scholarly journals A Novel Approach for Detection of Optic Disc and Lesion Location for Screening Diabetic Retinopathy

2021 ◽  
Vol 16 (4) ◽  
pp. 1-21
Author(s):  
Aakanksha Mahajan ◽  
Vasudha Vashisht ◽  
Rohit Bansal
Keyword(s):  
Diabetic Retinopathy ◽  
Signs And Symptoms ◽  
Rational Approach ◽  
Retinal Images ◽  
Diabetic Patients ◽  
Nearest Neighbour ◽  
Lesion Location ◽  
Novel Approach ◽  
Initial Stage ◽  
Bright Lesions

Diabetic Retinopathy is not typically perceivable in diabetic patients at the initial stage. Their first signs, like micro-aneurysms, often go unnoticed in preliminary testing by specialists. Additionally, its presence is difficult to detect as there are other pathologies that may also lead to induce similar signs and symptoms. Until the detection of the presence of exudates, a specialist cannot simply deduce the presence of diabetic retinopathy. This paper presents a method to assist in the identification and differentiation of exudates on colour retinal images based on a variety of k-nearest neighbour filters. The proposed method proved to be a rational approach to detect bright lesions with sufficient certainty, yielding a possible injury with a specificity of 99%.

Detection of Diabetic Maculopathy Using KNN Algorithm

2014 ◽  
Vol 573 ◽  
pp. 791-796 ◽  
Author(s):  
R. Sukanesh ◽  
S. Murugeswari
Keyword(s):  
Decision Making ◽  
Vision Loss ◽  
Eye Disease ◽  
Retinal Images ◽  
Diabetic Patients ◽  
Diabetic Maculopathy ◽  
Small Blood Vessel ◽  
Knn Classifier ◽  
Initial Stage ◽  
High Glucose Level

: Diabetic Maculopathy (DM), the most common eye disease of the diabetic patients, arises once a small blood vessel gets impaired in the macula, due to high glucose level. It affects the patients who have diabetes for more than 5 years, which can also prime to vision loss. Recognition of diabetic maculoathy in advance, protects patients from vision loss. The major symptom of diabetic maculopathy is the presence of any lesions. Detecting macula diseases in an initial stage, supports the ophthalmologists apply accurate treatments that might eliminate the disease or decrease the severity of it. This paper focuses diabetic maculopathy identification through detecting lesions by extracting features through GLCM in colour fundus retinal images and also classifies the meticulousness of the lesions. Decision making of the harshness level of the infection was performed by KNN classifier

scholarly journals SUN-686 Diabetic Retinopathy in Latinos with Type 2 Diabetes: Temperance Is Protective

2020 ◽  
Vol 4 (Supplement_1) ◽  
Author(s):  
Alex Fukunaga ◽  
Pauline Genter ◽  
Eli Ipp
Keyword(s):  
Diabetic Retinopathy ◽  
Alcohol Consumption ◽  
Alcohol Intake ◽  
Retinal Images ◽  
Diabetic Patients ◽  
Renal Protection ◽  
Type 2 Diabetic Patients ◽  
Type 2 Dm ◽  
Lower Alcohol

Abstract Diabetic retinopathy (DR) is a duration-dependent complication of diabetes (DM). Yet some people with DM do not develop DR despite long disease duration. We evaluated such a group in search of novel factors that might signal protection from DR, using a large cohort of Latinos with type 2 DM and readable retinal images in the GOLDR study (n=614). Participants were phenotyped and 7-field retinal images were evaluated using Airlie House criteria. We identified 90 participants with DM>10y without evidence for DR (NoDR). We compared this group of patients with another group more susceptible to DR with evidence for earlier onset DR, in DM <10y duration (EoDR, n=103). Duration of diabetes in NoDR was [x+SEM] 14.2+ 0.6y, and in EoDR, 4.3+ 2.9 y (p<0.001), a 10-y spread. We found that most of the typical DR-associated risk factors could not explain DR protection in NoDR, including age, sex, age at DM onset, systolic blood pressure (SBP), percent insulin users, duration of hypertension, fasting plasma glucose, A1C, urine albumin/creatinine ratio and estimate glomerular filtration rate; these parameters were not significantly different in the two groups. Protective factors that did emerge were female sex (p=0.02), lower diastolic BP 69.1+0.9 vs. 72.5+0.9 (p<0.01) and lower alcohol intake 3.1+0.8 vs. 7.8+2 de/w (14g drink equivalents/week; p=0.025). In a sensitivity analysis to determine whether sex accounted for the apparent effect of alcohol on DR, we evaluated the men in the study, who were more likely to be drinkers. Alcohol consumption was compared in men with DR who reported drinking alcohol (n=93) compared to men without DR who also reported drinking (n=53). Men without DR reported significantly less alcohol intake, 14.8+2.4 vs. 25.9 +3.3 de/w in those with DR (P<0.01), suggesting that a possible protective benefit of lower alcohol consumption observed in NoDR was not likely to be mediated by the presence of fewer men in that cohort. In summary, type 2 diabetic patients with no evidence of DR after 10y were more likely to be women, have a lower diastolic BP, and who imbibed less alcohol when compared with a more accelerated DR subgroup with <10yrs duration of DM. We conclude that in type 2 DM Latino patients, a focus on alcohol intake may be a useful management strategy in addition to traditional medication-based BP control and renal protection, as well as a pathophysiological pathway for DR worthy of investigation.

scholarly journals Enhanced CAE system for detection of exudates and diagnosis of diabetic retinopathy stages in fundus retinal images using soft computing techniques

2019 ◽  
Vol 25 (2) ◽  
pp. 131-139
Author(s):  
Sathya D Janaki ◽  
K Geetha
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Retinal Image ◽  
Visual Analysis ◽  
Support Vector ◽  
Retinal Images ◽  
Computer Assisted ◽  
Diabetic Patients ◽  
Soft Computing Techniques ◽  
Cae System

Abstract Diabetic Retinopathy (DR) is one of the leading causes of visual impairment. Diabetic Retinopathy is the most recent technique of identifying the intensity of acid secretion in the eye for diabetic patients. The identification of DR is performed by visual analysis of retinal images for exudates (fat deposits) and the main patterns are traced by ophthalmologists. This paper proposes a fully automated Computer Assisted Evaluation (CAE) system which comprises of a set of algorithms for exudates detection and to classify the different stages of Diabetics Retinopathy, which are identified as either normal or mild or moderate or severe. Experimental validation is performed on a real fundus retinal image database. The segmentation of exudates is achieved using fuzzy C-means clustering and entropy filtering. An optimal set obtained from the statistical textural features (GLCM and GLHM) is extracted from the segmented exudates for classifying the different stages of Diabetics Retinopathy. The different stages of Diabetic Retinopathy are classified using three classifiers such as Back Propagation Neural Network (BPN), Probabilistic Neural Network (PNN) and Support Vector Machine (SVM). The experimental results show that the SVM classifiers outperformed other classifiers for the examined fundus retinal image dataset. The results obtained confirm that with new a set of texture features, the proposed methodology provides better performance when compared to the other methods available in the literature. These results suggest that our proposed method in this paper can be useful as a diagnostic aid system for Diabetic Retinopathy.

scholarly journals A deep learning approach based on stochastic gradient descent and least absolute shrinkage and selection operator for identifying diabetic retinopathy

2022 ◽  
Vol 25 (1) ◽  
pp. 589
Author(s):  
Thirumalaimuthu Thirumalaiappan Ramanathan ◽  
Md. Jakir Hossen ◽  
Md. Shohel Sayeed ◽  
Joseph Emerson Raja
Keyword(s):  
Diabetic Retinopathy ◽  
Retinal Image ◽  
Gradient Descent ◽  
Research Work ◽  
Stochastic Gradient ◽  
Stochastic Gradient Descent ◽  
Retinal Images ◽  
Computational Techniques ◽  
Diabetic Patients ◽  
Selection Operator

More than eighty-five to ninety percentage of the diabetic patients are affected with diabetic retinopathy (DR) which is an eye disorder that leads to blindness. The computational techniques can support to detect the DR by using the retinal images. However, it is hard to measure the DR with the raw retinal image. This paper proposes an effective method for identification of DR from the retinal images. In this research work, initially the Weiner filter is used for preprocessing the raw retinal image. Then the preprocessed image is segmented using fuzzy c-mean technique. Then from the segmented image, the features are extracted using grey level co-occurrence matrix (GLCM). After extracting the fundus image, the feature selection is performed stochastic gradient descent, and least absolute shrinkage and selection operator (LASSO) for accurate identification during the classification process. Then the inception v3-convolutional neural network (IV3-CNN) model is used in the classification process to classify the image as DR image or non-DR image. By applying the proposed method, the classification performance of IV3-CNN model in identifying DR is studied. Using the proposed method, the DR is identified with the accuracy of about 95%, and the processed retinal image is identified as mild DR.

scholarly journals Regular Chinese Green Tea Consumption Is Protective for Diabetic Retinopathy: A Clinic-Based Case-Control Study

2015 ◽  
Vol 2015 ◽  
pp. 1-7 ◽  
Author(s):  
Qinghua Ma ◽  
Dandan Chen ◽  
Hong-Peng Sun ◽  
Ning Yan ◽  
Yong Xu ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Green Tea ◽  
Case Control Study ◽  
Case Control ◽  
Diabetic Patients ◽  
Tea Consumption ◽  
Crude Odds Ratio ◽  
Family History Of Diabetes ◽  
Novel Approach ◽  
Control Study

Objective.To determine the association between regular Chinese green tea consumption and the risk of diabetic retinopathy (DR) in diabetic patients in China.Methods.100 DR patients and 100 age-sex-matched diabetic controls without retinopathy were recruited in a clinic-based, case-control study. DR was defined from retinal photographs and detailed information on Chinese green tea consumption of the participants was collected through a face-to-face interview.Results.The crude odds ratio [OR] of Chinese green tea consumption for DR was 0.49 (95% confidence interval: 0.26–0.90). When stratified by sex, the protective effect of Chinese green tea consumption on DR was statistically significant in women (P=0.01) but not in men (P=0.63). After adjusting for age, sex, and other confounders, DR was significantly associated with Chinese green tea consumption (OR = 0.48;P=0.04), higher systolic blood pressure (OR = 1.02;P=0.05), longer duration of diabetes (OR = 1.07;P=0.02), and the presence of family history of diabetes (OR = 2.35;P=0.04).Conclusions.Diabetic patients who had regularly drunk Chinese green tea every week for at least one year in their lives had a DR risk reduction of about 50% compared with those who had not. Regular Chinese green tea consumption may be a novel approach for the prevention of DR.

scholarly journals Enhanced Detection of Diabetic Retinopathy using Advanced Filters

2019 ◽  
Vol 9 (2) ◽  
pp. 4470-4474
Keyword(s):  
Diabetic Retinopathy ◽  
Blood Vessel ◽  
Patient Information ◽  
Image Features ◽  
Retinal Images ◽  
Diabetic Patients ◽  
Local Entropy ◽  
Vessel Extraction ◽  
The Many ◽  
Short Time

Nowadays in India, diabetic patients are more increasing. The major issue with diabetic patients is Diabetic retinopathy which causes the loss of vision. For the ophthalmologist, it is very difficult to identify the diabetic retinopathy because of the low resolution of the eyes. For the specialists, it is easy to find the blood vessels in the retina to diagnose the many populations in a very short time. Various existing methods are used to find the abnormal retinal images of diabetic patients based on their image features. But the results are not that much accurate. In this paper, an enhanced image filter with local entropy thresholding for blood vessel extraction under different normal or abnormal conditions is proposed to improve the performance of the patient information.

scholarly journals Diabetic Retinopathy Detection Using Walter-Klein Contrast Enhancement

2018 ◽  
Vol 2 (3) ◽  
Keyword(s):  
Diabetic Retinopathy ◽  
Developed Countries ◽  
Lesion Detection ◽  
Eye Disease ◽  
Retinal Images ◽  
Diabetic Patients ◽  
Multiple Classifiers ◽  
Retinal Lesion ◽  
The Developed Countries ◽  
Screening Systems

When sugar level (glucose) in the blood fails to regulate the insulin properly in human body, diabetic is occurred. The effect of diabetic on eye causes diabetic retinopathy. Diabetic retinopathy (DR) is a serious eye disease that originates from diabetes mellitus and is the most common cause of blindness in the developed countries. Therefore, much effort has been made to establish reliable computer aided screening systems based on color fund us images. Diabetic Retinopathy is one of a complicated diabetes which can cause blindness. It is a metabolic disordered patients perceive no symptoms until the disease is at late stage. So early detection and proper treatment has to be ensured. To serve this purpose, various automated systems have been designed. We propose an ensemble-based framework for retinal lesion detection. Unlike the well-known approach of considering the output of multiple classifiers, we propose a combination of of Retinal Lesion detectors, namely preprocessing methods and candidate extractors. The presence of micro aneurysms in the eye is one of the early signs of diabetic retinopathy. We analzye the input retinal images of the Diabetic patients and we can classify that the patient is affected by DR or not. If not affected, they are normal patient. If they are affected, further it classifies the different stages of diabetic retinopathy affected patients such as Mild, Moderate and Severe.

scholarly journals Diabetic Retinopathy Detection

2020 ◽  
Vol 9 (4) ◽  
pp. 1022-1026
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Diabetic Retinopathy ◽  
Deep Learning ◽  
The Other ◽  
Retinal Images ◽  
Diabetic Patients ◽  
Learning Technique ◽  
Prevalent Disease ◽  
Surprising Fact

Diabetic retinopathy is becoming a more prevalent disease in diabetic patients nowadays. The surprising fact about the disease is it leaves no symptoms at the beginning stage and the patient can realize the disease only when his vision starts to fall. If the disease is not found at the earliest it leads to a stage where the probability of curing the disease is less. But if we find the disease at that stage, the patient might be in a situation of losing the vision completely. Hence, this paper aims at finding the disease at the earliest possible stage by extracting two features from the retinal image namely Microaneurysms which is found to be the starting symptom showing feature and Hemorrhage which shows symptoms of the other stages. Based on these two features we classify the stage of the disease as normal, beginning, mild and severe using convolutional neural network, a deep learning technique which reduces the burden of manual feature extraction and gives higher accuracy. We also locate the position of these features in the disease affected retinal images to help the doctors offer better medical treatment.

EFFICIENT DETECTION OF MICRO-ANEURYSMS IN RETINAL IMAGES FOR EARLY DIAGNOSIS OF DIABETIC RETINOPATHY

2017 ◽  
Vol 17 (08) ◽  
pp. 1750108 ◽  
Author(s):  
A. FEROUI ◽  
M. MESSADI ◽  
A. LAZOUNI ◽  
A. BESSAID
Keyword(s):  
Diabetic Retinopathy ◽  
Early Diagnosis ◽  
Ground Truth ◽  
Retinal Images ◽  
Diabetic Patients ◽  
New Approach ◽  
Prediction Rate ◽  
Efficient Detection ◽  
Knn Classification ◽  
Sensitivity Specificity

Diabetic retinopathy (DR) is a serious complication of diabetes mellitus and one of the major causes of blindness worldwide. As the number of diabetic patients increases, early detection of DR for regular screening can prevent loss of vision and blindness. The development of algorithms for detecting dark lesions may turn very useful in the early diagnosis and screening of retinopathy diseases. In this paper, a novel hybrid algorithm for the microaneurysms (MAs) detection is developed. This task is based on mathematical morphology, which is followed by a classification step. Although some algorithms have been developed, the accurate detection of MAs in color retinal images is still a challenging problem. The proposed approach aims to increase the number of true positives and minimize the false positives compared with methods developed in the literature. The new approach is tested on a set of 219 ophthalmologic images. A total of 12 microaneurysm features are considered in this study and selected for KNN classification. The validity of detection process is checked through comparisons at the pixel level with ophthalmologists’ hand-drawn ground truth. Sensitivity, specificity, prediction rate, and accuracy achieved by the proposed approach are 98.13%, 99.71%, 99.63% and 99.01% respectively.

Sign in / Sign up

Export Citation Format

Share Document