A Hybrid Machine Learning Strategy Assisted Diabetic Retinopathy Detection based on Retinal Images

2021 ◽  
Author(s):  
R. Kiran Kumar ◽  
K. Arunabhaskar
Keyword(s):  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Learning Strategy ◽  
Retinal Images ◽  
Hybrid Machine

scholarly journals Hybrid machine learning architecture for automated detection and grading of retinal images for diabetic retinopathy

2020 ◽  
Vol 7 (03) ◽  
pp. 1
Author(s):  
Barath Narayanan Narayanan ◽  
Russell C. Hardie ◽  
Manawaduge Supun De Silva ◽  
Nathaniel K. Kueterman
Keyword(s):  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Automated Detection ◽  
Retinal Images ◽  
Hybrid Machine

scholarly journals A Machine Learning Approach for the Diagnosis of Diabetes : A Review

2020 ◽  
pp. 509-516
Author(s):  
Pravin S. Rahate ◽  
Nikhat Raza
Keyword(s):  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Selection Process ◽  
High Sensitivity ◽  
Healthcare Services ◽  
Automated System ◽  
Retinal Images ◽  
Number Of Patients ◽  
Machine Learning Approach ◽  
Patients With Diabetes

Diabetes mellitus (DM) is a chronic disease that affects 382 million patients’ worldwide (2013 data) and is predicted to increase to as many as 592 million adults by 2035. DM is one of the major causes of blindness in young adults around the world. The most serious ocular complication of DM is diabetic retinopathy (DR).Diabetic retinopathy is the most common microvascular complication in diabetes1, for the screening of which the retinal imaging is the most widely used method due to its high sensitivity in detecting retinopathy. Prompt diagnosis is important through efficient screening. The evaluation of the severity and degree of retinopathy associated with a person having diabetes is currently performed by medical experts based on the fundus or retinal images of the patient’s eyes As the number of patients with diabetes is rapidly increasing, the number of retinal images produced by the screening programmes will also increase, which in turn introduces a large labor-intensive burden on the medical experts as well as cost to the healthcare services. Manual grading of these images to determine the severity of DR is rather slow and resource demanding. This could be alleviated with an automated system either as support for medical experts’ work or as full diagnosis tool. This labor-intensive task could greatly benefit from automatic detection using machine learning technique. Early detection and timely treatment have been shown to prevent visual loss and blindness in patients with retinal complications of diabetes. Machine learning in recent years has been the evolving, reliable and supporting tools in medical domain and has provided the greatest support for predicting disease with correct case of training and testing. The objective of this paper is to explore the work happening on the detection, progression and feature selection process for the prediction of DR and to establish the extent and depth of existing knowledge on RD prediction process.

scholarly journals Improving Diabetic Diagnosis and Prevention with Machine Learning on Retinal Imaging

2021 ◽  
Vol 271 ◽  
pp. 01034
Author(s):  
Yushan Min
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Diabetic Retinopathy ◽  
Learning Algorithms ◽  
Area Under The Curve ◽  
Retinal Imaging ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Retinal Images ◽  
Support Vector Machine Algorithm

If the retinal images show evidences of abnormalities such as change in volume, diameter, and unusual spots in the retina, then there is a positive correlation to the diabetic progress. Mathematical and statistical theories behind the machine learning algorithms are powerful enough to detect signs of diabetes through retinal images. Several machine learning algorithms: Logistic Regression, Support Vector Machine, Random Forest, and Neural Networks were applied to predict whether images contain signs of diabetic retinopathy or not. After building the models, the computed results of these algorithms were compared by confusion matrixes, receiver operating characteristic curves, and Precision-Recall curves. The performance of the Support Vector Machine algorithm was the best since it had the highest true-positive rate, area under the curve for ROC curve, and area under the curve for Precision-Recall curve. This conclusion shows that the most complex algorithms doesn’t always give the best performance, the final accuracy also depends on the dataset. For this dataset of retinal imaging, the Support Vector Machine algorithm achieved the best results. Detecting signs of diabetic retinopathy is helpful for detecting for diabetes since more than 60% of patients with diabetes have signs of diabetic retinopathy. Machine learning algorithms can speed up the process and improve the accuracy of diagnosis. When the method is reliable enough, it can be utilized in diabetes diagnosis directly in clinics. Current methods require going on diets and taking blood samples, which could be very time consuming and inconvenient. Using machine learning algorithms is fast and noninvasive compared to the existing methods. The purpose of this research was to build an optimized model by machine learning algorithms that can improve the diagnosis accuracy and classification of patients at high risk of diabetes using retinal imaging.

scholarly journals Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients

2020 ◽  
pp. bjophthalmol-2020-316594 ◽  
Author(s):  
Peter Heydon ◽  
Catherine Egan ◽  
Louis Bolter ◽  
Ryan Chambers ◽  
John Anderson ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Large Scale ◽  
Proliferative Retinopathy ◽  
Retinal Images ◽  
Technical Failure ◽  
Reference Standard ◽  
Diabetic Retinopathy Screening ◽  
Diabetic Eye Screening

Background/aimsHuman grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of diabetes. We evaluate the performance of an automated artificial intelligence (AI) algorithm to triage retinal images from the English Diabetic Eye Screening Programme (DESP) into test-positive/technical failure versus test-negative, using human grading following a standard national protocol as the reference standard.MethodsRetinal images from 30 405 consecutive screening episodes from three English DESPs were manually graded following a standard national protocol and by an automated process with machine learning enabled software, EyeArt v2.1. Screening performance (sensitivity, specificity) and diagnostic accuracy (95% CIs) were determined using human grades as the reference standard.ResultsSensitivity (95% CIs) of EyeArt was 95.7% (94.8% to 96.5%) for referable retinopathy (human graded ungradable, referable maculopathy, moderate-to-severe non-proliferative or proliferative). This comprises sensitivities of 98.3% (97.3% to 98.9%) for mild-to-moderate non-proliferative retinopathy with referable maculopathy, 100% (98.7%,100%) for moderate-to-severe non-proliferative retinopathy and 100% (97.9%,100%) for proliferative disease. EyeArt agreed with the human grade of no retinopathy (specificity) in 68% (67% to 69%), with a specificity of 54.0% (53.4% to 54.5%) when combined with non-referable retinopathy.ConclusionThe algorithm demonstrated safe levels of sensitivity for high-risk retinopathy in a real-world screening service, with specificity that could halve the workload for human graders. AI machine learning and deep learning algorithms such as this can provide clinically equivalent, rapid detection of retinopathy, particularly in settings where a trained workforce is unavailable or where large-scale and rapid results are needed.

scholarly journals A Comparative Study on Diabetic Retinopathy Detection Using Texture-Based Feature Extraction Techniques

Ophthalmology ◽  
2018 ◽  
pp. 122-152
Author(s):  
Azam Asilian Bidgoli ◽  
Hossein Ebrahimpour-Komleh ◽  
Seyed Jalaleddin Mousavirad
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Feature Extraction ◽  
Diabetic Retinopathy ◽  
Decision Support ◽  
Support System ◽  
Low Vision ◽  
Extraction Methods ◽  
Retinal Images ◽  
Eye Disorders

Diabetic retinopathy is proved to be one of the most important eye disorders in recent decades that late diagnosis of it may cause low vision or even blindness. Specialist are able to detect retinopathy in retinal images using machine learning as a decision support system which helps accelerate and facilitate the diagnosis. The automated diabetic retinopathy is a difficult computer vision problem –with the goal of detecting features of retinopathy. The present chapter is written with the purpose of analyzing and comparing different feature extraction methods to evaluate the best algorithm for detection retinopathy with least error. Extracted features using these methods are used to classify images into normal and altered groups.

scholarly journals Effective Procedure to Predict Rainfall Conditions using Hybrid Machine Learning Strategies

2021 ◽  
Vol 12 (6) ◽  
pp. 209-216
Author(s):  
S.Sakthivel Et.al
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Learning Strategies ◽  
Learning Strategy ◽  
Human Life ◽  
Machine Learning Algorithms ◽  
Rainfall Prediction ◽  
Long Period ◽  
Hybrid Machine ◽  
Limited Period

In the present information technology stream supports many natural disaster prediction schemes to save several people from disaster scenarios. In such case, rainfall prediction and analysis is the most important concern to take care as well as the prediction of high rainfall saves many individual's life and their assets. This kind of rainfall prediction schemes provides a facilitation to take respective precautions to avoid huge damages further. The rainfall predictions are categorized into two different variants such as Limited Period Rainfall Prediction and the long period Continuous Rainfall Prediction. Several past analysis and literatures provide accurate predictions for limited period rainfall but the major problem is to identify or predict the continuous long period rainfall. This kind of drawbacks leads many researchers to work on this domain and predict the rainfall status exactly for both limited period as well as long period continues rainfall. In this paper, a new hybrid machine learning strategy is implemented to predict the rainfall status exactly, in which the proposed methodology is named as Intense Neural Network Mining (INNM). This proposed approach of INNM analyze the rainfall prediction scenario based on two different machine learning logics such as Back Propagation Neural Network and the Rapid Miner. The general machine learning algorithms train the machine with respect to the dataset features and predict the result based on testing input. In this approach two different variants of machine learning principles are utilized to classify the resulting nature with better accuracy levels and cross-validations are providing best probabilistic results in outcome. And these two logics are integrated together to produce a new hybrid machine learning strategy to predict the rainfall status exactly and save human life against disasters. In this paper, a novel dataset is utilized from Regional Meteorological Centre Chennai to predict the rainfall summary in clear manner and the summarization of specific dataset is described on further sections. The proposed approach of INNM assures the resulting accuracy levels around 96.5% in prediction with lowest error ratio of 0.04% and the resulting portion of this paper provides a proper proof of this outcome in graphical manner.

A Comparative Study on Diabetic Retinopathy Detection Using Texture-Based Feature Extraction Techniques

2017 ◽  
pp. 242-271
Author(s):  
Azam Asilian Bidgoli ◽  
Hossein Ebrahimpour-Komleh ◽  
Seyed Jalaleddin Mousavirad
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Feature Extraction ◽  
Diabetic Retinopathy ◽  
Decision Support ◽  
Support System ◽  
Low Vision ◽  
Extraction Methods ◽  
Retinal Images ◽  
Eye Disorders

Diabetic retinopathy is proved to be one of the most important eye disorders in recent decades that late diagnosis of it may cause low vision or even blindness. Specialist are able to detect retinopathy in retinal images using machine learning as a decision support system which helps accelerate and facilitate the diagnosis. The automated diabetic retinopathy is a difficult computer vision problem –with the goal of detecting features of retinopathy. The present chapter is written with the purpose of analyzing and comparing different feature extraction methods to evaluate the best algorithm for detection retinopathy with least error. Extracted features using these methods are used to classify images into normal and altered groups.

scholarly journals Diabetic Retinopathy Detection System

2021 ◽  
Vol 9 (9) ◽  
pp. 1498-1502
Author(s):  
Manisha Gangesh
Keyword(s):  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Proliferative Diabetic Retinopathy ◽  
Web Application ◽  
Detection System ◽  
Retinal Images ◽  
Learning Approaches ◽  
Keywords Diabetic Retinopathy ◽  
Machine Learning Model ◽  
User Friendly

Abstract: Diabetic Retinopathy is a diabetes problem that affects the eye. Injury to the blood vessels of the light sensitive tissue inside the rear of the eye (retina) is that the most reason for diabetic retinopathy. To begin with, Diabetic Retinopathy may have no symptoms or just cause minor vision problems. It has the potential to lead to blindness. Machine learning approaches can be used for the early detection of Diabetic Retinopathy. This paper proposes an automated Diabetic Retinopathy detection system that can detect the presence of Diabetic Retinopathy from retinal images. This work uses ResNet50 for the detection and classification of Diabetic Retinopathy. ResNet50 is a type of neural network used as a backbone for many computer-vision tasks. This paper proposes a machine learning model which is developed using ResNet50, then the model will be deployed as a user-friendly web application where the user can upload the retinal images as input to the system then system will detect the presence of Diabetic Retinopathy and classifies it into the stage or class which the particular image belongs to. Keywords: Diabetic Retinopathy, ResNet50, Proliferative diabetic retinopathy, non-proliferative diabetic retinopathy.

Sign in / Sign up

Export Citation Format

Share Document