diabetic proliferative retinopathy
Recently Published Documents


TOTAL DOCUMENTS

19
(FIVE YEARS 5)

H-INDEX

6
(FIVE YEARS 0)

Author(s):  
Abdelali Elmoufidi ◽  
Ayoub Skouta ◽  
Said Jai-Andaloussi ◽  
Ouail Ouchetto

In the area of ophthalmology, glaucoma affects an increasing number of people. It is a major cause of blindness. Early detection avoids severe ocular complications such as glaucoma, cystoid macular edema, or diabetic proliferative retinopathy. Intelligent artificial intelligence has been confirmed beneficial for glaucoma assessment. In this paper, we describe an approach to automate glaucoma diagnosis using funds images. The setup of the proposed framework is in order: The Bi-dimensional Empirical Mode Decomposition (BEMD) algorithm is applied to decompose the Regions of Interest (ROI) to components (BIMFs+residue). CNN architecture VGG19 is implemented to extract features from decomposed BEMD components. Then, we fuse the features of the same ROI in a bag of features. These last very long; therefore, Principal Component Analysis (PCA) are used to reduce features dimensions. The bags of features obtained are the input parameters of the implemented classifier based on the Support Vector Machine (SVM). To train the built models, we have used two public datasets, which are ACRIMA and REFUGE. For testing our models, we have used a part of ACRIMA and REFUGE plus four other public datasets, which are RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF. The overall precision of 98.31%, 98.61%, 96.43%, 96.67%, 95.24%, and 98.60% is obtained on ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, by using the model trained on REFUGE. Again an accuracy of 98.92%, 99.06%, 98.27%, 97.10%, 96.97%, and 96.36% is obtained in the ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, using the model training on ACRIMA. The experimental results obtained from different datasets demonstrate the efficiency and robustness of the proposed approach. A comparison with some recent previous work in the literature has shown a significant advancement in our proposal.


Author(s):  
L.N. Boriskina ◽  
◽  
A.S. Zotov ◽  
A.S. Balalin ◽  
S.V. Balalin ◽  
...  

Objective. To evaluate the results of complicated cataract surgery in patients with neovascular glaucoma in case of diabetic proliferative retinopathy or postthrombotic macular edema. Material and methods. A retrospective study of the complicated cataract surgery with IOL implantation results was performed in 38 patients (38 eyes) with neovascular glaucoma. The first stage was Lucentis intravitreal injection, then after 2 weeks intraocular pressure (IOP) under combined medical therapy was determined: 1) if IOP was <25 mm Hg, then phacoemulsification was performed; 2) if IOP remained >25 mm Hg, the second stage was transscleral cyclophotocoagulation, and 2 weeks later – cataract phacoemulsification. Results. All patients with neovascular glaucoma had significant increase of the best corrected visual acuity from the initial level on the 1st day, 1- and 3-months post-op. IOP values under medical treatment corresponded to the range of the average statistical norm. There was no recurrence of neovascularization or IOP increase. Conclusion. The application of Lucentis intravitreal injections as well as IOP lowering to the average statistical norm range under medication or laser surgery provide the basis for an effective and safe complicated cataract surgery with IOL implantation in patients with neovascular glaucoma in case of diabetic proliferative retinopathy or post-thrombotic macular edema. Key words: cataract, neovascular glaucoma, phacoemulsification.


2021 ◽  
Author(s):  
Abdelali ELMOUFIDI ◽  
Said Jai-andaloussi

Abstract In the area of ophthalmology, glaucoma affects an increasing number of people. It is a major cause of blindness. Early detection avoids severe ocular complications such as glaucoma, cystoid macular edema, or diabetic proliferative retinopathy. Intelligent artificial has been confirmed beneficial for glaucoma assessment. In this paper, we describe an approach to automate glaucoma diagnosis using funds images. The setup of the proposed framework is, in order: The Bi-dimensional Empirical Mode Decomposition (BEMD) algorithm is applied to decompose the Regions of Interest (ROI) to components (BIMFs + residue). CNN architecture VGG19 is implemented to extract features from decomposed BEMD components. Then, we fuse the features of the same ROI in a bag of features. These last are very long; therefore, Principal Component Analyses (PCA) are used to reduce features dimensions. Obtained bags of features are the input parameters of the implemented classifier based on the Support Vector Machine (SVM). To train the built models, we have used two public datasets, which are ACRIMA and REFUGE. For testing our models, we have used a part of ACRIMA and REFUGE plus four other public datasets, which are RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF. The overall accuracy of 98.31%, 98.61%, 96.43%, 96.67%, 95.24%, and 98.60% are obtained on ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, by using the model trained on REFUGE. Against an accuracy of 98.92%, 99.06%, 98.27%, 97.10%, 96.97%, and 96.36% are obtained on ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, using the model training on ACRIMA. Obtained experimental results from different datasets demonstrate the efficiency and robustness of the proposed approach. A comparison with some recent previous work in the literature has shown a significant advancement in our proposal.


Author(s):  
A. M. Ruban

The article presents the some approaches to create a system support of making decision during vitrectomy in patients with diabetic proliferative retinopathy, promotes objective assessment of individual risk-management for patient and allows optimize ophthalmological care for them.


Author(s):  
A. M. Ruban

he article propose a new system support of making decision during vitrectomy in patients with diabetic proliferative retinopathy, according by objective assessment of individual risk-management. The article presents some comparative results (anatomical and functional results, rate of complications) between two groups: with new and standard approaches.


Author(s):  
А. M. Ruban

The article presents the some approaches to create a system support of making decision during miniinvasive diabetic vitrectomy in patients with diabetic proliferative retinopathy, promotes objective assessment of individual risk-management for patient and allows optimize ophthalmological care for them. This was a retrospective study of 145 patients (145 eyes) who underwent combined sutureless vitrectomy for the complications of proliferative diabetic retinopathy. The study and analysis of the clinical characteristics (N-145) and 60 kinds of complications have selected 33 factors, characterizing the general condition of the patient, ophthalmic status which have been integrated into the risk map. Prediction of surgical intervention was determined by the amount of points. Total risk was studied in three samples of “training” (145 patients), «control» (50 patients) and the “examination” (30 cases). Based on 225 observations determined the dependence of an adverse operation of points of risk and identified 4 risk levels: low risk (first stage), the likelihood of an adverse outcome is less than 0.05; average risk is the likelihood of an adverse outcome is 0.05-0.4; high risk-the probability of an adverse up 0.41-0.9 and extreme risks, the likelihood of an adverse outcome is greater than 0.9.


Sign in / Sign up

Export Citation Format

Share Document