scholarly journals Two Eyes Are Better Than One: Exploiting Binocular Correlation for Diabetic Retinopathy Severity Grading

2021 ◽  
Author(s):  
Peisheng Qian ◽  
Ziyuan Zhao ◽  
Cong Chen ◽  
Zeng Zeng ◽  
Xiaoli Li
Keyword(s):  
Diabetic Retinopathy ◽  
Severity Grading ◽  
Better Than

Computer-aided diabetic retinopathy diagnostic model using optimal thresholding merged with neural network

2020 ◽  
Vol 13 (3) ◽  
pp. 283-310 ◽  
Author(s):  
Ambaji S. Jadhav ◽  
Pushpa B. Patil ◽  
Sunil Biradar
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Diabetic Retinopathy ◽  
Blood Vessel ◽  
Vessel Segmentation ◽  
Gray Level ◽  
Content Type ◽  
Blood Vessel Segmentation ◽  
Computer Aided ◽  
Better Than

PurposeDiabetic retinopathy (DR) is a central root of blindness all over the world. Though DR is tough to diagnose in starting stages, and the detection procedure might be time-consuming even for qualified experts. Nowadays, intelligent disease detection techniques are extremely acceptable for progress analysis and recognition of various diseases. Therefore, a computer-aided diagnosis scheme based on intelligent learning approaches is intended to propose for diagnosing DR effectively using a benchmark dataset.Design/methodology/approachThe proposed DR diagnostic procedure involves four main steps: (1) image pre-processing, (2) blood vessel segmentation, (3) feature extraction, and (4) classification. Initially, the retinal fundus image is taken for pre-processing with the help of Contrast Limited Adaptive Histogram Equalization (CLAHE) and average filter. In the next step, the blood vessel segmentation is carried out using a segmentation process with optimized gray-level thresholding. Once the blood vessels are extracted, feature extraction is done, using Local Binary Pattern (LBP), Texture Energy Measurement (TEM based on Laws of Texture Energy), and two entropy computations – Shanon's entropy, and Kapur's entropy. These collected features are subjected to a classifier called Neural Network (NN) with an optimized training algorithm. Both the gray-level thresholding and NN is enhanced by the Modified Levy Updated-Dragonfly Algorithm (MLU-DA), which operates to maximize the segmentation accuracy and to reduce the error difference between the predicted and actual outcomes of the NN. Finally, this classification error can correctly prove the efficiency of the proposed DR detection model.FindingsThe overall accuracy of the proposed MLU-DA was 16.6% superior to conventional classifiers, and the precision of the developed MLU-DA was 22% better than LM-NN, 16.6% better than PSO-NN, GWO-NN, and DA-NN. Finally, it is concluded that the implemented MLU-DA outperformed state-of-the-art algorithms in detecting DR.Originality/valueThis paper adopts the latest optimization algorithm called MLU-DA-Neural Network with optimal gray-level thresholding for detecting diabetic retinopathy disease. This is the first work utilizes MLU-DA-based Neural Network for computer-aided Diabetic Retinopathy diagnosis.

scholarly journals Segmentation of exudates to assess diabetic retinopathy by reni’s entropy based thresholding

2018 ◽  
Vol 7 (2.25) ◽  
pp. 109
Author(s):  
Josline Elsa Joseph ◽  
R J. Hemalatha ◽  
Bincy Babu ◽  
T R. Thamizhvani ◽  
A Josephin Arockia Dhivya ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Active Contour ◽  
Medical Image ◽  
Active Contour Model ◽  
Unsharp Masking ◽  
Contour Model ◽  
Disease Condition ◽  
Renyi’S Entropy ◽  
Pathological Disease ◽  
Better Than

Objective: Diabetic retinopathy is a critical pathological disease condition which affects the lives of millions of people everyday. Exudates found in the eye are one of the important signs of Diabetic retinopathy. This work aims to segment exudates for faster detection and treatment of Diabetic retinopathy.Methods: This paper proposes a robust and efficient method to segment exu-dates. Initial pre-processing work applies adaptive unsharp masking which sharps the areas based on the level of smoothness in the image preventing accentuation of noise. Optic disc is removed by active contour model. The exudates are then segmented by Renyi’s Entropy based thresholding which choses the optimal threshold for segmentation, exploiting Renyi’s entropy da-ta.Results: The performance of the proposed system was evaluated and found better than state of art results giving accuracy, sensitivity and specificity 94.5%, 95.1% and 96.2% respectively.Conclusion: Effective computer aided system is essential for accurate exudates detection. The proposed algorithm utilises the advantages of adaptive unsharp masking in medical image pro-cessing along with Renyi’s entropy based thresholding to detect Exudates, which performs better than traditional thresholding techniques.  

scholarly journals Individual and combined effects of verapamil or trandolapril on attenuating hypertensive glomerulopathic changes in the stroke-prone rat.

1996 ◽  
Vol 7 (5) ◽  
pp. 681-686
Author(s):  
K Münter ◽  
S Hergenröder ◽  
K Jochims ◽  
M Kirchengast
Keyword(s):  
Ace Inhibitor ◽  
Blood Pressure Reduction ◽  
Control Group ◽  
Channel Blockers ◽  
Combined Effects ◽  
Spontaneously Hypertensive ◽  
Drug Classes ◽  
Kidney Morphology ◽  
Severity Grading ◽  
Better Than

Previous studies have demonstrated differences in the progression to glomerulosclerosis with the use of calcium channel blockers (CCB). The results with angiotensin-converting enzyme (ACE) inhibitors are more consistent. Moreover, only two studies have examined the combined effects of these drug classes on the development of glomerulosclerosis. The aim of the study presented here was to test the hypothesis that nonhypotensive doses of the combination (VT) of a nondihydropyridine CCB, verapamil (V), and an ACE-inhibitor, trandolapril (T), will slow the development of glomerulosclerosis better than either agent alone in stroke-prone spontaneously hypertensive rats (SHRSP). SHRSP were randomized to treatment in one of three groups with nonhypotensive doses of these agents; a fourth group served as control (C). The control rats developed significant increases in proteinuria compared with the other groups (C, 190 +/- 35 mg.kg-1.d-1 versus VT, 19 +/- 12 mg.kg-1.d-1; P < 0.05). This finding correlated with the degree of glomerulosclerosis (mean severity grading for C, 3.31 +/- 0.21 versus VT, 1.6 +/- 0.51; P < 0.05). Moreover, there was no significant reduction in arterial pressure between these groups (C, 282 +/- 5 versus VT, 259 +/- 13 mm Hg; P = 0.12). Despite persisting hypertension, the rise in proteinuria was also attenuated in both the V group (57 +/- 21 mg.kg-1.d-1) and the T group (43 +/- 24 mg.kg-1.d-1). However, compared with the control rats, kidney morphology was unchanged. Lastly, creatinine clearance was better preserved in the VT group compared with the control group (C, 0.57 +/- 0.01 versus VT, 0.74 +/- 0.06 mL.min-1.100 g-1; P < 0.05). It was concluded that the combination of nonhypotensive doses of VT attenuates the rise in proteinuria and progression to glomerulosclerosis. This study supports the concept that VT may have effects on the glomerulus that are independent of blood pressure reduction.

scholarly journals Visual fields correlate better than visual acuity to severity of diabetic retinopathy

Diabetologia ◽  
2005 ◽  
Vol 48 (12) ◽  
pp. 2494-2500 ◽  
Author(s):  
B. Bengtsson ◽  
A. Heijl ◽  
E. Agardh
Keyword(s):  
Visual Acuity ◽  
Diabetic Retinopathy ◽  
Visual Fields ◽  
Better Than

scholarly journals A Transfer Learning Approach for Diabetic Retinopathy and Diabetic Macular Edema Severity Grading

2021 ◽  
Vol 35 (6) ◽  
pp. 497-502
Author(s):  
Nida Nasir ◽  
Neda Afreen ◽  
Ranjeeta Patel ◽  
Simran Kaur ◽  
Mustafa Sameer
Keyword(s):  
Diabetic Retinopathy ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Transfer Learning ◽  
Learning Approach ◽  
Learning Technique ◽  
Working Age ◽  
Severity Grading ◽  
Aided Diagnosis

Diabetic Retinopathy (DR) and Diabetic Macular Edema (DME) are complication that occurs in diabetic patient especially among working age group that leads to vision impairment problem and sometimes even permanent blindness. Early detection is very much needed for diagnosis and to reduce blindness or deterioration. The diagnosis phase of DR consumes more time, effort and cost when manually performed by ophthalmologists and more chances of misdiagnosis still there. Research community is working on to design computer aided diagnosis system for prior detection and for DR grading based on its severity. Ongoing researches in Artificial Intelligence (AI) have set out the advancement of deep learning technique which comes as a best technique to perform analysis and classification of medical images. In this paper, research is applied on Resnet50 model for classification of DR and DME based on its severity grading on public benchmark dataset. Transfer learning approach accomplishes the best outcome on Indian Diabetic Retinopathy Image Dataset (IDRiD).

Sign in / Sign up

Export Citation Format

Share Document