scholarly journals Deep Neural Network-Based Method for Detecting Central Retinal Vein Occlusion Using Ultrawide-Field Fundus Ophthalmoscopy

2018 ◽  
Vol 2018 ◽  
pp. 1-6 ◽  
Author(s):  
Daisuke Nagasato ◽  
Hitoshi Tabuchi ◽  
Hideharu Ohsugi ◽  
Hiroki Masumoto ◽  
Hiroki Enno ◽  
...  
Keyword(s):  
Neural Network ◽  
Retinal Vein Occlusion ◽  
Central Retinal Vein Occlusion ◽  
Medical Center ◽  
Characteristic Curve ◽  
Support Vector ◽  
Fundus Images ◽  
Vein Occlusion ◽  
Svm Model ◽  
Central Retinal Vein

The aim of this study is to assess the performance of two machine-learning technologies, namely, deep learning (DL) and support vector machine (SVM) algorithms, for detecting central retinal vein occlusion (CRVO) in ultrawide-field fundus images. Images from 125 CRVO patients (n=125 images) and 202 non-CRVO normal subjects (n=238 images) were included in this study. Training to construct the DL model using deep convolutional neural network algorithms was provided using ultrawide-field fundus images. The SVM uses scikit-learn library with a radial basis function kernel. The diagnostic abilities of DL and the SVM were compared by assessing their sensitivity, specificity, and area under the curve (AUC) of the receiver operating characteristic curve for CRVO. For diagnosing CRVO, the DL model had a sensitivity of 98.4% (95% confidence interval (CI), 94.3–99.8%) and a specificity of 97.9% (95% CI, 94.6–99.1%) with an AUC of 0.989 (95% CI, 0.980–0.999). In contrast, the SVM model had a sensitivity of 84.0% (95% CI, 76.3–89.3%) and a specificity of 87.5% (95% CI, 82.7–91.1%) with an AUC of 0.895 (95% CI, 0.859–0.931). Thus, the DL model outperformed the SVM model in all indices assessed (P<0.001 for all). Our data suggest that a DL model derived using ultrawide-field fundus images could distinguish between normal and CRVO images with a high level of accuracy and that automatic CRVO detection in ultrawide-field fundus ophthalmoscopy is possible. This proposed DL-based model can also be used in ultrawide-field fundus ophthalmoscopy to accurately diagnose CRVO and improve medical care in remote locations where it is difficult for patients to attend an ophthalmic medical center.

scholarly journals Detection of Multi-Class Retinal Diseases Using Artificial Intelligence: An Expeditious Learning Using Deep CNN with Minimal Data

2019 ◽  
Vol 12 (3) ◽  
pp. 1577-1586 ◽  
Author(s):  
Karthikeyan S. ◽  
Sanjay Kumar P. ◽  
R J Madhusudan Madhusudan ◽  
S K Sundaramoorthy Sundaramoorthy ◽  
P K Krishnan Namboori3
Keyword(s):  
Real Time ◽  
Retinal Vein Occlusion ◽  
Central Retinal Vein Occlusion ◽  
Research Work ◽  
Diagnostic Strategy ◽  
Fundus Images ◽  
Vein Occlusion ◽  
Deep Cnn ◽  
The Right ◽  
Central Retinal Vein

The health-related complications such as diabetes, macular degeneration, inflammatory conditions, ageing and fungal infections may cause damages to the retina and the macula of the eye, leading to permanent vision loss. The major diseases associated with retina are Arteriosclerotic retinopathy (AR), Central retinal vein occlusion (CRVO), Branch retinal artery occlusion (BRAO), Coat's disease (CD) and Hemi-Central Retinal Vein Occlusion (HRVO). The symptomatic variations among these disorders are relatively confusing so that a systematic diagnostic strategy is difficult to set in. Therefore, an early detection device is required that is capable of differentiating the various ophthalmic complications and thereby helping in providing the right treatment to the patient at the right time. In this research work, 'Deep Convolution Neural Networks (Deep CNN) based machine learning approach has been used for the detection of the twelve major retinal complications from the minimal set of fundus images. The model was further cross-validated with real-time fundus images. The model is found to be superior in its efficiency, specificity and ability to minimize the misclassification. The “multi-class retinal disease” model on further cross-validation with real-time fundus image of the gave an accuracy of 95.63 %, validation accuracy of 92.99 % and F1 score of 91.96 %. The multi-class model is found to be a theranostic clinical support system for the ophthalmologist for diagnosing different kinds of retinal problems, especially BRAO, BRVO, CRAO, CD, DR, HRVO, HP, HR, and CN.

scholarly journals Using ultra-widefield red channel images to improve the detection of ischemic central retinal vein occlusion

PLoS ONE ◽  
2021 ◽  
Vol 16 (11) ◽  
pp. e0260383
Author(s):  
Akinori Sato ◽  
Ryo Asaoka ◽  
Shin Tanaka ◽  
Koichi Nagura ◽  
Yui Tanaka ◽  
...  
Keyword(s):  
Retinal Vein Occlusion ◽  
Central Retinal Vein Occlusion ◽  
Linear Mixed Model ◽  
Fundus Images ◽  
Vein Occlusion ◽  
Fundus Imaging ◽  
Significant Difference ◽  
Group A ◽  
Group B ◽  
Central Retinal Vein

Purpose To examine the usefulness of red channel fundus imaging to detect the ischemic status in eyes with central retinal vein occlusion (CRVO). Methods Ultra-widefield (UWF) fundus images were obtained from 42 eyes with CRVO. Twenty-one eyes were ischemic, and 21 eyes were non-ischemic. Rubeosis was found in 11 ischemic eyes. UWF images were split into red and green channels using ImageJ software. Both the color and red channel images were used to predict the presence or absence of ischemia when examined by masked graders. The sensitivity and specificity of UWF imagings for the detection of ischemia were calculated in Group A (total 42 eyes), Group B (32 eyes excluding non-rubeotic ischemic CRVO) and Group C (31 eyes excluding rubeotic ischemic CRVO), respectively. Moreover, a linear mixed model was conducted to investigate the relationship between the type of images and the accuracy of prediction in each group. Results No significant difference in the sensitivity of color fundus imaging was seen between Group A and Group B. By contrast, a significant difference in the sensitivity of red channel imaging was seen between Group A and Group B (p = 0.031). The accuracies of the predictions were not associated with the type of image in Group A and Group B, but were significantly associated in Group C (p = 0.026). Conclusions UWF red channel imaging enabled more accurate detection of the ischemic status, compared with color fundus images, especially in non-rubeotic CRVO eyes.

Hypercoagulability and High Lipoprotein(a) Levels in Patients with Central Retinal Vein Occlusion

1994 ◽  
Vol 72 (01) ◽  
pp. 039-043 ◽  
Author(s):  
Francesco Bandello ◽  
Silvana Vigano’ D’Angelo ◽  
Mariella Parlavecchia ◽  
Alessandra Tavola ◽  
Patrizia Della Valle ◽  
...  
Keyword(s):  
Retinal Vein Occlusion ◽  
Central Retinal Vein Occlusion ◽  
Specific Treatment ◽  
Fibrin Deposition ◽  
Heparin Cofactor Ii ◽  
Lipoprotein A ◽  
Vein Occlusion ◽  
Acute Event ◽  
D Dimer ◽  
Central Retinal Vein

SummaryA series of coagulation parameters and lipoprotein(a) (Lp(a)) were explored in plasma from 40 patients with central retinal vein occlusion (CRVO, non-ischemic type n = 12; ischemic type n = 28) free of local and systemic predisposing factors, 1 to 12 months after the acute event. Forty age- and sex-matched patients with cataract served as controls. Prothrombin fragment 1.2 (FI.2), D-dimer, FVII:C - but not FVII: Ag - were higher and fibrinogen was lower in CRVO patients than in controls. Patients with non-ischemic CRVO had higher FI .2 and FVII:C and lower heparin cofactor II than patients with ischemic CRVO. Lp(a) levels greater than 300 mg/1 were observed in 12 patients with CRVO and in 4 controls (30% vs 10%, p <0.025). Patients with high Lp(a) - consistently associated with the S2 phenotype - had higher FVII:C, FVII:C/Ag ratio, and fibrinogen than the remaining CRVO patients. Plasma FI.2 and D-dimer correlated fairly in controls (r = 0.41) and patients with normal Lp(a) levels (r = 0.55), but they did not in the group of patients with high Lp(a) (r = 0.19), where the latter parameter was negatively related to D-dimer (r = −0.55). There was no dependence of the abnormalities observed on the time elapsed from vein occlusion. The findings of activated FVII and high FI.2, D-dimer, and Lp(a) are not uncommon in patients with CRVO. Increased thrombin formation with fibrin deposition and impaired fibrinolysis may play a role in the pathophysiology of CRVO and require specific treatment

Retinal Vascular Occlusive Disorders - Risk Factors

2018 ◽  
Vol 3 (02) ◽  
Author(s):  
Shivcharan Lal Chandravanshi, Sunil Kumar Shrivastava, Priyanka Agnihotri, Smriti Gupta
Keyword(s):  
Risk Factors ◽  
Retinal Vein Occlusion ◽  
Central Retinal Vein Occlusion ◽  
Branch Retinal Vein Occlusion ◽  
Retinal Artery Occlusion ◽  
Artery Occlusion ◽  
Vein Occlusion ◽  
Department Of Ophthalmology ◽  
Retinal Artery ◽  
Central Retinal Vein

Aims and Objective - The aim of the present study is to identify risk factors associated with different retinal vascular occlusive diseases (RVOD), such as central retinal artery occlusion (CRAO), hemi-retinal artery occlusion (HRAO), branch retinal artery occlusion (BRAO), cilioretinal artery occlusion (Cilio-RAO), central retinal vein occlusion (CRVO), branch retinal vein occlusion (BRVO), and hemi-retinal vein occlusion (HRVO). Patients and Method - A cross-sectional study on 114 consecutive subjects, aged 24-96 years who have attended at the outpatient department of ophthalmology at Shyam Shah Medical College, Rewa, MP, were included in the study. The Duration of study was January 2016 to December 2017. Only patients with CRAO, BRAO, HRAO, Cilio-RAO, CRVO, BRVO, and HRVO were included in the study. Other retinal vascular disorders such as diabetic vaso-occlusive disease, anterior and posterior ischemic and non-ischemic neuropathy, hypertensive retinopathy, sickle cell retinopathy, retinal telangiectasia, retinopathy of prematurity, were excluded from study. Results - We have included 114 patients, 64 cases (56.14%) males, 50 (43.85%) females, aged 56+/-8 years (range 24-96 years).  Bilateral retinal vascular occlusive disorders were seen in only 4 cases (3.5%). Two patients have bilateral CRVO followed by one case of bilateral BRVO and one case of bilateral CRAO.  Out of 114 patients, branch retinal vein occlusion was seen in 62 cases (54.38%), followed by central retinal vein occlusion in 36 cases (31.57%), CRAO in 8 cases (7.01%), and hemi- retinal vein occlusion in 4 cases (3.50%). Hypertension was the most common, (40 cases, 35.08%) risk factor identified for retinal vascular occlusive disorders followed by diabetes 24 cases (21.05%), combined diabetes and hypertension in 22 cases (19.29%), and atherosclerosis in 18 cases (15.78%). Conclusions - Retinal vascular occlusive diseases have systemic as well as ocular risk factors. Understanding of these risk factors is essential for proper treatment of RVOD. Timely identification of risk factors for RVOD may helpful in decreasing ocular and systemic morbidity in these patients.

Sign in / Sign up

Export Citation Format

Share Document