disease in early stages. In this paper, two case studies are proposed, each on a different dataset. Firstly, automatic screening of diabetic retinopathy utilising pre-trained convolutional neural networks was employed on the Kaggle dataset. The reason for using pre-trained networks is to save time and resources during training compared to fully training a convolutional neural network. The proposed networks were fine-tuned for the pre-processed dataset, and the selectable parameters of the fine-tuning approach were optimised. At the end, the performance of the fine-tuned network was evaluated using a clinical dataset comprising 101 images. The clinical dataset is completely independent from the fine-tuning dataset and is taken by a different device with different image quality and size.

Automatic Diabetic Retinopathy Screening via Cascaded Framework Based on Image- and Lesion-Level Features Fusion

The early detection of diabetic retinopathy is crucial for preventing blindness. However, it is time-consuming to analyze fundus images manually, especially considering the increasing amount of medical images. In this paper, we propose an automatic diabetic retinopathy screening method using color fundus images. Our approach consists of three main components: edge-guided candidate microaneurysms detection, candidates classification using mixed features, and diabetic retinopathy prediction using fused features of image level and lesion level. We divide a screening task into two sub-classification tasks: 1) verifying candidate microaneurysms by a naive Bayes classifier; 2) predicting diabetic retinopathy using a support vector machine classifier. Our approach can effectively alleviate the imbalanced class distribution problem. We evaluate our method on two public databases: Lariboisiere and Messidor, resulting in an area under the curve of 0.908 on Lariboisiere and 0.832 on Messidor. These scores demonstrate the advantages of our approach over the existing methods.

604-P: Automated Diabetic Retinopathy Screening in the Primary Care Setting Improves Compliance with Follow-Up Ophthalmic Care

Purpose: Diabetic retinopathy (DR) is a leading cause of blindness, yet a majority of adults with diabetes are noncompliant with annual ophthalmic screening recommendations. We hypothesized that point-of-care automated DR could increase the rate of compliance with recommended retinal surveillance in patients with diabetes when administered during primary care visits. Methods: We performed a prospective cohort study of adults ages 18 or older with diabetes seen at a primary care clinic from 3/1/18 to 8/31/18. A retrospective chart review of adults with diabetes from the same clinic was also conducted and served as a historical control. Participants were screened using non-mydriatic fundus photography and automated DR screening software (Eyenuk Inc.). Those with positive or inconclusive screening results were referred to ophthalmology for comprehensive evaluation. Rates of compliance with referral recommendations were compared between the study participants and historical control. Results: One hundred and sixty-five adults with diabetes were included in the prospective study cohort. Twelve (7.3%) screened positive for referable DR, 23 (13.9%) screened positive for vision threatening DR, and 47 (28.4%) had an inconclusive screening result. Those that screened negative (83 participants) were all confirmed not to have DR by independent review from a retina specialist. The rate of compliance with follow-up eye care in referred participants was 54.9% compared to a historical rate of 18.7% (p<0.0001, chi-squared). Conclusions: The use of automated DR screening at our institution's primary care clinic reduced referrals for those with no retinopathy and increased the rate of compliance with follow-up eye care in those with positive or inconclusive screening results. These findings suggest that implementation of automated screening could effectively increase compliance with ophthalmic care among those with referable DR. Disclosure J.C. Liu: None. S. Ramchal: None. E. Gibson: None. K. Solanki: Employee; Self; Eyenuk Inc. Stock/Shareholder; Self; Eyenuk Inc. M. Bhaskaranand: Employee; Self; Eyenuk Inc. E. Fondahn: Consultant; Self; Greeley Company. R. Rajagopal: None.

Major automatic diabetic retinopathy screening systems and related core algorithms: a review

Diabetic retinopathy (DR), one of the major and long-term microvascular complications of diabetes, is the most common cause of vision loss and blindness in the working population of the world. Even with the management of diabetes, most patients will develop some forms of DR after approximately 20 years. However, DR is a treatable disease throughout the disease progression. To provide appropriate DR management, the USA and European countries have successfully implemented systematic early DR screening programs. At the same time, some computer-aided DR screening systems, which combine advanced DR detection algorithms and telemedicine technology, have also been developed for early-stage DR detection. Some of them have been tested in the DR screening programs. In this paper, we focus on a review of the major automatic DR screening systems which have performed large-scale evaluation rather than give an extensive review of all published DR grading algorithms. We first present the structures of the automatic systems and their supporting algorithms developed by the research groups, as well as the practices of the systems in their screening programs. We further present a more detailed review of the DR lesion detection algorithms in each system and reveal how the DR screening systems successfully practiced in clinical trials or large-scale screening programs. We also review recently new research areas as well as deep learning-based DR screening systems and compare them with the traditional lesion detection-based DR screening systems. The performances of the systems in the trials are summarized by considering the specificity and sensitivity with respect to the scale of testing datasets. At last, we will discuss future challenges.

Automatic Screening of Diabetic Retinopathy Based on Residual Network

Automatic Screening of Diabetic Retinopathy Based on Residual Network

Automated Diabetic Retinopathy Screening System Using Hybrid Simulated Annealing and Ensemble Bagging Classifier

Diabetic Retinopathy (DR) is the leading cause of blindness in working-age adults globally. Primary screening of DR is essential, and it is recommended that diabetes patients undergo this procedure at least once per year to prevent vision loss. However, in addition to the insufficient number of ophthalmologists available, the eye examination itself is labor-intensive and time-consuming. Thus, an automated DR screening method using retinal images is proposed in this paper to reduce the workload of ophthalmologists in the primary screening process and so that ophthalmologists may make effective treatment plans promptly to help prevent patient blindness. First, all possible candidate lesions of DR were segmented from the whole retinal image using a combination of morphological-top-hat and Kirsch edge-detection methods supplemented by pre- and post-processing steps. Then, eight feature extractors were utilized to extract a total of 208 features based on the pixel density of the binary image as well as texture, color, and intensity information for the detected regions. Finally, hybrid simulated annealing was applied to select the optimal feature set to be used as the input to the ensemble bagging classifier. The evaluation results of this proposed method, on a dataset containing 1200 retinal images, indicate that it performs better than previous methods, with an accuracy of 97.08%, a sensitivity of 90.90%, a specificity of 98.92%, a precision of 96.15%, an F-measure of 93.45% and the area under receiver operating characteristic curve at 98.34%.

Automated Diabetic Retinopathy Screening and Monitoring Using Retinal Fundus Image Analysis.

Diabetic retinopathy (DR)-a common complication of diabetes-is the leading cause of vision loss among the working-age population in the western world. DR is largely asymptomatic, but if detected at early stages the progression to vision loss can be significantly slowed. With the increasing diabetic population there is an urgent need for automated DR screening and monitoring. To address this growing need, in this article we discuss an automated DR screening tool and extend it for automated estimation of microaneurysm (MA) turnover, a potential biomarker for DR risk. The DR screening tool automatically analyzes color retinal fundus images from a patient encounter for the various DR pathologies and collates the information from all the images belonging to a patient encounter to generate a patient-level screening recommendation. The MA turnover estimation tool aligns retinal images from multiple encounters of a patient, localizes MAs, and performs MA dynamics analysis to evaluate new, persistent, and disappeared lesion maps and estimate MA turnover rates. The DR screening tool achieves 90% sensitivity at 63.2% specificity on a data set of 40 542 images from 5084 patient encounters obtained from the EyePACS telescreening system. On a subset of 7 longitudinal pairs the MA turnover estimation tool identifies new and disappeared MAs with 100% sensitivity and average false positives of 0.43 and 1.6 respectively. The presented automated tools have the potential to address the growing need for DR screening and monitoring, thereby saving vision of millions of diabetic patients worldwide.

An Automated Detection System for Microaneurysms That Is Effective across Different Racial Groups.

Patients without diabetic retinopathy (DR) represent a large proportion of the caseload seen by the DR screening service so reliable recognition of the absence of DR in digital fundus images (DFIs) is a prime focus of automated DR screening research. We investigate the use of a novel automated DR detection algorithm to assess retinal DFIs for absence of DR. A retrospective, masked, and controlled image-based study was undertaken. 17,850 DFIs of patients from six different countries were assessed for DR by the automated system and by human graders. The system's performance was compared across DFIs from the different countries/racial groups. The sensitivities for detection of DR by the automated system were Kenya 92.8%, Botswana 90.1%, Norway 93.5%, Mongolia 91.3%, China 91.9%, and UK 90.1%. The specificities were Kenya 82.7%, Botswana 83.2%, Norway 81.3%, Mongolia 82.5%, China 83.0%, and UK 79%. There was little variability in the calculated sensitivities and specificities across the six different countries involved in the study. These data suggest the possible scalability of an automated DR detection platform that enables rapid identification of patients without DR across a wide range of races.

Beyond Lesion-Based Diabetic Retinopathy: A Direct Approach for Referral.

Diabetic retinopathy (DR) is the leading cause of blindness in adults, but can be managed if detected early. Automated DR screening helps by indicating which patients should be referred to the doctor. However, current techniques of automated screening still depend too much on the detection of individual lesions. In this study, we bypass lesion detection, and directly train a classifier for DR referral. Additional novelties are the use of state-of-the-art mid-level features for the retinal images: BossaNova and Fisher Vector. Those features extend the classical Bags of Visual Words and greatly improve the accuracy of complex classification tasks. The proposed technique for direct referral is promising, achieving an area under the curve of 96.4%, thus, reducing the classification error by almost40% over the current state of the art, held by lesion-based techniques.

Computer-aided diabetic retinopathy detection using trace transforms on digital fundus images.

Diabetic retinopathy (DR) is a leading cause of vision loss among diabetic patients in developed countries. Early detection of occurrence of DR can greatly help in effective treatment. Unfortunately, symptoms of DR do not show up till an advanced stage. To counter this, regular screening for DR is essential in diabetic patients. Due to lack of enough skilled medical professionals, this task can become tedious as the number of images to be screened becomes high with regular screening of diabetic patients. An automated DR screening system can help in early diagnosis without the need for a large number of medical professionals. To improve detection, several pattern recognition techniques are being developed. In our study, we used trace transforms to model a human visual system which would replicate the way a human observer views an image. To classify features extracted using this technique, we used support vector machine (SVM) with quadratic, polynomial, radial basis function kernels and probabilistic neural network (PNN). Genetic algorithm (GA) was used to fine tune classification parameters. We obtained an accuracy of 99.41 and 99.12% with PNN-GA and SVM quadratic kernels, respectively.

An ensemble-based system for automatic screening of diabetic retinopathy

In this paper, an ensemble-based method for the screening of diabetic retinopathy (DR) is proposed. This approach is based on features extracted from the output of several retinal image processing algorithms, such as image-level (quality assessment, pre-screening, AM/FM), lesion-specific (microaneurysms, exudates) and anatomical (macula, optic disk) components. The actual decision about the presence of the disease is then made by an ensemble of machine learning classifiers. We have tested our approach on the publicly available Messidor database, where 90% sensitivity, 91% specificity and 90% accuracy and 0.989 AUC are achieved in a disease/no-disease setting. These results are highly competitive in this field and suggest that retinal image processing is a valid approach for automatic DR screening.