• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.67-76
• /
• 2024

Diabetic retinopathy is a threatening complication of diabetes, caused by damaged blood vessels of light sensitive areas of retina. DR leads to total or partial blindness if left untreated. DR does not give any symptoms at early stages so earlier detection of DR is a big challenge for proper treatment of diseases. With advancement of technology various computer-aided diagnostic programs using image processing and machine learning approaches are designed for early detection of DR so that proper treatment can be provided to the patients for preventing its harmful effects. Now a day machine learning techniques are widely applied for image processing. These techniques also provide amazing result in this field also. In this paper we discuss various machine learning and deep learning based techniques developed for automatic detection of Diabetic Retinopathy.

• Diabetes and Metabolism Journal
• /
• v.42 no.6
• /
• pp.538-543
• /
• 2018

Globally, diabetic retinopathy (DR) is one of the leading causes of blindness, that diminishes quality of life. This study aimed to describe the prevalence of DR, and its associated risk factors. This cross-sectional study was carried out among 478 diabetic patients in a referral center in Fars province, Iran. The mean${\pm}$standard deviation age of the participants was $56.64{\pm}12.45$ years old and DR prevalence was 32.8%. In multivariable analysis, lower education levels (adjusted odds ratio [aOR], 0.43; 95% confidence interval [CI], 0.24 to 0.76), being overweight (aOR, 1.70; 95% CI, 1.02 to 2.83) or obese (aOR, 1.88; 95% CI, 1.09 to 3.26), diabetes duration of 10 to 20 years (aOR, 2.35; 95% CI, 1.48 to 3.73) and over 20 years (aOR, 5.63; 95% CI, 2.97 to 10.68), receiving insulin (aOR, 1.99; 95% CI, 1.27 to 3.10), and having chronic diseases (aOR, 1.71; 95% CI, 1.02 to 2.85) were significantly associated with DR. In conclusion, longer diabetes duration and obesity or having chronic diseases are strongly associated with DR suggesting that control of these risk factors may reduce both the prevalence and impact of retinopathy in Iran.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.632-633
• /
• 2023

Diabetic retinopathy (DR) is a prevalent complication of diabetes that can lead to vision impairment if not diagnosed and treated promptly. This study presents a novel approach for the automated grading of diabetic retinopathy in ultra-widefield fundus images (UFI) using deep learning techniques. We propose a method that involves preprocessing UFIs by cropping the central region to focus on the most relevant information. Subsequently, we employ state-of-the-art deep learning models, including ResNet50, EfficientNetB3, and Xception, to perform DR grade classification. Our extensive experiments reveal that Xception outperforms the other models in terms of classification accuracy, sensitivity, and specificity. his research contributes to the development of automated tools that can assist healthcare professionals in early DR detection and management, thereby reducing the risk of vision loss among diabetic patients.

• Research in Community and Public Health Nursing
• /
• v.33 no.4
• /
• pp.408-417
• /
• 2022

Purpose: This study aimed to investigate the prevalence and risk factors of diabetic retinopathy (DR) in people with diabetes mellitus (DM) using Korean National Health and Nutrition Examination Survey VII (2017~2018). Methods: DM was defined as in two ways; 1) doctor's diagnosis (Group 1, n=549), 2) one of doctor's diagnosis, medication, or hyperglycemia (Group 2, n=849). The DR prevalence was measured as the prevalence proportion (%). Risk factors for developing DR were analyzed using multiple logistic regression, and odds ratios (ORs) and 95% confidence intervals (CIs) were calculated. Results: The prevalence of DR was 25.87% in Group 1 and 20.14% in Group 2. Risk factors for DR were identified as insulin therapy (Group 1: OR=5.31, Group 2: OR=5.27), DM duration ≥10 years (Group 1: OR=2.20, Group 2: OR=3.10), and systolic blood pressure ≥140 mmHg (Group 1: OR=2.26, Group 2: OR=2.23) for both groups. Conclusion: Considering the DR prevalence, eye examinations education is highly recommended as part of a diabetes management programs in the community. It is also proposed to shorten the eye examination cycle for people with risk factors and establish a referral system to link between screening to treatment.

• Journal of Yeungnam Medical Science
• /
• v.40 no.2
• /
• pp.146-155
• /
• 2023

Background: Despite the recent increasing trend in the prevalence of type 2 diabetes among older individuals, the relationship between diabetic retinopathy (DR) and chronic kidney disease (CKD) in these patients remains unclear. This study investigated the severity of renal dysfunction according to the degree of DR in older patients with type 2 diabetes. Methods: A total of 116 patients with diabetes and CKD stage ≥3 who visited both the nephrology and ophthalmology outpatient departments between July 2021 and January 2022 were screened. There were 53 patients in the no DR group, 20 in the nonproliferative DR (NPDR) group, and 43 in the proliferative DR (PDR) group. Results: DR severity was related to the deterioration of renal function. The proportion of patients with advanced CKD significantly increased with DR severity (p for trend <0.001). In the multivariate regression model adjusted for age of ≥80 years, male sex, poorly controlled diabetes, macroalbuminuria, insulin use, diabetes duration of ≥10 years, cerebrovascular accident, hypertension, hyperlipidemia, and cardiovascular disease history, the odds ratio compared with the no DR group was approximately 4.6 for the NPDR group and approximately 11.8 for the PDR group, which were both statistically significant (p=0.025 and p<0.001, respectively). Conclusion: DR severity in older patients with diabetes may be associated with deterioration of renal function and high prevalence of advanced CKD. Therefore, periodic examination for DR in older patients with diabetes is important for predicting renal function deterioration and CKD progression.

• The Journal of Korean Medicine Ophthalmology and Otolaryngology and Dermatology
• /
• v.17 no.2
• /
• pp.112-119
• /
• 2004

Objective: To carry out the oriental medical treatment on a patient with vitreous hemorrhage in the left eye caused by diabetic retinopathy and record the results of the treatment. Methods: 1. Diagnosis: Fundus photography, Colored paper, Dr. Hahn's standard test chart for 5M, Blood sugar measurement. 2. Treatment: Acupuncture, Electro-Acupuncture, Indirect moxibustion, Western medicines, Oryoungsan(Crude drug preparations) Results: Oriental treatment using Ohaeng-acupuncture, Electro-Acupuncture, Indirect moxibustion resulted in the Unaided visual acuity of 0.1 while it used to be the left eye visual acuity with only light sense I month ago. Looking from Fundus photography result, progress was achieved and diabetic retinopathy was found to be in progress in fluorescein fundus angiography to right eye also by revisiting the patient after treatment. Conclusions: 1. Vitrectomy has many advantages but there are instances where patients do not recover their visual acuity due to complications. Therefore it is necessary to prove the effect oriental medical treatment through more cases in future. 2 For diabetic retinopathy patients, diabetes must be treated together with visual acuity.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.556-558
• /
• 2022

Diabetic retinopathy (DR) is one of the leading diseases causing vision loss. Early detection of this disease has a crucial role in protecting patients' eyes. Recent works have achieved impressive result when performing DR detection on fundus images using deep learning. In the deep learning-based approach, data augmentation has significant impact on the result. Recently, many data augmentation policies have been proposed and achieved state-of-the-art performance on different tasks. In this work, we compare effects of three data augmentation policies on DR grading in fundus images.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.397-398
• /
• 2019

망막혈관 영상에서(retinal image) 혈관의 모양 또는 생성변화를 효과적으로 검진하기 위해서 망막혈관을 자동적으로 분리하는 영상분할 기법의 개발은 매우 중요한 사안이다. 이를 위해서 주로 망막혈관영상의 잡음을 억제하고 또한 혈관의 명암대비도(contrast)를 증가시키는 전처리 과정을 거쳐서 혈관의 국부적인 화소값의 변화, 방향성을 판별하여 혈관을 자동적으로 검출하는 방법들이 제시되어왔으며 최근에는 합성곱 신경망(CNN) 딥러닝 학습모델을 활용한 망막혈관 분리 알고리즘들이 제시되고 있다.

• Diabetes and Metabolism Journal
• /
• v.42 no.6
• /
• pp.513-518
• /
• 2018

Background: Recent studies have correlated serum cystatin C (CysC) with vascular complications, but few studies have investigated this correlation in diabetes patients without nephropathy. This study aimed to evaluate if higher serum CysC levels increase the risk for vascular complications in type 2 diabetes mellitus patients with normal renal function or mild renal impairment. Methods: A total of 806 consecutive patients with type 2 diabetes mellitus who were admitted to the diabetes center of Soonchunhyang University Hospital for blood glucose control were retrospectively reviewed. Patients with nephropathy were excluded. Subjects were categorized into quartiles of serum CysC levels (Q1, ${\leq}0.65mg/L$; Q2, 0.66 to 0.79 mg/L; Q3, 0.80 to 0.94 mg/L; and Q4, ${\geq}0.95mg/L$). Results: The proportion of patients with diabetic retinopathy (DR) (P for trend <0.001), coronary heart disease (CHD) (P for trend <0.001), and stroke (P for trend <0.001) increased across the serum CysC quartiles. After adjustment for confounding factors, the highest serum CysC level remained a significant risk factor for DR (odds ratio [OR], 1.929; 95% confidence interval [CI], 1.007 to 4.144; P=0.040). Compared with Q1, a significant positive association was observed between serum CysC and CHD in Q2 (OR, 7.321; 95% CI, 1.114 to 48.114; P=0.012), Q3 (OR, 6.027; 95% CI, 0.952 to 38.161; P=0.020), and Q4 (OR, 8.122; 95% CI, 1.258 to 52.453; P=0.007). No associations were observed between CysC and stroke after additional adjustment for confounding variables. Conclusion: Serum CysC levels are independently associated with DR and CHD, suggesting that CysC may be useful for identifying type 2 diabetes mellitus patients without nephropathy who are at high risk for vascular complications.

• Korean Journal of Environmental Biology
• /
• v.27 no.1
• /
• pp.66-72
• /
• 2009

Diabetic Retinopathy (DR) is a leading cause of blindness among adults in the western countries. Hyperglycemia is a condition, that induces apoptotic cell death in a variety of cell types in diabetes, but the mechanism remains unclear. The aim of the study is to understand the effects of high Glucose on Human Retinal Endothelial Cells. Retinal endothelial cells were cultured in Iscove's Modified Dulbecco's Medium (IMDM) containing 5, 25 and 50 mM Glucose, incubated for 24, 36 and 48 hours in humidified 5 % CO$_2$ incubator at 37$^{\circ}C$. Human Retinal Endothelial Cell Line (HREC) were characterized for morphology with different treatment by phase contrast microscopic analysis. Number of dead and viable cells was counted by trypan blue exclusion and supported by MTT assay. The intracellular Hydrogen peroxide (H$_2$O$_2$), a Reactive Oxygen Species (ROS) generation in high glucose conditions was assessed by FOX II assay and apoptosis by caspase-3 assay. The high glucose treated cells undergoing DNA fragmentation was witnessed by Agarose gel electrophoresis. We found that the cells incubated with 25 and 50 mM glucose containing medium for 48 hours altered the morphology of the cell, induced apoptosis and DNA fragmentation. The dead cell number were high in 25 and 50 mM when compared to the cells incubated with 5 mM glucose for 24, 36, and 48 hours. Also, the H$_2$O$_2$ levels and the activity of caspase-3 were increased in high glucose treated cells. Conclusions/interpretation: Our results demonstrated that elevated glucose induces apoptosis in cultured HREC. The hyperglycemia-induced increase in apoptosis may be dependent on caspase activation. The association between ROS generation and caspase-3 activation on high glucose treated cells is yet to be investigated.