scholarly journals Detecting Diabetic Retinopathy Using Embedded Computer Vision

2020 ◽  
Vol 10 (20) ◽  
pp. 7274
Author(s):  
Parshva Vora ◽  
Sudhir Shrestha
Keyword(s):  
Computer Vision ◽  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Underserved Populations ◽  
The United States ◽  
Medically Underserved ◽  
Embedded Computer Vision ◽  
Embedded Computer ◽  
Increased Risk ◽  
Significant Step

Diabetic retinopathy is one of the leading causes of vision loss in the United States and other countries around the world. People who have diabetic retinopathy may not have symptoms until the condition becomes severe, which may eventually lead to vision loss. Thus, the medically underserved populations are at an increased risk of diabetic retinopathy-related blindness. In this paper, we present development efforts on an embedded vision algorithm that can classify healthy versus diabetic retinopathic images. Convolution neural network and a k-fold cross-validation process were used. We used 88,000 labeled high-resolution retina images obtained from the publicly available Kaggle/EyePacs database. The trained algorithm was able to detect diabetic retinopathy with up to 76% accuracy. Although the accuracy needs to be further improved, the presented results represent a significant step forward in the direction of detecting diabetic retinopathy using embedded computer vision. This technology has the potential of being able to detect diabetic retinopathy without having to see an eye specialist in remote and medically underserved locations, which can have significant implications in reducing diabetes-related vision losses.

Anxiety and depression among racial/ethnic minorities and impoverished women testing positive for BRCA1/2 mutations in the United States

2021 ◽  
Author(s):  
Kate E Dibble ◽  
Avonne E Connor
Keyword(s):  
United States ◽  
Depressive Symptoms ◽  
Hispanic Women ◽  
Ethnic Disparities ◽  
The United States ◽  
Medically Underserved ◽  
Increased Risk ◽  
Poverty Status ◽  
Race Ethnicity ◽  
Severe Anxiety

Abstract PurposeTo outline the association between race/ethnicity and poverty status and perceived anxiety and depressive symptomologies among BRCA1/2-positive United States (US) women to identify high-risk groups of mutation carriers from medically underserved backgrounds.Methods211 BRCA1/2-positive women from medically underserved backgrounds were recruited through national Facebook support groups and completed an online survey. Adjusted odds ratios (aOR) and 95% confidence intervals (CIs) were estimated using multivariable logistic regression for associations between race/ethnicity, poverty status, and self-reported moderate-to-severe anxiety and depressive symptoms.ResultsWomen ranged in age (18–75, M = 39.5, SD = 10.6). Most women were non-Hispanic white (NHW) (67.2%) and were not impoverished (76.7%). Hispanic women with BRCA1/2 mutations were 6.11 times more likely to report moderate-to-severe anxiety (95% CI, 2.16–17.2, p = 0.001) and 4.28 times more likely to report moderate-to-severe depressive symptoms (95% CI, 1.98–9.60, p = < 0.001) than NHW women with BRCA1/2. Associations were not statistically significant among other minority women. Women living in poverty were significantly less likely to report moderate-to-severe depressive symptoms than women not in poverty (aOR, 0.42, 95% CI, 0.18–0.95, p = 0.04).ConclusionHispanic women with BRCA1/2 mutations from medically underserved backgrounds are an important population at increased risk for worse anxiety and depressive symptomology. Our findings among Hispanic women with BRCA1/2 mutations add to the growing body of literature focused on ethnic disparities experienced across the cancer control continuum.

scholarly journals Racial Disparities-Associated COVID-19 Mortality among Minority Populations in the US

2020 ◽  
Vol 9 (8) ◽  
pp. 2442 ◽  
Author(s):  
Donald J. Alcendor
Keyword(s):  
Social Services ◽  
Underserved Populations ◽  
The United States ◽  
Cultural Barriers ◽  
Systems Science ◽  
Minority Populations ◽  
Populations At Risk ◽  
Increased Risk ◽  
The Us ◽  
Novel Coronavirus

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), a betacoronavirus that causes the novel coronavirus disease 2019 (COVID-19), is highly transmissible and pathogenic for humans and may cause life-threatening disease and mortality, especially in individuals with underlying comorbidities. First identified in an outbreak in Wuhan, China, COVID-19 is affecting more than 185 countries and territories around the world, with more than 15,754,651 confirmed cases and more than 640,029 deaths. Since December 2019, SARS-CoV-2 transmission has become a global threat, which includes confirmed cases in all 50 states within the United States (US). As of 25 July 2020, the Johns Hopkins Whiting School of Engineering Center for Systems Science and Engineering reports more than 4,112,651 cases and 145,546 deaths. To date, health disparities are associated with COVID-19 mortality among underserved populations. Here, the author explores potential underlying reasons for reported disproportionate, increased risks of mortality among African Americans and Hispanics/Latinos with COVID-19 compared with non-Hispanic Whites. The author examines the underlying clinical implications that may predispose minority populations and the adverse clinical outcomes that may contribute to increased risk of mortality. Government and community-based strategies to safeguard minority populations at risk for increased morbidity and mortality are essential. Underserved populations living in poverty with limited access to social services across the US are more likely to have underlying medical conditions and are among the most vulnerable. Societal and cultural barriers for ethnic minorities to achieve health equity are systemic issues that may be addressed only through shifts in governmental policies, producing long-overdue, substantive changes to end health care inequities.

scholarly journals Diabetic Retinopathy and Risk of Stroke

Stroke ◽  
2020 ◽  
Vol 51 (12) ◽  
pp. 3733-3736
Author(s):  
Ka-Ho Wong ◽  
Katherine Hu ◽  
Cecilia Peterson ◽  
Nazanin Sheibani ◽  
Georgios Tsivgoulis ◽  
...  
Keyword(s):  
Blood Pressure ◽  
Diabetic Retinopathy ◽  
Primary Outcome ◽  
Vision Loss ◽  
Proportional Hazards ◽  
Cox Regression ◽  
Secondary Analysis ◽  
Cox Proportional Hazards ◽  
Increased Risk

Background and Purpose: Diabetic retinopathy (DR) is a common microvascular complication of diabetes, which causes damage to the retina and may lead to rapid vision loss. Previous research has shown that the macrovascular complications of diabetes, including stroke, are often comorbid with DR. We sought to explore the association between DR and subsequent stroke events. Methods: This is a secondary analysis of patients enrolled in the ACCORD Eye study (Action to Control Cardiovascular Risk in Diabetes). The primary outcome was stroke during follow-up. The exposure was presence of DR at study baseline. We fit adjusted Cox proportional hazards models to provide hazard ratios for stroke and included interaction terms with the ACCORD randomization arms. Results: We included 2828 patients, in whom the primary outcome of stroke was met by 117 (4.1%) patients during a mean (SD) of 5.4 (1.8) years of follow-up. DR was present in 874 of 2828 (30.9%) patients at baseline and was more common in patients with than without incident stroke (41.0% versus 30.5%; P =0.016). In an adjusted Cox regression model, DR was independently associated with incident stroke (hazard ratio, 1.52 [95% CI, 1.05–2.20]; P =0.026). This association was not affected by randomization arm in the ACCORD glucose ( P =0.300), lipid ( P =0.660), or blood pressure interventions ( P =0.469). Conclusions: DR is associated with an increased risk of stroke, which suggests that the microvascular pathology inherent to DR has larger cerebrovascular implications. This association appears not to be mediated by serum glucose, lipid, and blood pressure interventions.

Diabetic Retinopathy—Update on Prevention Techniques, Present Therapies, and New Leads

2014 ◽  
Vol 10 (01) ◽  
pp. 25
Author(s):  
Lauren M Marozas ◽  
Patrice E Fort ◽  
◽  
Keyword(s):  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Developed Countries ◽  
Detection Methods ◽  
Retinal Microvasculature ◽  
Increased Risk ◽  
Patients With Diabetes ◽  
Combined Control ◽  
Working Age ◽  
Proactive Measures

Diabetic retinopathy is the major ocular complication associated with diabetes, and represents the leading cause of legal blindness in the working-age population of developed countries. Although classically diagnosed based on abnormalities of the retinal microvasculature, diabetic retinopathy is now widely recognized as a neurovascular disease. While all patients with diabetes are at increased risk for eye disease including diabetic retinopathy, proactive measures, and timely intervention can prevent or delay subsequent vision loss. Systemic management of diabetes by combined control of glycemia, blood pressure, and serum lipid levels remains the most important method of preventing diabetic retinopathy onset and progression. Once detected, surgical and medical interventions including photocoagulation, vitrectomy, and intravitral drug injection can help preserve vision. However, the need for improved detection methods and therapies that will allow earlier diagnosis and treatment remains apparent. This review summarizes current techniques for the prevention and intervention for diabetic retinopathy, and examines ongoing developments in the search for new endpoints and therapies as they apply to preventing vision loss associated with diabetes.

Tailoring design for embedded computer vision applications

Computer ◽  
2015 ◽  
Vol 48 (5) ◽  
pp. 58-62 ◽  
Author(s):  
Jason Schlessman ◽  
Marilyn Wolf
Keyword(s):  
Computer Vision ◽  
Embedded Computer Vision ◽  
Embedded Computer ◽  
Computer Vision Applications

scholarly journals Smart Doll: Emotion Recognition Using Embedded Deep Learning

Symmetry ◽  
2018 ◽  
Vol 10 (9) ◽  
pp. 387 ◽  
Author(s):  
Jose Espinosa-Aranda ◽  
Noelia Vallez ◽  
Jose Rico-Saavedra ◽  
Javier Parra-Patino ◽  
Gloria Bueno ◽  
...  
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Ethical Issues ◽  
Real Life ◽  
Graphic Processing Units ◽  
Cloud Processing ◽  
Embedded Computer Vision ◽  
Embedded Computer ◽  
Learning Techniques ◽  
Learning Capabilities

Computer vision and deep learning are clearly demonstrating a capability to create engaging cognitive applications and services. However, these applications have been mostly confined to powerful Graphic Processing Units (GPUs) or the cloud due to their demanding computational requirements. Cloud processing has obvious bandwidth, energy consumption and privacy issues. The Eyes of Things (EoT) is a powerful and versatile embedded computer vision platform which allows the user to develop artificial vision and deep learning applications that analyse images locally. In this article, we use the deep learning capabilities of an EoT device for a real-life facial informatics application: a doll capable of recognizing emotions, using deep learning techniques, and acting accordingly. The main impact and significance of the presented application is in showing that a toy can now do advanced processing locally, without the need of further computation in the cloud, thus reducing latency and removing most of the ethical issues involved. Finally, the performance of the convolutional neural network developed for that purpose is studied and a pilot was conducted on a panel of 12 children aged between four and ten years old to test the doll.

Sign in / Sign up

Export Citation Format

Share Document