Moderate Diabetic Retinopathy Research Articles

Baseline Diabetic Retinopathy Severity and Time to Diabetic Macular Edema Resolution with Ranibizumab Treatment: A Meta-Analysis

Having a better understanding of how long diabetic macular edema (DME) takes to resolve in patients with diabetic retinopathy (DR) after treatment with ranibizumab, and the factors affecting this outcome, would be of benefit to physicians and patients alike. The objective of this analysis was to evaluate the time to first DME resolution and the impact of baseline DR severity on this outcome in patients treated with ranibizumab in phase III clinical trials. Meta-analysis of data from the phase III trials, RIDE (NCT00473382) and RISE (NCT00473330), and DR Clinical Research Network protocols I (NCT00444600), S (NCT01489189), and T (NCT01627249). Patients with DME (central subfield thickness [CST] > 250 μm) and DR with Diabetic Retinopathy Severity Scale (DRSS) score between 35 and85. Intravitreal injection of ranibizumab. The time to first DME resolution (defined as CST ≤ 250 μm) within 24 months was evaluated overall and by baseline DR severity category per the DRSS (35 of 43 [mild or moderate nonproliferative DR], 47-53 [moderately severe or severe nonproliferative DR], 60 [mild proliferative DR], and 61-85 [moderately severe to severe proliferative DR]). There were 777 patients included in the meta-analysis. The overall mean (95% confidence interval) time to first DME resolution, adjusted for baseline CST, was 6.0 (5.6-6.4) months. The mean (95% CI) time to first DME resolution was 7.1 (6.2-7.9), 5.9 (5.2-6.6), 6.0 (4.8-7.2), and 4.5 (3.5-5.5) months for the 35 of 43, 47 to 53, 60, and 61 to 85 baseline DRSS categories, respectively (overall P= 0.002). By month 24, the proportion of eyes with DME resolution was 74.9% (221 of 295), 77.5% (299 of 386), 69.4% (109 of 157), and 78.7% (148 of 188) for the 35 of 43, 47 to 53, 60, and 61 to 85 baseline DRSS categories, respectively (overall P= 0.17). This meta-analysis of data from patients treated with ranibizumab showed that DME resolution was faster in patients with more severe DR at baseline. However, by month 24, a similar proportion of patients achieved DME resolution, regardless of baseline DR severity. These findings may guide treatment decisions and inform patient expectations in clinical practice. Proprietary or commercial disclosure may be found after the references.

Evaluation of diabetic retinopathy severity on ultrawide field colour images compared with ultrawide fluorescein angiograms

PurposeTo compare Early Treatment Diabetic Retinopathy Study (ETDRS) diabetic retinopathy (DR) severity on ultrawide field (UWF) colour imaging (CI) and UWF fluorescein angiography (FA).DesignCross-sectional retrospective review.SubjectsPatients with diabetes mellitus and...

Association between abdominal obesity and diabetic retinopathy in patients with diabetes mellitus: A systematic review and meta-analysis.

Previous studies have reported different opinions regarding the association between abdominal obesity and diabetic retinopathy (DR) in patients with diabetes mellitus (DM). In this study, we aimed to investigate this problem through a systematic review and meta-analysis to provide a basis for clinical interventions. A comprehensive search was conducted in the PubMed, Embase, and Web of Science databases up to May 1, 2022, for all eligible observational studies. Standardized mean differences (SMD) and 95% confidence intervals (CI) were evaluated using a random-effects model in the Stata software. We then conducted, publication bias assessment, heterogeneity, subgroup and sensitivity analyses. A total of 5596 DR patients and 17907 non-DR patients were included from 24 studies. The results of the meta-analysis of abdominal obesity parameters showed statistically significant differences between DR and non-DR patients in both type 1 and type 2 diabetes. Waist circumference (WC) was higher in patients with DR than in the non-DR patients. In the waist-hip ratio (WHR) subgroup, the level of WHR was higher in patients with DR than that in non-DR patients. The association between abdominal obesity and mild to moderate nonproliferative DR or vision-threatening DR groups did not show any statistical difference. Subgroup analysis according to ethnicity showed that Caucasians had higher levels of combined abdominal obesity parameters than Asians. We found that abdominal obesity measured by WC and WHR is associated with DR in patients with type 1 and type 2 diabetes. This association is stronger in Caucasians than in Asians, where isolated abdominal obesity might be more related to DR. However, no correlation was found between abdominal obesity and varying degrees of diabetic retinopathy. Further prospective cohort studies with larger sample sizes are yet to be conducted to clarify our findings.

Gaussian Blur Masked ResNet2.0 Architecture for Diabetic Retinopathy燚etection

Diabetic Retinopathy (DR) is a serious hazard that can result in irreversible blindness if not addressed in a timely manner. Hence, numerous techniques have been proposed for the accurate and timely detection of this disease. Out of these, Deep Learning (DL) and Computer Vision (CV) methods for multiclass categorization of color fundus images diagnosed with Diabetic Retinopathy have sparked considerable attention. In this paper, we attempt to develop an extended ResNet152V2 architecture-based Deep Learning model, named ResNet2.0 to aid the timely detection of DR. The APTOS-2019 dataset was used to train the model. This consists of 3662 fundus images belonging to five different stages of DR: no DR (Class 0), mild DR (Class 1), moderate DR (Class 2), severe DR (Class 3), and proliferative DR (Class 4). The model was gauged based on ability to detect stage-wise DR. The images were pre-processed using negative and positive weighted Gaussian-based masks as feature engineering to further enhance the quality of the fundus images by removing the noise and normalizing the images. Up-sampling and data augmentation methods were used to address the skewness of the original dataset. The proposed model achieved an overall accuracy of 91% and an area under the receiver-operating characteristic curve (AUC) score of 95.1%, outperforming existing Deep Learning models by around 10%. Furthermore, the class-wise F1 score for No DR was 92%, Mild DR was 82%, Moderate DR was 66%, Severe was DR 89% and Proliferative DR was 80%.

Serum brain-derived neurotrophic factor and macular perfusion in type 2 diabetes mellitus using optical coherence tomography angiography

PURPOSE: To investigate the relationship between serum brain-derived neurotrophic factor (BDNF) and changes in macular perfusion in different stages of diabetic retinopathy (DR) using optical coherence tomography angiography (OCTA). MATERIALS AND METHODS: The study was conducted on 72 eyes of people with type 2 diabetes mellitus (DM). They were divided into five groups based on their DR stage: no DR (nDR), mild and moderate nonproliferative DR, severe nonproliferative DR, active proliferative DR (aPDR), and stable PDR. The presence or absence of diabetic maculopathy was also used to categorize the cases. All patients underwent a complete history, ophthalmological examination, OCTA imaging, and evaluation of BDNF and glycated hemoglobin A1c levels. RESULTS: The mean blood BDNF levels in the aPDR group were considerably lower than those in the nDR group (P = 0.023). In comparison to eyes without maculopathy, eyes with maculopathy had considerably decreased mean blood BDNF levels (P = 0.0004). Comparing NPDR and PDR groups to nDR as well as NPDR and PDR, a substantial decrease in average and parafoveal vessel density (VD) of the retina and choriocapillaries was seen (P = 0.02). The Foveal Avascular Zone (FAZ) acircularity index and VD were found to be significantly impacted by deteriorating DR (P = 0.001 and 0.017, respectively). It was discovered that there is a positive correlation between BDNF and the FAZ fractal dimension (P = 0.03). In diabetic eyes, there was a statistically favorable correlation between BDNF levels and best corrected visual acuity (P = 0.002). Furthermore, there was a negative relationship between DM duration and BDNF (P = 0.021). CONCLUSION: Serum BDNF levels decreased with the progression of DR and in patients with maculopathy. BDNF was found to be related to macular perfusion, particularly in the fovea.

Diabetic Retinopathy Grading using Blended Deep Learning

Diabetic retinopathy is a complication of diabetes that is mainly caused by the damage of the blood vessels located in the retina. Retinal screening contributes to early detection and treatment of diabetic retinopathy. DR has five stages, namely healthy, mild, moderate, severe and proliferative diabetic retinopathy. Computer-aided diagnosis approaches are needed to allow an early detection and treatment. Several automated deep learning (DL) based approaches have been proven to be a powerful tool for DR grading. However, these approaches are usually based on one DL architecture only which could produce over-fitted results. Another identified problem is the use of imbalanced datasets. In this paper, we proposed a blended deep learning approach obtained by training several individual DL models, using a 5-fold cross-validation technique and combining their predictions in a final score. This blended model highlights each individual model where it performs best and discredits where it performs poorly, increasing the robustness of the results. The experiments were conducted on a balanced DDR dataset containing 33310 retina fundus images equally distributed for the DR grades. An explainability algorithm was also used to show the efficiency of the proposed approach in detecting DR signs.

Detection of Diabetic Retinopathy from Retinal Images Using DenseNet Models

A prevalent diabetic complication is Diabetic Retinopathy (DR), which can damage the retina’s veins, leading to a severe loss of vision. If treated in the early stage, it can help to prevent vision loss. But since its diagnosis takes time and there is a shortage of ophthalmologists, patients suffer vision loss even before diagnosis. Hence, early detection of DR is the necessity of the time. The primary purpose of the work is to apply the data fusion/feature fusion technique, which combines more than one relevant feature to predict diabetic retinopathy at an early stage with greater accuracy. Mechanized procedures for diabetic retinopathy analysis are fundamental in taking care of these issues. While profound learning for parallel characterization has accomplished high approval exactness’s, multi-stage order results are less noteworthy, especially during beginning phase sickness. Densely Connected Convolutional Networks are suggested to detect of Diabetic Retinopathy on retinal images. The presented model is trained on a Diabetic Retinopathy Dataset having 3,662 images given by APTOS. Experimental results suggest that the training accuracy of 93.51% 0.98 precision, 0.98 recall and 0.98 F1-score has been achieved through the best one out of the three models in the proposed work. The same model is tested on 550 images of the Kaggle 2015 dataset where the proposed model was able to detect No DR images with 96% accuracy, Mild DR images with 90% accuracy, Moderate DR images with 89% accuracy, Severe DR images with 87% accuracy and Proliferative DR images with 93% accuracy.

Anatomical changes in the retinal capillary plexuses assessed by optical coherence tomography angiography in diabetic patients

AbstractPurpose: To assess anatomical changes in the retinal superficial capillary (SCP) and deep capillary (PCP) plexuses, as well as choriocapillary (CC) in patients with diabetes mellitus (DM) without diabetic retinopathy (DR), and in DM patients with mild and moderate DR without diabetic macular edema (DME) using optical coherence tomography angiography (OCTA).Methods: Ninety eyes were included, 34 patients with long‐term DM (more than 10 years) but without DR signs, and 54 patients with mild or moderate DR (levels 35 and 43 on the ETDRS scale) without DME. All participants underwent a complete ophthalmic examination including best corrected visual acuity (BCVA) and OCTA examination using deep‐range imaging with the DRI‐Triton SS‐OCT.Results: The mean age was 63.82 ± 8.56 years and 63.00 ± 13.21 years in long‐term DM without DR and with DR, respectively. In patients with long‐term DM without DR, foveal avascular zone (FAZ) abnormalities were seen in both SCP and DCP (55% and 5%), and microaneurysms (MAs) were present in SCP and DCP (35% and 47.5%). Loss of perfusion was detected in SCP and DCP (30% and 47.5%), and ischemia was observed in SCP, DCP and CC (60%, 37.5% and 10%). In patients with mild or moderate DR without DME, OCTA also detected morphological abnormalities such as FAZ changes and MAs (79.6% and 81.11%), loss of perfusion (83.3% and 64.2%), and ischemia (66.67%, 81.1% and 18.5%) in SCP, DCP and CC respectively. Microvascular tortuosity and intraretinal microvascular anomalies (IRMAs) were detected in 48.1% and 46.3% in SCP vs 22.6% and 20.8% in DCP, respectively.Conclusions: Patients with long‐term DM without DR present morphological changes measured with OCTA, such as MAs in both retinal plexuses. The changes in the FAZ are more evident in the SCP due to the capillary anastomosis. Capillary dropout can be found in both plexuses. Patients with DR show more evident changes that include MAs, loss of perfusion and ischemia and other vascular abnormalities.

Changes in choroidal and retinal thickness assessed by optical coherence tomography in type 2 diabetes mellitus patients with moderate diabetic retinopathy

AbstractPurpose: To study choroidal thickness (CT) in type 2 diabetes mellitus (DM2) patients with moderate diabetic retinopathy (DR) without diabetic macular edema (DME) and to correlate with changes in retinal thickness (RT) with swept source OCT (SS‐OCT)) compared to healthy subjects.Methods: Fifty‐four DM2 patients with moderate DR without DME and 73 age‐matched healthy subjects were evaluated using SS‐OCT to measure changes in total RT and the CT in the nine areas of the Early Treatment Diabetic Retinopathy Study (ETDRS) macular grid.Results: The mean ages were 64.06 ± 11.98 years and 60.79 ± 8.62 years in the diabetic and control groups, respectively. Visual acuity (VA) with ETDRS 100% was lower in the DM2 patients (p < 0.001). In the total RT, statistically significant differences were found in the temporal inner area being thicker thickness in the DM2 group (260.70 ± 19.22 μm vs. 271.90 ± 37.61 μm with p = 0.010, in control and DM2 group, respectively). The CT did not show significant differences between both groups (p > 0.05) in any ETDRS area. There was a significant negative correlation between RT and age in all of the external ETDRS areas and a positive significant correlation in the central area for DM2 group. There was also a negative significant correlation between CT and age in all ETDRS areas except for the inferior inner area. In the DM2 group, a negative correlation was observed between RT and CT in the central area (p = 0.039) and in both horizontal parafoveal areas (temporal inner: p = 0.028, central: p = 0.039 and nasal inner: p = 0.003).Conclusions: DM2 patients with moderate DR have no changes in CT. CT and RT decrease with age and show a negative correlation with RT in the central and horizontal parafoveal areas of the ETDRS grid.

Impact of the COVID-19 Pandemic on the Metabolic Control of Diabetic Patients in Diabetic Retinopathy and Its Screening

(1) Background: Diabetic retinopathy (DR) is a complication of diabetes mellitus (DM), screening programs of which have been affected by the COVID-19 pandemic. The aim of the present study was to determine the impact of the COVID-19 pandemic on the screening of diabetes patients in our healthcare area (HCA). (2) Methods: We carried out a retrospective study of patients with DM who had attended the DR screening program between January 2015 and June 2022. We studied attendance, DM metabolic control and DR incidence. (3) Results: Screening for DR decreased in the first few months of the pandemic. The incidence of mild and moderate DR remained stable throughout the study, and we observed little increase in severe DR, proliferative DR and neovascular glaucoma during 2021 and 2022. (4) Conclusions: The current study shows that during the COVID-19 pandemic, screening program attendance decreased during the year 2020, which then recovered in 2021. Regarding the most severe forms of DR, a slight increase in cases was observed, beginning in the year 2021. Nevertheless, we aimed to improve the telemedicine systems, since the conditions of a significant proportion of the studied patients worsened during the pandemic; these patients are likely those who were already poorly monitored.

Macular Vascular Complexity Analysis of Diabetes Mellitus by Swept-Source Optical Coherence Tomographic Angiography

Purpose: This study was designed to evaluate the associations between retinal vascular complexity features, including fractal dimension (FD) and blood vessel tortuosity (BVT), and the severity of diabetic retinopathy (DR) by using optical coherence tomographic angiography (OCTA). Methods: In this prospective cross-sectional study, 1,282 ocular-treatment-naive patients with type 2 diabetes mellitus (DM) (1,059 without DR and 223 with DR) registered in the community of Guangzhou, China, were enrolled. OCTA was used to measure FD and BVT in the superficial capillary plexus (SCP) and the deep capillary plexus (DCP). Univariate and multivariate linear regression analyses were performed to analyze the correlation of FD and BVT in different layers with DR severity. Results: In this study, 1,282 patients with DM (1,282 eyes), with a mean age of 64.2 ± 7.8 years, were included. FD in the DCP decreased and BVT in the DCP increased in patients with DR compared with those in patients without DR, even after adjusting for confounding factors (p < 0.05). Trend analysis showed a significant decrease in the FD values as the DR progressed, whereas the BVT progressively increased with worsening DR severity (p < 0.01). The FD in DCP had a statistically significant positive correlation with FD in SCP and a negative correlation with BVT in SCP and BVT in DCP in all of the participants, including the non-DR group, moderate DR group, and severe DR group (p < 0.01). Conclusions: FD and BVT determined using OCTA might be useful parameters for objectively distinguishing DR from non-DR and indicating DR progression.

Aqueous Humor Apolipoprotein Concentration and Severity of Diabetic Retinopathy in Type 2 Diabetes

An imbalance of plasma apolipoproteins has been linked to diabetic retinopathy (DR); however, there is scarce information regarding their presence in the aqueous humor (AH) and their role in DR. Here, we aimed at analysing the relationship between apolipoprotein concentrations in human AH and the severity of DR. Concentrations of apolipoproteins were measured retrospectively in patients with type 2 diabetes mellitus (T2DM) without DR (n = 23), with mild to moderate nonproliferative DR (NPDR) (n = 13), and advanced NPDR/proliferative DR (PDR) (n = 14) using a multiplex immunoassay. Compared to the non-apparent DR group, the concentrations of seven apolipoproteins were elevated in advanced NPDR/PDR (Apo AI 5.8-fold, Apo AII 4.5-fold, Apo CI 3.3-fold, Apo CIII 6.8-fold, Apo D 3.3-fold, Apo E 2.4-fold, and Apo H 6.6-fold). No significant differences were observed in apolipoprotein concentrations between patients with non-apparent DR and healthy controls (n = 17). In conclusion, the AH concentrations of apolipoproteins AI, AII, CI, CIII, D, E, and H increased in advancing stages of DR, suggesting their role in the pathogenesis of DR, which deserves further examination.

The effectiveness of artificial intelligence-based automated grading and training system in education of manual detection of diabetic retinopathy.

The purpose of this study is to develop an artificial intelligence (AI)-based automated diabetic retinopathy (DR) grading and training system from a real-world diabetic dataset of China, and in particular, to investigate its effectiveness as a learning tool of DR manual grading for medical students. We developed an automated DR grading and training system equipped with an AI-driven diagnosis algorithm to highlight highly prognostic related regions in the input image. Less experienced prospective physicians received pre- and post-training tests by the AI diagnosis platform. Then, changes in the diagnostic accuracy of the participants were evaluated. We randomly selected 8,063 cases diagnosed with DR and 7,925 with non-DR fundus images from type 2 diabetes patients. The automated DR grading system we developed achieved accuracy, sensitivity/specificity, and AUC values of 0.965, 0.965/0.966, and 0.980 for moderate or worse DR (95 percent CI: 0.976-0.984). When the graders received assistance from the output of the AI system, the metrics were enhanced in varying degrees. The automated DR grading system helped to improve the accuracy of human graders, i.e., junior residents and medical students, from 0.947 and 0.915 to 0.978 and 0.954, respectively. The AI-based systemdemonstrated high diagnostic accuracy for the detection of DR on fundus images from real-world diabetics, and could be utilized as a training aid system for trainees lacking formal instruction on DR management.

Telemedicine Screening of the Prevalence of Diabetic Retinopathy Among Type 2 Diabetic Filipinos in the Community

Purpose: To determine the feasibility of telemedicine screening for diabetic retinopathy in a community setting and to determine the prevalence of diabetic retinopathy among Filipino patients with type 2 diabetes in the community. Study Design: Cross-sectional study among patients with type 2 diabetes in six community health centers in an urban city in the Philippines. Materials and methods: Subjects were examined from November 2018 to December 2018. A three-field non-mydriatic 45’ fundus photographs were taken for each patient and photographs were uploaded in cloud storage and read by a retina specialist in a tertiary hospital for assessment of diabetic retinopathy and grading of the fundus photographs. The results were sent back to local health centers. Results: A total of 387 eyes of 195 persons were examined. Overall, 288 out of 387 eyes (95.36%) had gradable quality fundus photo (grade 3 and higher) and did not need eye dilation. Prevalence of diabetic retinopathy among the respondents was 25.26% - 3.16% had mild diabetic retinopathy, 15.79% had moderate diabetic retinopathy, 3.68% had severe diabetic retinopathy, and 3.68% had proliferative diabetic retinopathy. Other fundus findings noted include hypertensive retinopathy glaucomatous optic nerve, age-related macular degeneration, posterior vitreous detachment, clinically significant macular edema, and epiretinal membrane. Conclusion: Due to the significant number of patients with diabetic retinopathy among type 2 diabetics in the community, telemedicine screening was a feasible alternative to dilated fundus examination and may be considered as part of the local health program to prevent blindness due to diabetes.

Choroidal and Retinal Thicknesses in Type 2 Diabetes Mellitus with Moderate Diabetic Retinopathy Measured by Swept Source OCT.

Background: To study choroidal thickness (CT) in type 2 diabetes mellitus (DM2) patients with moderate diabetic retinopathy (DR) and to correlate with changes in retinal thickness (RT) with swept-source OCT (SS-OCT) compared to healthy subjects. Methods: Fifty-four DM2 patients with moderate DR without diabetic macular edema (DME) and 73 age-matched healthy subjects were evaluated using SS-OCT to measure changes in total RT and CT in the nine areas of the Early Treatment Diabetic Retinopathy Study (ETDRS) macular grid. Results: The mean age was 64.06 ± 11.98 years and 60.79 ± 8.62 years in the diabetic and control groups, respectively. Total RT showed statistically significant differences in the temporal inner area, with higher values in the DM2 group (p = 0.010). CT did not show differences between the groups. There was a significant negative correlation between RT and age in all of the outer ETDRS areas and a positive significant correlation in the central area for the DM2 group. There was also a negative significant correlation between CT and age in all of the ETDRS areas except for the inferior inner area. In the DM2 group, a negative correlation was observed between RT and CT in the central area (p = 0.039) and in both horizontal parafoveal areas (temporal inner, p = 0.028; nasal inner, p= 0.003). Conclusion: DM2 patients with moderate DR have no changes with regard to CT. Both CT and RT decreased with age in DM2, showing a negative correlation between these factors in the central and horizontal parafoveal areas of the ETDRS grid.

The Relationship Between Diabetic Retinopathy Degree With Visual Acuity And Retinal Nerve Fiber Layer Thickness In Type 2 Diabetes Mellitus Patients

Introduction: Diabetic retinopathy is an ocular complication of diabetes mellitus (DM), and is one of the leading causes of visual impairment and blindness worldwide.. More than one third of people with diabetes have signs of diabetic retinopathy.&#x0D; &#x0D; Methods: This was an analytic observational study with cross-sectional design. The sample was type 2 diabetes mellitus patients with diabetic retinopathy who visited the eye clinic at the University of Sumatera Utara General Hospital from September 2021-December 2021. The sample were then analyzed with the Mann-Whitney and Kruskal Wallis test to find the relationship between diabetic retinopathy degree with visual acuity and retinal nerve fiber layer thickness in type 2 diabetes mellitus patients.&#x0D; &#x0D; Results: The sample of this study were 20 subjects with diabetic retinopathy and 20 subjects without diabetic retinopathy as the control group. The mean visual acuity in subjects with mild diabetic retinopathy was 0.65+0.48. Average visual acuity in subjects with the degree of moderate diabetic retinopathy was 0.83+0.46. The mean visual acuity in subjects with a proliferative degrees diabetic retinopathy was 0.77+0.64. Mann Whitney test revealed no statistically significant relationship between the degree of diabetic retinopathy and visual acuity (p=0.734). Using the Kruskal Wallis test revealed that there was no significant relationship between the degree of retinopathy diabetic with Avg RNFL (p=0.495), superior RNFL (p=0.385), inferior RNFL (p=0.111), temporal RNFL (p=0.064), nasal RNFL (p=0.535).&#x0D; &#x0D; Discussion: Controlling blood glucose levels becomes more important than the duration of diabetes in preventing the development of retinopathy. Most patients are advised to have an HbA1c of 7% or lower, and for certain patients it is recommended to be lower than6.5%. Diabetic retinopathy slowly damages the retinal blood vessels or the optic nerve layer, leading to leakage, thus resulting in accumulation of fluid containing lipid and blood in the retina which will gradually lead to visual impairment, and even blindness.&#x0D; &#x0D; Conclusion: There is no significant relationship between diabetic retinopathy degree with visual acuity and retinal nerve fiber layer thickness in type 2 diabetes mellitus patients.

Optimal Frequency of Retinopathy Screening in Adolescents With Type 1 Diabetes: Markov Modeling Approach Based on 30 Years of Data.

Current guidelines recommend biennial diabetic retinopathy (DR) screening commencing at the age of 11 years and after 2-5 years' duration of type 1 diabetes. Growing evidence suggests less frequent screening may be feasible. Prospective data were collected from 2,063 youth with type 1 diabetes who were screened two or more times between 1990 and 2019. Baseline (mean ± SD) age was 13.3 ± 1.8 years, HbA1c was 8.6 ± 1.3% (70.1 ± 14.7 mmol/mol), diabetes duration was 5.6 ± 2.8 years, and follow-up time was 4.8 ± 2.8 years. DR was manually graded from 7-field retinal photographs using the Early Treatment Diabetic Retinopathy Study (ETDRS) scale. Markov chain was used to calculate probabilities of DR change over time and hazard ratio (HR) of DR stage transition. The incidence of moderate nonproliferative DR (MNPDR) or worse was 8.6 per 1,000 patient-years. Probabilities of transition to this state after a 3-year interval were from no DR, 1.3%; from minimal DR, 5.1%; and from mild DR, 22.2%, respectively. HRs (95% CIs) for transition per 1% current HbA1c increase were 1.23 (1.16-1.31) from no DR to minimal NPDR, 1.12 (1.03-1.23) from minimal to mild NPDR, and 1.28 (1.13-1.46) from mild to MNPDR or worse. HbA1c alone explained 27% of the transitions between no retinopathy and MNPDR or worse. The addition of diabetes duration into the model increased this value to 31% (P = 0.03). Risk was also increased by female sex and higher attained age. These results support less frequent DR screening in youth with type 1 diabetes without DR and short duration. Although DR progression to advanced stages is generally slow, higher HbA1c greatly accelerates it.

Automated Diabetic Retinopathy Detection Using Horizontal and Vertical Patch Division-Based Pre-Trained DenseNET with Digital Fundus Images.

Diabetic retinopathy (DR) is a common complication of diabetes that can lead to progressive vision loss. Regular surveillance with fundal photography, early diagnosis, and prompt intervention are paramount to reducing the incidence of DR-induced vision loss. However, manual interpretation of fundal photographs is subject to human error. In this study, a new method based on horizontal and vertical patch division was proposed for the automated classification of DR images on fundal photographs. The novel sides of this study are given as follows. We proposed a new non-fixed-size patch division model to obtain high classification results and collected a new fundus image dataset. Moreover, two datasets are used to test the model: a newly collected three-class (normal, non-proliferative DR, and proliferative DR) dataset comprising 2355 DR images and the established open-access five-class Asia Pacific Tele-Ophthalmology Society (APTOS) 2019 dataset comprising 3662 images. Two analysis scenarios, Case 1 and Case 2, with three (normal, non-proliferative DR, and proliferative DR) and five classes (normal, mild DR, moderate DR, severe DR, and proliferative DR), respectively, were derived from the APTOS 2019 dataset. These datasets and these cases have been used to demonstrate the general classification performance of our proposal. By applying transfer learning, the last fully connected and global average pooling layers of the DenseNet201 architecture were used to extract deep features from input DR images and each of the eight subdivided horizontal and vertical patches. The most discriminative features are then selected using neighborhood component analysis. These were fed as input to a standard shallow cubic support vector machine for classification. Our new DR dataset obtained 94.06% and 91.55% accuracy values for three-class classification with 80:20 hold-out validation and 10-fold cross-validation, respectively. As can be seen from steps of the proposed model, a new patch-based deep-feature engineering model has been proposed. The proposed deep-feature engineering model is a cognitive model, since it uses efficient methods in each phase. Similar excellent results were seen for three-class classification with the Case 1 dataset. In addition, the model attained 87.43% and 84.90% five-class classification accuracy rates using 80:20 hold-out validation and 10-fold cross-validation, respectively, on the Case 2 dataset, which outperformed prior DR classification studies based on the five-class APTOS 2019 dataset. Our model attained about >2% classification results compared to others. These findings demonstrate the accuracy and robustness of the proposed model for classification of DR images.

Correlation of Diabetic Disease Severity to Degree of Quadrant Asymmetry in En Face OCTA Metrics.

PurposeTo determine if diabetic retinopathy (DR) severity affects quadrant asymmetry (QA) of optical coherence tomography angiography (OCTA) metrics differentially.MethodsNinety eyes (60 patients) with no diabetes mellitus (DM) (n = 39) or varying levels of DR (n = 51) had OCTA images (3 × 3 mm, Cirrus5000) acquired five times and averaged. The vessel length density (VLD) and perfusion density (PD) of the superficial retinal layer (SRL) and deep retinal layer (DRL) were measured. QA was defined as the maximum minus minimum value among four parafoveal Early Treatment Diabetic Retinopathy quadrants, and compared with DR severity by linear regression including fixed effects for each individual and eye.ResultsThe mean patient age was 55.5 years (range, 24–88 years) and 60% were male. Comparing severe nonproliferative DR or proliferative DR versus no DM/DR eyes, QA was significantly higher for SRL VLD, and PD (+0.67 ± 0.16 and +0.014 ± 0.003; P < 0.001) and DRL VLD, and PD (+1.25 ± 0.16 and +0.032 ± 0.003; P < 0.001). When comparing mild or moderate nonproliferative DR versus no DM/DR, the DRL VLD, and PD were significantly higher (+0.51 ± 0.13 and +0.015 ± 0.003; P < 0.001). For every step increase in DR severity, there was a +0.20 QA for SRL VLD, +0.004 SRL PD, +0.33 DRL VLD and +0.009 DRL PD (P < 0.001). Regression analysis comparing intraquadrant effect on DR severity demonstrated that the superior quadrant was most affected for all OCTA metrics.ConclusionsDR severity affects VLD and PD more asymmetrically across Early Treatment Diabetic Retinopathy quadrants with a linear increase in QA for each worsening level of DR. Individual intraeye metrics such as QA can accurately quantify DR severity without concerns for intereye variabilities that could affect the reproducibility and reliability of OCTA quantification.

Age-Related Eye Diseases in Individuals With Mild Cognitive Impairment and Alzheimer's Disease.

IntroductionAlzheimer's disease (AD) and age-related eye diseases pose an increasing burden as the world's population ages. However, there is limited understanding on the association of AD/cognitive impairment, no dementia (CIND) with age-related eye diseases.MethodsIn this cross-sectional, memory clinic-based study of multiethnic Asians aged 50 and above, participants were diagnosed as AD (n = 216), cognitive impairment, no dementia (CIND) (n = 252), and no cognitive impairment (NCI) (n = 124) according to internationally accepted criteria. Retinal photographs were graded for the presence of age-related macular degeneration (AMD) and diabetic retinopathy (DR) using standard grading systems. Multivariable-adjusted logistic regression models were used to determine the associations between neurological diagnosis and odds of having eye diseases.ResultsOver half of the adults had at least one eye disease, with AMD being the most common (60.1%; n = 356), followed by DR (8.4%; n = 50). After controlling for age, sex, race, educational level, and marital status, persons with AD were more likely to have moderate DR or worse (OR = 2.95, 95% CI = 1.15–7.60) compared with NCI. In the fully adjusted model, the neurological diagnosis was not associated with AMD (OR = 0.75, 95% CI = 0.45–1.24).ConclusionPatients with AD have an increased odds of having moderate DR or worse, which suggests that these vulnerable individuals may benefit from specific social support and screening for eye diseases.