As for clinical classification of diabetic retinopathy (review)

2021 ◽  
pp. 77-85
Author(s):  
K.N. Akhtyamov ◽  
◽  
M.R. Kalanov ◽  
R.M. Zainullin ◽  
T.A. Khalimov ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Diabetic Retinopathy ◽  
Surgical Treatment ◽  
Morphological Changes ◽  
Clinical Classification ◽  
Lively Discussion ◽  
Optimal Classification ◽  
The Subject ◽  
Combined Interventions

Currently no unified generally accepted classification of intraocular changes due to diabetes mellitus (DM), in particular, diabetic retinopathy (DR). The methodological heterogeneity of the existing classifications is largely due to the different directions of their application. Some classifications are optimal for the choice of surgical treatment tactics, others - for laser and / or combined interventions. Obviously, the valuation of any classification lies in the completeness whole palette of available clinical and morphological changes considering staging pathogenetic process. Therefore, the search for optimal classification of DR that meets current possibilities of treating vitreoretinal pathology is the subject of a lively discussion. Key words: classifications, diabetic retinopathy, advantages and limitations.

C-peptide and the classification of diabetes mellitus patients in the Early treatment diabetic retinopathy study report number 6

1993 ◽  
Vol 3 (1) ◽  
pp. 9-17 ◽  
Author(s):  
Mary Jane Prior ◽  
Thaddeus Prout ◽  
Dayton Miller ◽  
Robin Ewart ◽  
Dinesh Kumar
Keyword(s):  
Diabetes Mellitus ◽  
Diabetic Retinopathy ◽  
Early Treatment ◽  
C Peptide ◽  
Study Report

scholarly journals Deep Learning based Method for Multi-class Classification of Diabetic Retinopathy

2021 ◽  
Vol 2 (2) ◽  
pp. 1-5
Author(s):  
Komal Damodara ◽  
Keyword(s):  
Diabetes Mellitus ◽  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Blood Sugar Level ◽  
Retinal Disease ◽  
Fundus Imaging ◽  
Retinal Blood Vessels ◽  
The World ◽  
Multi Class Classification

Diabetes mellitus is a form of diabetes with secondary microvascular complication leading to renal dysfunction and retinal loss also termed as diabetic retinopathy. Retinopathy is grave form of retinal disease. It is the leading cause of blindness in the world. Blockage of tiny minute retinal blood vessels due to the high blood sugar level is the reason why retinopathy leads to blindness or loss of vision. This study serves the purpose of deep learning-based diagnosis of Diabetic retinopathy using the fundus imaging of the eye. In this study architectures such as VGG 16 and VGG 19 are deployed in order to classify the images into 5 categories. The performance of the two models were compared. The highest accuracy is 77.67% when using the VGG 16 pre-trained model.

scholarly journals Surgical Treatment of Diabetic Recurrent Vitreous Hemorrhage and Traction Retinal Detachment

2018 ◽  
pp. 202-207
Keyword(s):  
Diabetes Mellitus ◽  
Vascular Endothelial Growth Factor ◽  
Diabetic Retinopathy ◽  
Surgical Treatment ◽  
High Frequency ◽  
Vitreoretinal Surgery ◽  
Vitreous Hemorrhage ◽  
Vascular Endothelial ◽  
Endothelial Growth Factor ◽  
Recurrent Vitreous Hemorrhage

Although the irreversible proliferative complications of diabetes are less visible with anti-vascular endothelial growth factor (anti-VEGF) agents, surgical treatment is still important for these groups of patients; because of the high frequency of diabetes mellitus. The most common indications for vitreoretinal surgery for proliferative diabetic retinopathy are vitreous hemorrhages and tractional retinal detachments. This review summarized the surgical treatment of these two complications.

scholarly journals Prevalence and characteristics of primary open-angle glaucoma in patients with diabetic retinopathy in type 2 diabetes mellitus

2021 ◽  
Vol 9 (1) ◽  
pp. 14-20
Author(s):  
S.Yu. Mogilevskyy ◽  
K.A. Hudzenko
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Diabetic Retinopathy ◽  
Primary Open Angle Glaucoma ◽  
Open Angle Glaucoma ◽  
Stage I ◽  
Open Angle

Background. Numerous literature data made it possible to establish the dependence of primary open-angle glaucoma (POAG) in patients with diabetic retinopathy (DR) on type 2 diabetes mellitus (DM2). The purpose was to determine the prevalence and characteristics of primary open-angle glaucoma in patients with diabetic retinopathy in type 2 diabetes mellitus. Material and me­thods. One thousand four hundred and fifty patients with DM2 were examined, in whom the stage of DR was determined according to the classification of American Academy of Ophthalmology (2002). POAG stage was established according to the classification of A.P. Nesterov and A.Ya. Bunin (1976) and classification of perimetric changes by glaucoma stages. The age of patients, 970 (66.9 %) men and 480 (33.1 %) women, was from 45 to 75 years. The duration of DM2 was from 2 to 15 years. For statistical studies, MedStat and MedCalc v.15.1 (Medcalc Software bvba) were used. Results. In patients with DM2 and DR of different stages, the prevalence of POAG amounted to 20.8 %, which is 4–6 times higher than in the general population. Among individuals with DR stage I (no retinopathy), 71.6 % had POAG stage I and II, among patients with non-proliferative DR, 87.6 % had stages II and III, and among those with proliferative DR, 78.4 % had stages III and IV. Among all patients with DR and POAG, the proportion of normal tension glaucoma was 18.6 %, which did not differ from that in POAG without DM2. 42.9 % of patients initially had the development of DM2 in past medical history, joined by POAG in 1–7 years, and 57.1 % first had POAG, joined by DM2 in 1–8 years. Depending on the duration of the disease, the severity of both DR and POAG increased, which indicated the dependence of DR and POAG severity on disease duration and acceleration of their development if they combined. Conclusions. The results of the study confirmed the wider pre­valence and mutual burden of DR course in DM2 and POAG, which justifies the need to study the general mechanisms of their pathogenesis.

scholarly journals Building the knowledge base for non-combinable codes according to the Korean Standard Classification of Diseases

2018 ◽  
Vol 7 (3.33) ◽  
pp. 223
Author(s):  
Mijung Kim ◽  
. .
Keyword(s):  
Diabetes Mellitus ◽  
Knowledge Base ◽  
Disease Classification ◽  
Authoring Tool ◽  
Classification Rules ◽  
Classification Of Diseases ◽  
Combinatorial Codes ◽  
Standard Classification ◽  
The Subject

The purpose of this study is to develop a knowledge base for non-combinable combinatorial codes to improve the accuracy of disease classification. We defined the rules related to non-combinable codes according to the list of code pairs proposed by the HIRA and the KCD-7 classification rules. A knowledge base was created according to defined rules and verified. To validate the knowledge base, inpatients who were billed for diabetes mellitus in December 2016 were selected as the subject of the study. As a result, the number of combinatorial codes proposed by the HIRA was 1,195, but the number of code pairs generated in the knowledge base was 25,439. Non-combinable codes by confirming with an indication of the HIRA have discovered 1,391 cases. As a result of verification with the code pair of the proposed knowledge base, 100 combinations were found. Non-combinable codes by confirming with an indication of the HIRA have discovered 1,391 cases. As a result of verification with the code pair of the proposed knowledge base, 3,525 combinations were found. It is meaningful that a convenient authoring tool that can automatically catch combinatorial codes was developed to build a knowledge base.  

scholarly journals Comparison of Convolutional Neural Network Model in Classification of Diabetic Retinopathy

2019 ◽  
Vol 9 (2) ◽  
pp. 141
Author(s):  
Hartanto Ignatius ◽  
Ricky Chandra ◽  
Nicholas Bohdan ◽  
Abdi Dharma
Keyword(s):  
Neural Network ◽  
Diabetes Mellitus ◽  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Network ◽  
Contrast Enhancement ◽  
Neural Network Model ◽  
Reasonable Accuracy ◽  
Deep Architecture

<p class="JGI-AbstractIsi">Untreated diabetes mellitus will cause complications, and one of the diseases caused by it is Diabetic Retinopathy (DR). Machine learning is one of the methods that can be used to classify DR. Convolutional Neural Network (CNN) is a branch of machine learning that can classify images with reasonable accuracy. The Messidor dataset, which has 1,200 images, is often used as a dataset for the DR classification. Before training the model, we carried out several data preprocessing, such as labeling, resizing, cropping, separation of the green channel of images, contrast enhancement, and changing image extensions. In this paper, we proposed three methods of DR classification: Simple CNN, Le-Net, and DRnet model. The accuracy of testing of the several models of test data was 46.7%, 51.1%, and 58.3% Based on the research, we can see that DR classification must use a deep architecture so that the feature of the DR can be recognized. In this DR classification, DRnet achieved better accuracy with an average of 9.4% compared to Simple CNN and Le-Net model.</p>

scholarly journals Hemophthalmia after surgical treatment of diabetic retinopathy in patients with type 2 diabetes mellitus

2021 ◽  
Vol 9 (3) ◽  
pp. 14-20
Author(s):  
S.S. Lytvynenko
Keyword(s):  
Diabetes Mellitus ◽  
Risk Factors ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Diabetic Retinopathy ◽  
Surgical Treatment ◽  
Glycated Hemoglobin ◽  
Vitreous Hemorrhage ◽  
History Of

Background. In patients with type 2 diabetes mellitus (DM2) and diabetic retinopathy (DR), vitreous hemorrhage is one of the most common complications after pars plana vitrectomy (PPV) and ranges from 12 to 63 %. The study was aimed to analyze the frequency and causes of the development of hemophthalmia after surgical treatment of diabetic retinopathy in patients with type 2 diabetes mellitus. Materials and methods. The study involved 118 patients (118 eyes) with type 2 diabetes mellitus and DR, who were divided into three groups: the first group — with initial non-proliferative DR (NPDR; 28 eyes), the second group — with moderate to severe NPDR (49 eyes) and the third group — with proliferative DR (РDR; 41 eyes). The age of patients ranged from 44 to 84 years, men — 52 (44.1 %), women — 66 (55.9 %). The study did not include the patients with severe PDR and tractional retinal detachment or massive hemorrhage that required silicone oil tamponade of the vitreal cavity. All patients underwent closed subtotal vitrectomy 25G with panretinal laser photocoagulation and tamponade with an air-gas C3F8 mixture or the operation was completed with BSS plus solution injected into the vitreal cavity. Patients were examined based on a standard protocol of clinical and ophthalmological studies. Results. Within three months after vitrectomy, 33.1 % of patients developed postoperative hemophthalmia, which happened more often in РDR (39.0 %). In most cases (71.4 %), the preoperative hemophthalmia in РDR was accompanied by the development of postoperative hemophthalmia. Gender did not significantly impact the incidence of postoperative hemophthalmia. Patients with hemophthalmia were 9.3 years older than patients without hemophthalmia (p < 0.001), which affected both men and women equally. Patients with hemophthalmia had a longer history of type 2 diabetes mellitus compared to those wi­thout it (three years; p = 0.007), which was confirmed for men: men with hemophthalmia had a longer history of type 2diabetes mellitus than those without hemophthalmia (seven years; p = 0.026). Elevated blood levels of glycated hemoglobin (HbA1c) and a high score on the ETDRS scale are the risk factors for the development of postoperative hemophthalmos in patients with РDR. Conclusions. A study within three months after PPV in patients with DR and type 2 diabetes mellitus found that 33.1 % of patients developed postoperative hemophthalmia, which occurred more often in РDR (39.0 %). In most cases (71.4 %), the preoperative hemophthalmos in РDR was accompanied by the development of postoperative hemophthalmia. The risk factors for postoperative hemophthalmia after vitrectomy in type 2 diabetes mellitus and DR were age and diabetes duration, and for РDR — the presence of preoperative hemophthalmia, increased blood glycated hemoglobin, and a high score on the ETDRS scale.

Deep Learning-Based Diabetic Retinopathy Detection

2021 ◽  
Vol 11 (3) ◽  
pp. 38-48
Author(s):  
Mohamed Jebran P. ◽  
Sufia Banu
Keyword(s):  
Diabetes Mellitus ◽  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Classification Performance ◽  
Learning Problems ◽  
Deep Learning Algorithm ◽  
Lesion Level ◽  
Fundus Photographs

Artificial intelligence (AI) is rapidly evolving from machine learning (ML) to deep learning (DL), which has ignited particular interest in ophthalmology as well. Deep learning has been applied in ophthalmology to fundus photographs, which achieve robust classification performance in the detection of diabetic retinopathy (DR). Diabetic retinopathy is a progressive condition observed in people who have had multiple years of diabetes mellitus. This paper focuses on examining how a deep learning algorithm can be applied for the detection and classification of diabetic retinopathy, both at the image level and at the lesion level. The performance of various neural networks is summarized by taking into account the sensitivity, precision, accuracy with respect to the size of the test datasets. Deep learning problems are discussed at the end.

scholarly journals Comparison of Convolutional Neural Network Model in Classification of Diabetic Retinopathy

2019 ◽  
Vol 9 (2) ◽  
pp. 141-150
Author(s):  
Hartanto Ignatius ◽  
Ricky Chandra ◽  
Nicholas Bohdan ◽  
Abdi Dharma
Keyword(s):  
Neural Network ◽  
Diabetes Mellitus ◽  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Network ◽  
Contrast Enhancement ◽  
Neural Network Model ◽  
Reasonable Accuracy ◽  
Deep Architecture

Untreated diabetes mellitus will cause complications, and one of the diseases caused by it is Diabetic Retinopathy (DR). Machine learning is one of the methods that can be used to classify DR. Convolutional Neural Network (CNN) is a branch of machine learning that can classify images with reasonable accuracy. The Messidor dataset, which has 1,200 images, is often used as a dataset for the DR classification. Before training the model, we carried out several data preprocessing, such as labeling, resizing, cropping, separation of the green channel of images, contrast enhancement, and changing image extensions. In this paper, we proposed three methods of DR classification: Simple CNN, Le-Net, and DRnet model. The accuracy of testing of the several models of test data was 46.7%, 51.1%, and 58.3% Based on the research, we can see that DR classification must use a deep architecture so that the feature of the DR can be recognized. In this DR classification, DRnet achieved better accuracy with an average of 9.4% compared to Simple CNN and Le-Net model.

scholarly journals Analysis of Initial Clinical and CT Features of COVID-19 Pneumonia in Different Clinical Types

2020 ◽  
Author(s):  
Wei Li ◽  
Wenjun Yu ◽  
Jianwei Liao ◽  
Lin Yao ◽  
Yijie Fang ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Risk Factors ◽  
Chest Ct ◽  
Lower Body ◽  
Clinical Classification ◽  
Clinical Factors ◽  
Factors Associated ◽  
Critical Patients ◽  
Ct Features

Abstract Background Different clinical classifications of COVID-19 pneumonia patients have different clinical and CT features, which is very important for the treatment after admission. As the epidemic situation in China continues to improve, it is particularly important to re-clarify the correlation between them.Methods 97 confirmed patients with COVID-19 pneumonia were enrolled from January 17, 2019 to February 21, 2020, including 75 mild/ordinary cases and 22 severe/critical cases. The clinical data and initial chest CT images of the patients were reviewed and compared. The risk factors associated with disease severity were analyzed.Results Compared with the mild/ordinary patients, the severe/critical patients had older ages, higher incidence of comorbidities, first CT positive, CT always negative and fever. Mild/ordinary patients had lower body temperature than mild/ordinary patients. The incidences of large/multiple GGO in severe/critical patients were significantly higher than those of the mild/ordinary patients, furthermore, severe/critical patients showed higher incidences of 4-5 lobe infections than the ordinary patients. The CT scores of severe/critical patients were significantly higher than those of the ordinary patients (P < 0.001). The clinical factors of age, sex, comorbidities, hypertension, diabetes mellitus, heart disease, pharyngeal discomfort, abdominal pain/diarrhea, temperature and CT score were risk factors for severe/critical COVID-19 pneumonia.Conclusion The initial clinical and CT characteristics have certain significance for the clinical classification of COVID-19 respiratory infection. Especially in terms of CT score, it can predict the trend of clinical classification of patients to a certain extent.

Sign in / Sign up

Export Citation Format

Share Document