scholarly journals Hemodynamics in the retinal vasculature during the progression of diabetic retinopathy

2017 ◽  
Vol 1 (4) ◽  
pp. 6-15
Author(s):  
Francesco Calivá ◽  
Georgios Leontidis ◽  
Piotr Chudzik ◽  
Andrew Hunter ◽  
Luca Antiga ◽  
...  
Keyword(s):  
Reynolds Number ◽  
Blood Flow ◽  
Diabetic Retinopathy ◽  
Fluid Dynamic ◽  
First Year ◽  
Retinal Vasculature ◽  
Fundus Images ◽  
Parent Vessel ◽  
Last Stage ◽  
Vascular Trees

Purpose: In this study, it is shown that hemodynamic features are applicable as biomarkers to evaluate the progression of diabetic retinopathy (DR). Methods: Ninety-six fundus images from twenty-four subjects were selected. For each patient, four photographs were captured during the three years before DR and in the first year of DR. The vascular trees, which consisted of a parent vessel and two child branches were extracted, and at the branching nodes, the fluid dynamic conditions were estimated. Results: Veins were mostly affected during the last stage of diabetes before DR. In the arteries, the blood flow in both child branches and the Reynolds number in the smaller child branch were mostly affected. Conclusion: This study showed that hemodynamic features can add further information to the study of the progression of DR.

The Diagnosis Of Diabetic Retinopathy By Means Of Transfer Learning And Fine-Tuned Dense Layer Pipeline

Mekatronika ◽  
2020 ◽  
Vol 2 (1) ◽  
pp. 68-72
Author(s):  
Abdulaziz Abdo Salman ◽  
Ismail Mohd Khairuddin ◽  
Anwar P.P. Abdul Majeed ◽  
Mohd Azraai Mohd Razman
Keyword(s):  
Blood Flow ◽  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Blood Vessels ◽  
Transfer Learning ◽  
The Body ◽  
Dense Layer ◽  
Fundus Images ◽  
Detection Approach ◽  
Deep Learning Model

Diabetes is a global disease that occurs when the body is disabled pancreas to secrete insulin to convert the sugar to power in the blood. As a result, some tiny blood vessels on the part of the body, such as the eyes, are affected by high sugar and cause blocking blood flow in the vessels, which is called diabetic retinopathy.  This disease may lead to permanent blindness due to the growth of new vessels in the back of the retina causing it to detach from the eyes. In 2016, 387 million people were diagnosed with Diabetic retinopathy, and the number is growing yearly, and the old detection approach becomes worse. Therefore, the purpose of this paper is to computerize the old method of detecting different classes of DR from 0-4 according to severity by given fundus images. The method is to construct a fine-tuned deep learning model based on transfer learning with dense layers. The used models here are InceptionV3, VGG16, and ResNet50 with a sharpening filter. Subsequently, InceptionV3 has achieved 94% as the highest accuracy among other models.  

Critical Influence of Framing Coil Orientation on Intra-Aneurysmal and Neck Region Hemodynamics in a Sidewall Aneurysm Model

Neurosurgery ◽  
2010 ◽  
Vol 67 (6) ◽  
pp. 1692-1702 ◽  
Author(s):  
Clemens M Schirmer ◽  
Adel M Malek
Keyword(s):  
Blood Flow ◽  
Shear Stress ◽  
Wall Shear Stress ◽  
Dynamic Analysis ◽  
Computational Fluid Dynamic ◽  
Rank Order ◽  
Fluid Dynamic ◽  
Parent Vessel ◽  
Computational Fluid Dynamic Analysis ◽  
Wall Shear

Abstract BACKGROUND: Although coiling of intracranial aneurysms is thought to rely on obstruction of blood flow into the aneurysm and induction of intra-aneurysmal thrombosis, little data exist regarding the effect of coil deployment on hemodynamics. OBJECTIVE: To evaluate the effects of simulated coiling of a model aneurysm on flow and wall shear stress in the dome and neck regions using computational fluid dynamic analysis. METHODS: A spherical sidewall aneurysm on a curved parent vessel underwent simulated embolization with 1 or more computer-designed helical coils. The coils' axes had parallel, orthogonal, or transverse orientation with respect to blood flow. Pulsatile laminar flow computational fluid dynamic analysis was performed on high-resolution conformal meshes of the aneurysm-coil complex using realistic non-Newtonian blood viscosity. RESULTS: Intra-aneurysmal flow and energy flux into the dome were significantly reduced by coil insertion, with little effect on pressure distribution. Coiling increased viscosity in the distal dome with progressive spread toward the neck with greater coil packing. Coiling also decreased wall shear stress and its gradient both in the inflow zone and the downstream parent vessel. These alterations were dependent on coil orientation, with effectiveness rank order of parallel > transverse > orthogonal. CONCLUSION: We successfully modeled the hemodynamic effects of aneurysm coil embolization and uncovered a framing coil orientation dependence of dome and parent vessel hemodynamics. In addition to suggesting a pathophysiological link among coil configuration, protection from rupture, and aneurysm regrowth, these results pave the way for the analysis of aneurysm-coil complex interactions on a patient lesion-specific basis.

Role of blood flow and impaired autoregulation in the pathogenesis of diabetic retinopathy

Diabetes ◽  
1995 ◽  
Vol 44 (6) ◽  
pp. 603-607 ◽  
Author(s):  
E. M. Kohner ◽  
V. Patel ◽  
S. M. Rassam
Keyword(s):  
Blood Flow ◽  
Diabetic Retinopathy

The Implementation of Biological Phosphorus and Nitrogen Removal with the Bio-Denipho Process on a 265,000 PE Treatment Plant

1992 ◽  
Vol 25 (4-5) ◽  
pp. 161-168 ◽  
Author(s):  
J. Einfeldt
Keyword(s):  
Nitrogen Removal ◽  
Treatment Plant ◽  
First Year ◽  
In Series ◽  
Design Loads ◽  
Last Stage ◽  
Two Stages ◽  
The City ◽  
Biological Phosphorus

A process, called Bio-Denipho, for combined biological phosphorus and nitrogen removal in a combination of an anaerobic tank and two oxidation ditches is described. In this process the anaerobic tank consisting of three sections working in series is followed by two oxidation ditches. These too are working in series, but with both inlet to and outlet from the tanks changing in a cycle. The Bio-Denipho process is described specifically for the process itself and as a case study for the implementation of the process on a 265,000 pe wastewater treatment plant for the city of Aalborg in Denmark. The plant was designed and erected in two stages and the last stage was inaugurated October 31,1989. Lay-out and functions for the plant is described and design loads, plan lay-out and tank volumes are given in this paper together with performance data for the first year in operation.

Two-Tier Grading System for NPDR Severities of Diabetic Retinopathy in Retinal Fundus Images

2020 ◽  
Vol 14 ◽  
Author(s):  
Charu Bhardwaj ◽  
Shruti Jain ◽  
Meenakshi Sood
Keyword(s):  
Diabetic Retinopathy ◽  
Statistical Analysis ◽  
Early Stage ◽  
Image Feature ◽  
Grading System ◽  
Fundus Images ◽  
Fundus Image ◽  
Retinal Fundus Images ◽  
Retinal Fundus ◽  
Timely Treatment

: Diabetic Retinopathy is the leading cause of vision impairment and its early stage diagnosis relies on regular monitoring and timely treatment for anomalies exhibiting subtle distinction among different severity grades. The existing Diabetic Retinopathy (DR) detection approaches are subjective, laborious and time consuming which can only be carried out by skilled professionals. All the patents related to DR detection and diagnoses applicable for our research problem were revised by the authors. The major limitation in classification of severities lies in poor discrimination between actual lesions, background noise and other anatomical structures. A robust and computationally efficient Two-Tier DR (2TDR) grading system is proposed in this paper to categorize various DR severities (mild, moderate and severe) present in retinal fundus images. In the proposed 2TDR grading system, input fundus image is subjected to background segmentation and the foreground fundus image is used for anomaly identification followed by GLCM feature extraction forming an image feature set. The novelty of our model lies in the exhaustive statistical analysis of extracted feature set to obtain optimal reduced image feature set employed further for classification. Classification outcomes are obtained for both extracted as well as reduced feature set to validate the significance of statistical analysis in severity classification and grading. For single tier classification stage, the proposed system achieves an overall accuracy of 100% by k- Nearest Neighbour (kNN) and Artificial Neural Network (ANN) classifier. In second tier classification stage an overall accuracy of 95.3% with kNN and 98.0% with ANN is achieved for all stages utilizing optimal reduced feature set. 2TDR system demonstrates overall improvement in classification performance by 2% and 6% for kNN and ANN respectively after feature set reduction, and also outperforms the accuracy obtained by other state of the art methods when applied to the MESSIDOR dataset. This application oriented work aids in accurate DR classification for effective diagnosis and timely treatment of severe retinal ailment.

scholarly journals Detection of significantly high vitreous concentrations of fatty acid-binding protein 4 in patients with proliferative diabetic retinopathy

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Kaku Itoh ◽  
Masato Furuhashi ◽  
Yosuke Ida ◽  
Hiroshi Ohguro ◽  
Megumi Watanabe ◽  
...  
Keyword(s):  
Blood Flow ◽  
Diabetic Retinopathy ◽  
Fatty Acid ◽  
Proliferative Diabetic Retinopathy ◽  
Ocular Blood Flow ◽  
Laser Speckle ◽  
Laser Speckle Flowgraphy ◽  
Fatty Acid Binding ◽  
High Positive Correlation ◽  
Blood Biochemical

AbstractThe fatty acid-binding protein4 (FABP4) and vascular endothelial growth factor A (VEGFA) play key roles in the metabolic and cardiovascular diseases, and proliferative diabetic retinopathy (PDR), respectively. To identify FABP4 in vitreous fluid in PDR, vitreous concentrations of FABP4 (V-FABP4) and VEGFA (V-VEGFA) from PDR (n = 20) and non-PDR (n = 20) patients were determined by Enzyme-Linked ImmunoSorbent Assays. The data, which included height and weight, systemic blood pressures, several blood biochemical parameters and blood flow at the optic nerve head (ONH) by laser speckle flowgraphy (LSFG) were collected. The levels of V-FABP4 and V-VEGFA were significantly higher in PDR patients than in non-PDR patients (P < 0.001) with a high positive correlation (r = 0.72, P < 0.001) between them. The findings were not affected by body mass index values and the presence of vitreous hemorrhaging. Among the clinical parameters, V-FABP4 correlated positively with creatinine and negatively with age and aspartate transaminase (AST) levels, while V-VEGFA correlated positively with fasting plasma glucose and hemoglobin A1c (HbA1c) levels but negatively with AST. Multiple regression analyses indicated that V-VEGFA, or V-FABP4, AST and HbA1c were independent predictors of V-FABP4 or V-VEGFA, respectively. Both were negatively correlated, but more evident in V-FABP4, with the ONH ocular blood flow.

scholarly journals Deep Learning for Diabetic Retinopathy Detection and Classification Based on Fundus Images: A Review

2021 ◽  
pp. 104599
Author(s):  
Nikos Tsiknakis ◽  
Dimitris Theodoropoulos ◽  
Georgios Manikis ◽  
Emmanouil Ktistakis ◽  
Ourania Boutsora ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Fundus Images

The effect of insulin pump therapy in retinal vasculature in type 1 diabetic patients

2021 ◽  
pp. 112067212199057
Author(s):  
Tomás de Oliveira Loureiro ◽  
João Nobre Cardoso ◽  
Carlos Diogo Pinheiro Lima Lopes ◽  
Ana Rita Carreira ◽  
Sandra Rodrigues-Barros ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Metabolic Control ◽  
Insulin Pump Therapy ◽  
Vascular Density ◽  
Diabetic Patients ◽  
Retinal Vasculature ◽  
Increased Risk ◽  
The Mean ◽  
Type 1 Diabetic Patients

Background/objectives: Continuous subcutaneous insulin infusion (CSII) is a treatment for type 1 diabetes that improves metabolic control and reduces micro and macrovascular complications. The aim of this study was to compare the effect of CSII versus traditional multiple daily injections (MDI) therapy on retinal vasculature. Methods: We performed a prospective study with type 1 diabetic patients with no prior history of ocular pathology other than mild diabetic retinopathy. The patients were divided into two groups according to their therapeutic modality (CSII vs MDI). The retinal nerve fiber layers thickness and vascular densities were compared between groups in both macula and optic disc. The correlations between vascular density and clinical features were also determined. Statistical significance was defined as p < 0.05. Results: The study included 52 eyes, 28 in the insulin CSII group. The mean age was 36.66 ± 12.97 years, with no difference between groups ( p = 0.49). The mean glycated hemoglobin (HbA1c) was found to be lower in the CSII group (7.1% ± 0.7 vs 7.5% ± 0.7 p < 0.01). The parafoveal vascular density was found to be higher in the CSII group (42.5% ± 0.4 vs 37.7% ± 0.6, p < 0.01). We found an inverse correlation between HbA1c value and parafoveal vascular densities ( p < 0.01, r = −0.50). Conclusion: We found that CSII provided better metabolic control than MDI and this seemed to result in higher parafoveal vascular density. As lower vascular density is associated with an increased risk of diabetic retinopathy, these results suggest that CSII could be the safest therapeutic option to prevent retinopathy.

scholarly journals Adversarial Attack and Defence through Adversarial Training and Feature Fusion for Diabetic Retinopathy Recognition

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3922
Author(s):  
Sheeba Lal ◽  
Saeed Ur Rehman ◽  
Jamal Hussain Shah ◽  
Talha Meraj ◽  
Hafiz Tayyab Rauf ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Feature Fusion ◽  
Speckle Noise ◽  
Fundus Images ◽  
Adversarial Examples ◽  
Adversarial Training ◽  
Adversarial Attack ◽  
Retinal Fundus Images ◽  
Attacks And Defenses ◽  
Retinal Fundus

Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the security and robustness of the deployed algorithms need to be guaranteed. The security susceptibility of the DL algorithms to adversarial examples has been widely acknowledged. The artificially created examples will lead to different instances negatively identified by the DL models that are humanly considered benign. Practical application in actual physical scenarios with adversarial threats shows their features. Thus, adversarial attacks and defense, including machine learning and its reliability, have drawn growing interest and, in recent years, has been a hot topic of research. We introduce a framework that provides a defensive model against the adversarial speckle-noise attack, the adversarial training, and a feature fusion strategy, which preserves the classification with correct labelling. We evaluate and analyze the adversarial attacks and defenses on the retinal fundus images for the Diabetic Retinopathy recognition problem, which is considered a state-of-the-art endeavor. Results obtained on the retinal fundus images, which are prone to adversarial attacks, are 99% accurate and prove that the proposed defensive model is robust.

Sign in / Sign up

Export Citation Format

Share Document