Automated DR and prediction of various related diseases of retinal fundus images

Sumathy, B.; Poornachandra, S.

doi:10.4066/biomedicalresearch.29-17-480

Cited by 4 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural Network for Detection of Diabetic Retinopathy. 1) "B. Sumathy" et al [2] describes the abnormal features in the fundus images with the performance approaching that of trained clinical observer. A novel combination of image preprocessing technique for retinal anatomical structures and classification with machine learning is a computer based which extracts abnormal features such as micro aneurysms, exudates, hemorrhages and new vessels etc.…”

Section: Bmentioning

confidence: 99%

Detection of Retinal Blood Vessels for Disease Prediction using Machine Learning

Wagh¹

2019

IJRASET

View full text Add to dashboard Cite

Retinal diseases like glaucoma, diabetic retinopathy, age-related macular degeneration, stargardt's disease, retinopathy of prematurity that can lead to blindness manifest as artifacts in the retinal image. The term Diabetic retinopathy is the serious issue that is caused by the diabetes, which affects the eyes and results in blindness. It's due to damage of the arteries and veins that are present in the fundus of the eye (retina) that is the origin of light sensitive tissues. Although DR can be prevalent now days, its prevention remains challenging. Visual analysis of the funds and consideration of color photographs Ophthalmologists directly examine the existence and severity of DR. This process is expensive as well as time consuming as there are huge number of diabetes patients worldwide. The automatic DR system is expanded to predict various related diseases that are analyzed.

show abstract

Section: Bmentioning

confidence: 99%

Detection of Retinal Blood Vessels for Disease Prediction using Machine Learning

Wagh¹

2019

IJRASET

View full text Add to dashboard Cite

show abstract

“…Adalarasan, et alPortrays a system utilizing versatile channels separated in green channel of the picture [10].Approach 3 is based on Neural Network for Detection of Diabetic Retinopathy:Xiyang Liu, et al Talk about a strategy dependent on PC vision for the electronic determination of slit lamp images [11]. B. Sumathy et al Indicate for what is abnormal in the fundus pictures with picture preprocessing procedure and grouping with AI [12]. Approach 4 is based on Computer Aided Diagnosis System For Diabetic Retinopathy: Mike Voets, et al Replication thinks about are identified with finding of diabetic retinopathy in fundus photos.…”

Section: Literature Surveymentioning

confidence: 99%

Diabetic Retinopathy, An Eye Disease Prediction System using Convolutional Neural Network

Mutha¹

2019

IJRASET

View full text Add to dashboard Cite

Diabetic Retinopathy" is the certifiable issue that is made by the diabetes and there are enormous number of diabetes patients worldwide, which impact the vision and results in visual deficiency and DR happens because of harm of the corridors and veins that are available in the fundus of the eye retina and its avoidance stays testing. Fundus pictures assume a principal job for the examination of DR. With the visual investigation of the fundus pictures and thought of shading photos, Ophthalmologists specifically inspect the presence and seriousness of DR. This procedure turns out to be expensive and time engaging. The framework for forecast of Diabetic Retinopathy is being proposed and is for the examination of fundus picture by dissecting its area of premium and applying convolutional neural network for order of the fundus pictures and to create and send a mechanized examination programming for ophthalmologists and patients in clinical applications, which thusly will accelerate the task and make it more affordable.

show abstract

Performance and Limitation of Machine Learning Algorithms for Diabetic Retinopathy Screening: Meta-analysis

Wu¹,

Liu²,

Hsu³

et al. 2021

J Med Internet Res

View full text Add to dashboard Cite

Background Diabetic retinopathy (DR), whose standard diagnosis is performed by human experts, has high prevalence and requires a more efficient screening method. Although machine learning (ML)–based automated DR diagnosis has gained attention due to recent approval of IDx-DR, performance of this tool has not been examined systematically, and the best ML technique for use in a real-world setting has not been discussed. Objective The aim of this study was to systematically examine the overall diagnostic accuracy of ML in diagnosing DR of different categories based on color fundus photographs and to determine the state-of-the-art ML approach. Methods Published studies in PubMed and EMBASE were searched from inception to June 2020. Studies were screened for relevant outcomes, publication types, and data sufficiency, and a total of 60 out of 2128 (2.82%) studies were retrieved after study selection. Extraction of data was performed by 2 authors according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses), and the quality assessment was performed according to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Meta-analysis of diagnostic accuracy was pooled using a bivariate random effects model. The main outcomes included diagnostic accuracy, sensitivity, and specificity of ML in diagnosing DR based on color fundus photographs, as well as the performances of different major types of ML algorithms. Results The primary meta-analysis included 60 color fundus photograph studies (445,175 interpretations). Overall, ML demonstrated high accuracy in diagnosing DR of various categories, with a pooled area under the receiver operating characteristic (AUROC) ranging from 0.97 (95% CI 0.96-0.99) to 0.99 (95% CI 0.98-1.00). The performance of ML in detecting more-than-mild DR was robust (sensitivity 0.95; AUROC 0.97), and by subgroup analyses, we observed that robust performance of ML was not limited to benchmark data sets (sensitivity 0.92; AUROC 0.96) but could be generalized to images collected in clinical practice (sensitivity 0.97; AUROC 0.97). Neural network was the most widely used method, and the subgroup analysis revealed a pooled AUROC of 0.98 (95% CI 0.96-0.99) for studies that used neural networks to diagnose more-than-mild DR. Conclusions This meta-analysis demonstrated high diagnostic accuracy of ML algorithms in detecting DR on color fundus photographs, suggesting that state-of-the-art, ML-based DR screening algorithms are likely ready for clinical applications. However, a significant portion of the earlier published studies had methodology flaws, such as the lack of external validation and presence of spectrum bias. The results of these studies should be interpreted with caution.

show abstract

Automated DR and prediction of various related diseases of retinal fundus images

Cited by 4 publications

References 16 publications

Detection of Retinal Blood Vessels for Disease Prediction using Machine Learning

Detection of Retinal Blood Vessels for Disease Prediction using Machine Learning

Diabetic Retinopathy, An Eye Disease Prediction System using Convolutional Neural Network

Performance and Limitation of Machine Learning Algorithms for Diabetic Retinopathy Screening: Meta-analysis

Contact Info

Product

Resources

About