EXUDATES DETECTION AND CLASSIFICATION ALGORITHM OF DIABETIC PATIENTS' RETINA IMAGES

2013 ◽  
Vol 22 (02) ◽  
pp. 1250087
Author(s):  
VESNA ZELJKOVIĆ ◽  
MILENA BOJIC ◽  
CLAUDE TAMEZE ◽  
VENTZESLAV VALEV
Keyword(s):  
Diabetic Retinopathy ◽  
Diabetic Patients ◽  
Diabetic Retinopathy Screening ◽  
Automated Algorithm ◽  
Chronic Hyperglycemia ◽  
Clinical Environments ◽  
Retinal Fundus ◽  
Retina Images

The chronic hyperglycemia of diabetes is associated with long-term damage, dysfunction, and failure of different organs, especially the eyes, kidneys, nerves, heart and blood vessels. The regular examination of diabetic patients can potentially reduce the risk of vision impairment and in the last instance blindness. Early diabetic retinopathy detection enables application of laser therapy treatment in order to prevent or delay loss of vision. The diagnostics and detection of diabetic retinopathy is performed by specialized ophthalmologists manually and represents expensive procedure. Automatic exudates detection and retina images classification would be helpful for reducing diabetic retinopathy screening costs and encouraging regular examinations. We proposed the automated algorithm that applies mathematical modeling which enables light intensity levels emphasis, easier exudates detection, efficient and correct classification of retina images. The proposed algorithm is robust to various appearance changes of retinal fundus images which are usually processed in clinical environments.

scholarly journals Prevalence Trend of Diabetic Retinopathy in India

2021 ◽  
Vol 9 (3) ◽  
pp. 49-56
Author(s):  
M Chitra ◽  
Aruthdha Shree Neevanandam
Keyword(s):  
Diabetic Retinopathy ◽  
Tamil Nadu ◽  
Its Region ◽  
Vital Role ◽  
Diabetic Patients ◽  
Cross Sectional ◽  
Diabetic Retinopathy Screening ◽  
The Impact

Background: Diabetic Retinopathy plays a vital role in the impact of long-term Diabetic patients in global humankind. The health of diabetic people determined by many factors, specifically the number of years of diabetic suffering. There is a positive relationship between the risk of diabetic retinopathy and the number of years of diabetic sufferings, which was identified by many researchers globally. In addition, patients who suffer from type 2 diabetes mellitus are suffering from diabetic retinopathy. However, there are few comprehensive reviews and studies focusing on its prevalence and the factors of prevalence. It is worthwhile to pay attention to diabetic retinopathy in Global, India and its region, given that the trend and structure of diabetic retinopathy from reviews. Method: Prevalence provides a cross-sectional snapshot of morbidity at that point or period. The study is a concurrent review of diabetic retinopathy in India and its region. It presents the findings from some national or regional camp data, interviews with key informants, reviews of relevant published papers and policy contents. Results and Conclusion: Approximately one in five people living with diabetes in India has some degree of DR (13 million in India) and one in ten (6.5 million) has the vision-threatening form of DR. Tamil Nadu is the topmost in the prevalence rate of Diabetic Retinopathy among the states of India with above 10.5 percentage based on the report of Amaltas 2019. Hence, a mass survey for diabetic retinopathy screening needed to be conducted in all districts to know the exact status and plan in the National Programme for Control of Blindness and Visual Impairment (NPCB & VI).

Using transfer learning for diabetic retinopathy stage classification

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Enas M.F. El Houby
Keyword(s):  
Diabetic Retinopathy ◽  
Transfer Learning ◽  
Grade Level ◽  
Design Methodology ◽  
Content Type ◽  
Stage Classification ◽  
Set Up ◽  
Retinal Fundus ◽  
Automated Methods

PurposeDiabetic retinopathy (DR) is one of the dangerous complications of diabetes. Its grade level must be tracked to manage its progress and to start the appropriate decision for treatment in time. Effective automated methods for the detection of DR and the classification of its severity stage are necessary to reduce the burden on ophthalmologists and diagnostic contradictions among manual readers.Design/methodology/approachIn this research, convolutional neural network (CNN) was used based on colored retinal fundus images for the detection of DR and classification of its stages. CNN can recognize sophisticated features on the retina and provides an automatic diagnosis. The pre-trained VGG-16 CNN model was applied using a transfer learning (TL) approach to utilize the already learned parameters in the detection.FindingsBy conducting different experiments set up with different severity groupings, the achieved results are promising. The best-achieved accuracies for 2-class, 3-class, 4-class and 5-class classifications are 86.5, 80.5, 63.5 and 73.7, respectively.Originality/valueIn this research, VGG-16 was used to detect and classify DR stages using the TL approach. Different combinations of classes were used in the classification of DR severity stages to illustrate the ability of the model to differentiate between the classes and verify the effect of these changes on the performance of the model.

scholarly journals Time-Specific Associations of Wearable, Sensor-Based Cardiovascular and Behavioral Readouts with Disease Phenotypes in the Outpatient Setting of the Chronic Renal Insufficiency Cohort (CRIC)

2022 ◽  
Author(s):  
Nicholas F Lahens ◽  
Mahboob Rahman ◽  
Jordana B Cohen ◽  
Debbie L Cohen ◽  
Jing Chen ◽  
...  
Keyword(s):  
Renal Insufficiency ◽  
Chronic Renal Insufficiency ◽  
Nervous Activity ◽  
Outpatient Setting ◽  
Fluctuation Analysis ◽  
Diabetic Patients ◽  
Clinical Environments ◽  
Time Specific ◽  
Detrended Fluctuation

Patients with chronic kidney disease (CKD) are at risk of developing cardiovascular disease. To facilitate out-of-clinic evaluation, we piloted wearable device-based analysis of heart rate variability and behavioral readouts in patients with CKD participating in the Chronic Renal Insufficiency Cohort and (n=49) controls. Time-specific partitioning of HRV readouts indicate higher parasympathetic nervous activity during the night (mean RR at night 14.4+/-1.9 ms versus 12.8+/-2.1 ms during active hours; n=47, ANOVA q=0.001). The alpha2 long-term fluctuations in the detrended fluctuation analysis, a parameter predictive of cardiovascular mortality, significantly differentiated between diabetic and non-diabetic patients (prominent at night with 0.58+/-0.2 versus 0.45+/-0.12, respectively, adj. p=0.004). Both diabetic and nondiabetic CKD patients showed loss of rhythmic organization compared to controls, with diabetic CKD patients exhibiting deconsolidation of peak phases between their activity and SDNN (standard deviation of interbeat intervals) rhythms (mean phase difference CKD 8.3h, CKD/T2DM 4h, controls 6.8h). This work provides a roadmap toward deriving actionable clinical insights from the data collected by wearable devices outside of highly controlled clinical environments.

scholarly journals Retinal Blood Vessel and Optic Disc Segmentation

2019 ◽  
Vol 8 (2) ◽  
pp. 833-838
Keyword(s):  
Diabetic Retinopathy ◽  
Blood Vessel ◽  
Optic Disc ◽  
Diabetic Patients ◽  
Retinal Vessels ◽  
Retinal Blood Vessel ◽  
Computerized Screening ◽  
Retinal Fundus

Diabetic Retinopathy (DR) is a main source of vision misfortune in diabetic patients. DR is a predominantly caused because of the harm caused in retinal veins of a diabetic patients. It is fundamental to recognize and fragment their tinal veins for DR identification and determination, which avoids prior vision misfortune in diabetic patients. The PC helped programmed discovery and division of veins through the end of optic location district in Retina. Optic Disc (OD) discovery is a principle step while creating computerized screening framework for diabetic retinopathy. This is a technique to naturally recognize the situation of the OD in advanced retinal fundus pictures. The strategy begins by normalizing glow and difference all through the picture utilizing brightening evening out and versatile histogram balance techniques individually. The OD recognition calculation depends on coordinating the normal directional example of the retinal veins. Henceforth, a straightforward coordinated channel is proposed to generally coordinate the headings of the vessels at the OD region. The retinal vessels are portioned utilizing a basic and standard 2-D Gaussian coordinated channel.

scholarly journals Utilization of diabetic retinopathy screening among diabetic patients at a tertiary care hospital in Kerala, India

2021 ◽  
Vol 8 (10) ◽  
pp. 4938
Author(s):  
Sona Sabitha Kumar ◽  
Lathika Vasu Kamaladevi ◽  
Sruthi Mankara Valsan
Keyword(s):  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Adult Population ◽  
Tertiary Care ◽  
Health Concern ◽  
Diabetic Patients ◽  
Care Hospital ◽  
Screening Programs ◽  
Diabetic Retinopathy Screening ◽  
Retinopathy Screening

Background: Diabetes is a major public health concern that affects nearly 463 million (9.3%) of global adult population. Diabetic retinopathy, which affects around 35% of all diabetic patients, is the fifth leading cause of preventable global blindness. This study was done to determine the status of diabetic retinopathy screening and the factors that influence its uptake among diabetic patients attending a tertiary care setting in Kerala, India.Methods: 200 patients with diabetes mellitus on physician care were enrolled for a questionnaire-based survey which collected information on patient demographics, education, occupation, patient’s awareness of retinopathy, screening, diabetic blindness and their source of such knowledge.Results: 83% were aware that diabetes can result in vision loss. 61% were aware that diabetic blindness is preventable. 42% patients were aware of screening options for retinopathy. The awareness of retinopathy screening was significantly associated (p=0.0001) only with duration of diabetes.Conclusions: Awareness of diabetic retinopathy among diabetic patients in Kerala was sub optimal. Better patient education and use of mass media can increase awareness on diabetes retinopathy screening programs. 

Associations Between Diabetic Retinopathy and Plasma Levels of High-sensitive C-reactive Protein or Von Willebrand Factor in Long-term Type 1 Diabetic Patients

2012 ◽  
Vol 38 (1) ◽  
pp. 174-179 ◽  
Author(s):  
Jonas Vejvad Nørskov Laursen ◽  
Stine Skovbo Hoffmann ◽  
Anders Green ◽  
Mads Nybo ◽  
Anne Katrin Sjølie ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Diabetic Patients ◽  
C Reactive Protein ◽  
Reactive Protein ◽  
Von Willebrand ◽  
Type 1 Diabetic Patients ◽  
Willebrand Factor ◽  
Term Type

scholarly journals Transfer Learning with Convolutional Neural Networks for Diabetic Retinopathy Image Classification. A Review

2020 ◽  
Vol 10 (6) ◽  
pp. 2021 ◽  
Author(s):  
Ibrahem Kandel ◽  
Mauro Castelli
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Transfer Learning ◽  
Main Idea ◽  
Diabetic Patients ◽  
Domain Transfer ◽  
Domain Transfer Learning ◽  
Enormous Number ◽  
Deep Learning Model

Diabetic retinopathy (DR) is a dangerous eye condition that affects diabetic patients. Without early detection, it can affect the retina and may eventually cause permanent blindness. The early diagnosis of DR is crucial for its treatment. However, the diagnosis of DR is a very difficult process that requires an experienced ophthalmologist. A breakthrough in the field of artificial intelligence called deep learning can help in giving the ophthalmologist a second opinion regarding the classification of the DR by using an autonomous classifier. To accurately train a deep learning model to classify DR, an enormous number of images is required, and this is an important limitation in the DR domain. Transfer learning is a technique that can help in overcoming the scarcity of images. The main idea that is exploited by transfer learning is that a deep learning architecture, previously trained on non-medical images, can be fine-tuned to suit the DR dataset. This paper reviews research papers that focus on DR classification by using transfer learning to present the best existing methods to address this problem. This review can help future researchers to find out existing transfer learning methods to address the DR classification task and to show their differences in terms of performance.

Sign in / Sign up

Export Citation Format

Share Document