Detection of Microaneurysms in Fundus Images using ELM Classifier

2017 ◽  
Vol 8 (03) ◽  
Author(s):  
G. R. Hemalakshmi ◽  
N. B. Prakash
Keyword(s):  
Diabetic Retinopathy ◽  
Retinal Disease ◽  
Peak Detection ◽  
Input Image ◽  
Experimental Results ◽  
Fundus Images ◽  
Cross Sectional ◽  
Property Measurement ◽  
Elm Classifier

The main objective of this paper is to detect the microaneurysms which is the sign and symptom for the retinal disease Diabetic Retinopathy (DR). In this work, the input image is preprocessed and then cross sectional scanning is applied for peak detection and property measurement. Feature set from the processed images is extracted and ELM classifier is used for MA detection. The experimental results show the proposed system provides better results compared to existing system.

scholarly journals DIABETIC RETINOPATHY;

2018 ◽  
Vol 25 (08) ◽  
pp. 1256-1260
Author(s):  
Nasir Ahmad Chaudhary ◽  
Samreen Hameed ◽  
Muhammad Sultan Ul Moazzam ◽  
Sarmad Zahoor ◽  
Sidrah Latif ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Predictive Value ◽  
Tertiary Care ◽  
Retinal Disease ◽  
Cross Sectional Study ◽  
Diabetic Patients ◽  
Cross Sectional ◽  
Retinal Examination ◽  
Tertiary Care Hospitals ◽  
Hba1c Levels

Background: Diabetic retinopathy is one of the most common complications ofdiabetes affecting more than 1/4th of the diabetics and is also the leading cause of blindness inmany parts of the globe. Regular fundoscopic examination for screening is a routine practicein tertiary care hospitals but is not available in the primary care centers. This necessitatesthe development of a reliable screening tool which will allow for early referral of those withcomplications to the specialist centers. Objective: To determine the predictive value of HbA1clevels for the presence of diabetic retinopathy. Study Design: A cross-sectional study. Setting:Diabetic Clinic of Mayo Hospital, Lahore. Period: 04 months, January to April 2017. Method:75 diabetic patients who presented in Diabetic clinic were investigated for HbA1c levels andfundoscopic evaluation was done to detect retinal changes. Results: Out of 75 patients, 35(46.7%) were female, 40 (53.3%) were male. Median age of the patients was 51 years. All patientshad HbA1c levels more than 6.0% and 62% patients had detectable changes on fundi while therest had no detectable retinal disease despite elevated HbA1c levels. Positive predictive value(PPV) of elevated HbA1c levels for the presence of diabetic retinal changes was calculated tobe 62.66%. Conclusion: All the patients who had retinal disease on fundoscopy had HbA1clevels of more than 6.0% (PPV = 62.66) which means that elevated HbA1c levels warrant afundoscopic retinal examination to rule out diabetic retinopathy.

scholarly journals The Diagnostic Accuracy of an Intelligent and Automated Fundus Disease Image Assessment System with Lesion Quantitative Function (SmartEye) in Diabetic Patients

2019 ◽  
Author(s):  
Yi XU ◽  
Yongyi WANG ◽  
Bin LIU ◽  
Lin TANG ◽  
Liangqing LV ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Quantitative Analysis ◽  
Diagnostic Accuracy ◽  
Proliferative Diabetic Retinopathy ◽  
Screening Program ◽  
Assessment System ◽  
Diabetic Patients ◽  
Fundus Images ◽  
Cross Sectional ◽  
Community Healthcare

Abstract Background: With the diabetes mellitus (DM) prevalence increasing annually, the human grading of retinal images to evaluate DR has posed a substantial burden worldwide. SmartEye is a recently developed fundus image processing and analysis system with lesion quantification function for DR screening. It is sensitive to the lesion area and can automatically identify the lesion position and size. We reported the diabetic retinopathy (DR) grading results of SmartEye versus ophthalmologists in analyzing images captured with non-mydriatic fundus cameras in community healthcare centers, as well as DR lesion quantitative analysis results on different disease stages. Methods: This is a cross-sectional study. All the fundus images were collected from the Shanghai Diabetic Eye Study in Diabetics (SDES) program from Apr 2016 to Aug 2017. 19904 fundus images were acquired from 6013 diabetic patients. The grading results of ophthalmologists and SmartEye are compared. Lesion quantification of several images at different DR stages is also presented. Results: The sensitivity for diagnosing no DR, mild NPDR (non-proliferative diabetic retinopathy), moderate NPDR, severe NPDR, PDR (proliferative diabetic retinopathy) are 86.19%, 83.18%, 88.64%, 89.59%, and 85.02%. The specificity are 63.07%, 70.96%, 64.16%, 70.38%, and 74.79%, respectively. The AUC are PDR, 0.80 (0.79, 0.81); severe NPDR, 0.80 (0.79, 0.80); moderate NPDR, 0.77 (0.76, 0.77); and mild NPDR, 0.78 (0.77, 0.79). Lesion quantification results showed that the total hemorrhage area, maximum hemorrhage area, total exudation area, and maximum exudation area increase with DR severity. Conclusions: SmartEye has a high diagnostic accuracy in DR screening program using non-mydriatic fundus cameras. SmartEye quantitative analysis may be an innovative and promising method of DR diagnosis and grading. Keywords: Diabetic retinopathy, Screening, Digital imaging processing, Lesion quantification, Epidemiology.

scholarly journals The Diagnostic Accuracy of an Intelligent and Automated Fundus Disease Image Assessment System with Lesion Quantitative Function (SmartEye) in Diabetic Patients

2019 ◽  
Author(s):  
Yi XU ◽  
Yongyi WANG ◽  
Bin LIU ◽  
Lin TANG ◽  
Liangqing LV ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Quantitative Analysis ◽  
Diagnostic Accuracy ◽  
Proliferative Diabetic Retinopathy ◽  
Screening Program ◽  
Assessment System ◽  
Diabetic Patients ◽  
Fundus Images ◽  
Cross Sectional ◽  
Community Healthcare

Abstract Background With the diabetes mellitus (DM) prevalence increasing annually, the human grading of retinal images to evaluate DR has posed a substantial burden worldwide. SmartEye is a recently developed fundus image processing and analysis system with lesion quantification function for DR screening. It is sensitive to the lesion area and can automatically identify the lesion position and size. We reported the diabetic retinopathy (DR) grading results of SmartEye versus ophthalmologists in analyzing images captured with non-mydriatic fundus cameras in community healthcare centers, as well as DR lesion quantitative analysis results on different disease stages. Methods This is a cross-sectional study. All the fundus images were collected from the Shanghai Diabetic Eye Study in Diabetics (SDES) program from Apr 2016 to Aug 2017. 19904 fundus images were acquired from 6013 diabetic patients. The grading results of ophthalmologists and SmartEye are compared. Lesion quantification of several images at different DR stages is also presented. Results The sensitivity for diagnosing no DR, mild NPDR (non-proliferative diabetic retinopathy), moderate NPDR, severe NPDR, PDR (proliferative diabetic retinopathy) are 86.19%, 83.18%, 88.64%, 89.59%, and 85.02%. The specificity are 63.07%, 70.96%, 64.16%, 70.38%, and 74.79%, respectively. The AUC are PDR, 0.80 (0.79, 0.81); severe NPDR, 0.80 (0.79, 0.80); moderate NPDR, 0.77 (0.76, 0.77); and mild NPDR, 0.78 (0.77, 0.79). Lesion quantification results showed that the total hemorrhage area, maximum hemorrhage area, total exudation area, and maximum exudation area increase with DR severity. Conclusions SmartEye has a high diagnostic accuracy in DR screening program using non-mydriatic fundus cameras. SmartEye quantitative analysis may be an innovative and promising method of DR diagnosis and grading.

scholarly journals The Diagnostic Accuracy of an Intelligent and Automated Fundus Disease Image Assessment System with Lesion Quantitative Function (SmartEye) in Diabetic Patients

2019 ◽  
Author(s):  
Yi XU ◽  
Yongyi WANG ◽  
Bin LIU ◽  
Lin TANG ◽  
Liangqing LV ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Quantitative Analysis ◽  
Diagnostic Accuracy ◽  
Proliferative Diabetic Retinopathy ◽  
Screening Program ◽  
Assessment System ◽  
Diabetic Patients ◽  
Fundus Images ◽  
Cross Sectional ◽  
Community Healthcare

Abstract Background With the diabetes mellitus (DM) prevalence increasing annually, the human grading of retinal images to evaluate DR has posed a substantial burden worldwide. SmartEye is a recently developed fundus image processing and analysis system with lesion quantification function for DR screening. It is sensitive to the lesion area and can automatically identify the lesion position and size. We reported the diabetic retinopathy (DR) grading results of SmartEye versus ophthalmologists in analyzing images captured with non-mydriatic fundus cameras in community healthcare centers, as well as DR lesion quantitative analysis results on different disease stages. Methods This is a cross-sectional study. All the fundus images were collected from the Shanghai Diabetic Eye Study in Diabetics (SDES) program from Apr 2016 to Aug 2017. 19904 fundus images were acquired from 6013 diabetic patients. The grading results of ophthalmologists and SmartEye are compared. Lesion quantification of several images at different DR stages is also presented. Results The sensitivity for diagnosing no DR, mild NPDR (non-proliferative diabetic retinopathy), moderate NPDR, severe NPDR, PDR (proliferative diabetic retinopathy) are 86.19%, 83.18%, 88.64%, 89.59%, and 85.02%. The specificity are 63.07%, 70.96%, 64.16%, 70.38%, and 74.79%, respectively. The AUC are PDR, 0.80 (0.79, 0.81); severe NPDR, 0.80 (0.79, 0.80); moderate NPDR, 0.77 (0.76, 0.77); and mild NPDR, 0.78 (0.77, 0.79). Lesion quantification results showed that the total hemorrhage area, maximum hemorrhage area, total exudation area, and maximum exudation area increase with DR severity. Conclusions SmartEye has a high diagnostic accuracy in DR screening program using non-mydriatic fundus cameras. SmartEye quantitative analysis may be an innovative and promising method of DR diagnosis and grading.

scholarly journals Intravitreal injections during the COVID-19 pandemic era

2021 ◽  
Vol 2 (2) ◽  
pp. 50-55
Author(s):  
Selda Celik Dulger ◽  
Mehmet Citirik ◽  
Esra Bahadir Camgoz ◽  
Mehmet Yasin Teke
Keyword(s):  
Diabetic Retinopathy ◽  
Demographic Data ◽  
Retinal Disease ◽  
Tertiary Hospital ◽  
Cross Sectional Study ◽  
Age Related Macular Degeneration ◽  
Intravitreal Injections ◽  
Cross Sectional ◽  
Age Related ◽  
Number Of Patients

Background: This study aimed to evaluate the clinical characteristics and changes in the number of patients receiving intravitreal injections (IVIs) at a tertiary hospital during the coronavirus disease 2019 (COVID-19) pandemic as compared to the pre-pandemic period. Methods: This retrospective, cross-sectional study included 3,211 patients with retinal disease, who received IVIs of anti-vascular endothelial growth factor (anti-VEGF) between January and May 2020. This 5-month period was divided into a pre-pandemic and a pandemic period. Clinical and demographic data were collected and were compared between the patients in each period. All COVID-19 infection precautions were implemented to minimize the potential transmission of COVID-19 to both healthcare workers and patients. Results: A total of 3,211 IVIs were administered to patients with diabetic retinopathy, age-related macular degeneration, retinal vein occlusion, and other retinal conditions. Diabetic retinopathy was the most common indication for treatment in the pre-pandemic as well as pandemic periods. Bevacizumab (Avastin, Roche) was the most common IVI type, followed by aflibercept (Eylea, Bayer). Of 3,211 IVIs, 2,943 (91.7%) were administered during the pre-pandemic period and 268 (8.3%) during the pandemic period. There was a statistically significant decrease in injections between the pre-pandemic and pandemic periods, with an overall reduction of 90.8% in IVIs (P < 0.05). No cases of confirmed transmission of COVID-19 orcomplications associated with IVIs were recorded. Conclusions: This study showed that the number of IVIs and patient visits decreased significantly, by more than 10-fold, during the lockdown period. These findings show that COVID-19 has turned the management of sight-threatening eye diseases into a challenging process and must be addressed if future healthcarerestrictions are imposed.

scholarly journals Exploration of Retinopathy Disease using Machine Learning Methodology

2019 ◽  
Vol 8 (6S) ◽  
pp. 914-921
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Diabetic Retinopathy ◽  
Color Image ◽  
Research Work ◽  
Input Image ◽  
Fundus Images ◽  
Green Color ◽  
Research Institutes ◽  
Segmentation Algorithms

The whole world is affected with the problem of Diabetic Retinopathy. Whenever a patient has diabetes, it starts affects human body sensitive parts. So the situation becomes very dangerous for the person. Here in this research work it is tried to detect Hemorrhages and micro aneurysms in multiple fundus images collected from various research institutes worldwide and available datasets. In initial it is required to separate RGB colors from the image. The green color is used for further processing. Further the grey color image is extracted for getting the texture of the input image. The feature extraction algorithms are used to classification. So that it is possible to predict the current situation of the retinal image. Once the situation is classified the segmentation algorithms are used using adaptive thresholding segmentation

scholarly journals The Diagnostic Accuracy of an Intelligent and Automated Fundus Disease Image Assessment System with Lesion Quantitative Function (SmartEye) in Diabetic Patients

2019 ◽  
Author(s):  
Yi XU ◽  
Yongyi WANG ◽  
Bin LIU ◽  
Lin TANG ◽  
Liangqing LV ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Quantitative Analysis ◽  
Diagnostic Accuracy ◽  
Proliferative Diabetic Retinopathy ◽  
Screening Program ◽  
Assessment System ◽  
Diabetic Patients ◽  
Fundus Images ◽  
Cross Sectional ◽  
Community Healthcare

Abstract Background With the diabetes mellitus (DM) prevalence increasing annually, the human grading of retinal images to evaluate DR has posed a substantial burden worldwide. SmartEye is a recently developed fundus image processing and analysis system with lesion quantification function for DR screening. It is sensitive to the lesion area and can automatically identify the lesion position and size. We reported the diabetic retinopathy (DR) grading results of SmartEye versus ophthalmologists in analyzing images captured with non-mydriatic fundus cameras in community healthcare centers, as well as DR lesion quantitative analysis results on different disease stages. Methods This is a cross-sectional study. All the fundus images were collected from the Shanghai Diabetic Eye Study in Diabetics (SDES) program from Apr 2016 to Aug 2017. 19904 fundus images were acquired from 6013 diabetic patients. The grading results of ophthalmologists and SmartEye are compared. Lesion quantification of several images at different DR stages is also presented. Results The sensitivity for diagnosing no DR, mild NPDR (non-proliferative diabetic retinopathy), moderate NPDR, severe NPDR, PDR (proliferative diabetic retinopathy) are 86.19%, 83.18%, 88.64%, 89.59%, and 85.02%. The specificity are 63.07%, 70.96%, 64.16%, 70.38%, and 74.79%, respectively. The AUC are PDR, 0.80 (0.79, 0.81); severe NPDR, 0.80 (0.79, 0.80); moderate NPDR, 0.77 (0.76, 0.77); and mild NPDR, 0.78 (0.77, 0.79). Lesion quantification results showed that the total hemorrhage area, maximum hemorrhage area, total exudation area, and maximum exudation area increase with DR severity. Conclusions SmartEye has a high diagnostic accuracy in DR screening program using non-mydriatic fundus cameras. SmartEye quantitative analysis may be an innovative and promising method of DR diagnosis and grading.

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.

Sign in / Sign up

Export Citation Format

Share Document