Severe Non-proliferative Diabetic Retinopathy Research Articles

Implementation of a Teleophthalmology Screening Program for Diabetic Retinopathy in New York City.

Purpose: To examine the implementation of a teleophthalmology program for diabetic retinopathy (DR) screening at a metropolitan hospital system and identify the challenges that the clinical teams encountered using the program. Methods: The study was conducted in 2 parts. The first was a pilot retrospective chart review of 300 consecutive patients screened for DR by the teleophthalmology screening program. The baseline variables, DR capture rate and staging, and continuity of care for those diagnosed with DR were analyzed. The second was a web-based survey identifying the barriers encountered by 36 physicians and clinical staff as they participated in the teleophthalmology screening program. Results: Part 1: Of the patients evaluated, 57 (19.0%) were diagnosed with DR; 42 (73.7%) had mild nonproliferative DR (NPDR), 7 (12.3%) had moderate NPDR, none had severe NPDR, and 8 (14.0%) had PDR. Thirty-one patients (54.4%) with retinopathy diagnoses were referred for an in-person follow-up at the clinic while the rest continued monitoring via the program. Of this subset, 22 (71.0%) completed the follow-up visit. Part 2: The survey respondents comprised 28 physicians (77.8%), 6 licensed nurse practitioners (16.7%), and 2 medical assistants (5.6%). Twenty-two providers (71.0%) preferred initiating referrals for in-person annual examinations over teleophthalmology screening referrals. The most common barriers described were related to workflow interruption, time constraints, and staff shortages. Conclusions: The teleophthalmology DR screening program allowed identification of early or absent DR at clinics in an urban setting (New York City). The findings suggest areas for targeted improvement in the screening program to better complement internal referral practices' workflows.

Study of OCT based biomarkers as a predictor of visual outcome in diabetic macular edema

To determine the association between optical coherence tomography (SD-OCT) based biomarkers and visual acuity (VA) in diabetic macular edema (DME). This cross-sectional study was conducted at a tertiary care teaching hospitalbetweenJanuary 2021 and July 2022.The study included 54 eyes (30 patients) with DME. Based on the early treatment diabetic retinopathy study (ETDRS) grading system, these were classified as mild (n=1), moderate (n=31), severe (n=14), and very severe (n=8) non-proliferative diabetic retinopathy (NPDR). The demographics, VA recorded using ETDRS chart and ETDRS scoring system, slit lamp biomicroscopy findings, colour fundus pictures and biomarkers determined using macular scans on SD-OCT were noted. Six eyes with proliferative diabetic retinopathy (n-4) and considerable media opacity (n-2) were excluded. The data was entered into Microsoft Excel spreadsheet 2021and IBM's SPSS 26 statistical program was used to calculate the results.VA and biomarkers, which included central macular thickness, disorganisation of retinal inner layers (DRIL), ellipsoid zone disruption (EZD), choroidal thickness were measured on SD-OCT.: The mean age was 59.4±9.4 years, and male to female ratio was 1.3:1. Mean uncorrected and best corrected VA were 46 and 61 letters, 55.12±1.76 and 67.25±10.05 letters for moderate NPDR, 43.07±3.95 and 52.14±17.83 letters for severe NPDR, and 26.50±16.53 and 36±16.38 letters for very severe NPDR, respectively. VA deteriorated with increasing disease severity. Poorer VA was associated with increased average foveal and macular thickness and increased mean horizontal disruption of the inner retinal layers (DRIL). Average choroidal thickness positively correlated with increasing DR severity. : Poorer VA was associated with increasing DR severity, increased central retinal thickness, increased mean horizontal DRIL and increased average foveal choroidal thickness. We found no statistically significant correlation between VA and ellipsoid zone disruption.

The effect of hypothyroidism on the risk of diabetes and its microvascular complications: a Mendelian randomization study.

Several observational studies have found that hypothyroidism is associated with diabetes and its microvascular complications. However, the cause and effect have not been clarified. The aim of the study was to examine the causality of such associations by a Mendelian randomization study. Two-sample Mendelian randomization analysis was conducted to investigate the associations. Summary statistics for hypothyroidism were from the UK Biobank, and diabetes and its microvascular complications were from the largest available genome-wide association studies. MR-Egger, weighted median, inverse variance weighted, simple mode and weighted mode were used to examine the causal associations, and several sensitivity analyses were used to assess pleiotropy. Inverse variance weighted estimates suggested that hypothyroidism was associated with type 1 diabetes and type 1 diabetes with renal complications (β= 9.059926, se= 1.762903, P = 2.76E-07 and β= 10.18375, se= 2.021879, P = 4.73E-07, respectively) but not type 2 diabetes and type 2 diabetes with renal complications. In addition, hypothyroidism was positively associated with severe nonproliferative diabetic retinopathy and proliferative diabetic retinopathy (β= 8.427943, se= 2.142493, P = 8.36E-05 and β= 3.100939, se= 0.74956, P=3.52E-05, respectively). The study identified the causal roles of hypothyroidism in diabetes and its microvascular complications. Hypothyroidism can lead to type 1 diabetes, type 1 diabetes with renal complications, severe nonproliferative diabetic retinopathy and proliferative diabetic retinopathy.

Evaluation of Quality of Life and Emotional Disturbances in Patients with Diabetic Retinopathy.

The purpose of this study was to evaluate the association of Diabetic Retinopathy (DR) and diabetic macular edema with vision-related quality of life, as well as the potential association between the disease's severity, emotional status of patients and the manifestation of anxiety and psychological features. Patients with fundoscopic findings had significantly lower scores in all VFQ-25 subscales, indicating worse quality of life in comparison to patients without DR. Severity of DR, greater levels of anxiety, daily sitting time, unemployment and lower education level, were all found to be significantly, negatively associated with a worse quality of life. Regarding emotional status, more years of suffering from diabetes, treatment with insulin and the hours being idle per day were associated with an increased burden of anxiety. In addition, the presence of a concomitant disease, findings in fundoscopy, diabetic macular edema and treatment with anti-VEFG injections, as well as the number of doses, were significantly associated with greater anxiety. Multivariate analysis showed that having Severe Non-Proliferative Diabetic Retinopathy or having Proliferative Diabetic Retinopathy and receiving insulin therapy (alone or in combination with another treatment), were significantly associated with higher levels of anxiety. The well-established impact of DR on the patients' well-being, quality of life and emotional status render DR and CME prevention, stabilization or delaying progression as a necessity in order to protect patients from developing psychiatric symptoms. On the other hand, the speculated bi-directional association between emotional problems and DR progression highlights the importance of acknowledging and dealing with psychological issues with the aim of delaying DR progression.

Prevalence and Risk Factors of Retinopathy in Type 1 Diabetes: A Cross-Sectional Study.

Introduction Diabetic retinopathy (DR) is a severe complication of diabetes. It remains a major cause of visual impairment and blindness, especially in young people. It is a silent affection that only becomes symptomatic at the onset of complications. Our study aimed to estimate the prevalence of retinopathy in patients with type 1 diabetes mellitus (T1DM) and evaluate the associated risk factors in our population. Materials and methods A descriptive and analytical study, with a cross-sectional study involving 359 patients with type 1 diabetes, was followed up in the Department of Endocrinology, Diabetology, and Nutrition of the University Hospital Center Mohammed VI Oujda, Morocco. Data were collected from medical records and analyzed by binary logistic regression using IBM Corp. Released 2012. IBM SPSS Statistics for Windows, Version 21.0. Armonk, NY: IBM Corp. Results The average age of our patients was 24.2 ± 11.4 years. The mean duration of diabetes was 11.8±4.4 years. The average glycated hemoglobin (HbA1c) at admission was 10.1 ± 2.4%. DR was found in 30% of patients, including 28.6% with minimal non-proliferative diabetic retinopathy (NPDR), 19.1% with moderate NPDR, 19.1% with severe NPDR, and 33.3% with proliferative DR. Patients with diabetic retinopathy appear to have a longer duration of diabetes (13.05±9.05 vs. 10.6±8.07 years). The longer duration of diabetes, neuropathy, and nephropathy was significantly associated with diabetic retinopathy (p=0.02, p=0.002, and p=0.0001, respectively). Conclusion The frequency of diabetic retinopathy increases with age, poor glycemic control, and the duration of diabetes. Therefore, cooperation between diabetologists and ophthalmologists is essential for making an early diagnosis and providing early treatment.

Ocular and Systemic Risk Factors for Disease Worsening Among Patients with NPDR: Post Hoc Analysis of the PANORAMA Trial

PurposeIdentify baseline systemic and ocular characteristics associated with nonproliferative diabetic retinopathy (NPDR) worsening, and the impact of intravitreal aflibercept injection (IAI) on these associations. DesignPost hoc analysis of PANORAMA. ParticipantsPatients with moderately severe to severe NPDR enrolled in the prospective PANORAMA phase 3 trial. MethodsAssociations between baseline systemic and ocular factors with events indicative of NPDR worsening at Week 100 were evaluated by multivariable analysis in sham-treated eyes. NPDR worsening was defined as development of (1) vision-threatening complications (VTCs; comprising PDR and/or anterior segment neovascularization), (2) center-involved diabetic macular edema (CI-DME), or (3) ≥ 2-step Diabetic Retinopathy Severity Scale (DRSS) worsening. Impact of IAI on identified baseline factors was evaluated using univariable analysis in combined IAI groups. Main Outcomes MeasuresBaseline systemic and ocular factors associated with events indicative of NPDR worsening at Week 100. The cumulative incidence and risk of developing such events at Week 100 among sham versus IAI-treated eyes. ResultsUsing multivariable analyses among sham-treated eyes, 5 baseline factors associated with increased risk of NPDR worsening were identified: fluorescein leakage, retinal nonperfusion area, thicker central subfield thickness, eosinophil level, and proteinuria. Considering baseline fluorescein leakage area as a prognostic indicator in detail, the risk of developing VTCs alone, VTCs and/or CI-DME, or ≥ 2-step DRSS worsening increased with increasing fluorescein leakage area in the sham group (all P < 0.05). Considering baseline retinal nonperfusion area as a prognostic indicator in detail, the risk of developing VTCs alone, CI-DME alone, or VTCs and/or CI-DME increased with increasing baseline retinal nonperfusion area in the sham group (all P < 0.05). In contrast, among IAI-treated eyes, increasing baseline fluorescein leakage or retinal nonperfusion areas did not increase the risks of NPDR worsening. ConclusionsWithin the PANORAMA trial, increased areas of fluorescein leakage and retinal nonperfusion at baseline were identified as key ocular biomarkers associated with events indicative of NPDR worsening among sham-treated patients. IAI treatment appeared to mitigate the effect of these baseline risk factors and reduced the likelihood of NPDR worsening.

Association between macrophage-like cell density and ischemia metrics in diabetic eyes

We previously showed that macrophage-like cells (MLCs) are increased in eyes with advanced diabetic retinopathy (DR). Here, we hypothesized that MLC density was correlated with ischemia using optical coherence tomography angiography (OCTA) and ultra-widefield fluorescein angiography (UWF-FA). Treatment-naïve diabetic eyes were prospectively imaged with repeated OCTA (average 5.3 scans per eye) and UWF-FA imaging. OCTA images were registered and averaged to generate a superficial capillary plexus (SCP), deep capillary plexus (DCP), and MLC slab. We calculated geometric perfusion deficit (GPD), vessel length density, and vessel density for the SCP and DCP. MLC density was quantified by two masked graders and averaged. Ischemia on UWF-FA was measured to generate a non-perfusion area (NPA) and index (NPI). Since MLC density was non-parametrically distributed, MLC density was correlated with ischemia metrics using Spearman correlations. Forty-five treatment-naïve eyes of 45 patients (59 ± 12 years of age; 56% female) were imaged. We included 6 eyes with no DR, 7 eyes with mild non-proliferative DR (NPDR), 22 moderate NPDR, 4 severe NPDR, and 6 PDR eyes. MLC density between graders was highly correlated (r = 0.9592, p < 0.0001). MLC density was correlated with DCP GPD (r = 0.296, p = 0.049), but no other OCTA ischemia metrics. MLC density was also correlated with UWF-FA NPA (r = 0.330, p = 0.035) and NPI (r = 0.332, p = 0.034). MLC density was correlated with total ischemia on UWF-FA and local DCP GPD. Since both UWF-FA and DCP non-perfusion are associated with higher risk for DR progression, MLC density could be another potential biomarker for DR progression.

A Prediction Model for Sight-Threatening Diabetic Retinopathy Based on Plasma Adipokines among Patients with Mild Diabetic Retinopathy.

Accumulating evidence has suggested a link between adipokines and diabetic retinopathy (DR). This study is aimed at investigating the risk factors for sight-threatening DR (STDR) and establishing a prognostic model for predicting STDR among a high-risk population of patients with type 2 diabetes mellitus (T2DM). Plasma concentrations of adipokines were determined by enzyme-linked immunosorbent assay. In the case-control set, principal component analysis (PCA) was performed to select optimal predictive cytokines for STDR, involving severe nonproliferative DR (NPDR) and proliferative DR. Support vector machine (SVM) was used to examine the possible combination of baseline plasma adipokines to discriminate the patients with mild NPDR who will later develop STDR. An individual prospective cohort with a follow-up period of 3 years was used for the external validation. In both training and testing sets, involving 306 patients with T2DM, median levels of plasma adiponectin (APN), leptin, and fatty acid-binding protein 4 (FABP4) were significantly higher in the STDR group than those in mild NPDR. Except for adipsin, the other three adipokines, FABP4, APN, and leptin, were selected by PCA and integrated into SVM. The accuracy of the multivariate SVM classification model was acceptable in both the training set (AUC = 0.81, sensitivity = 71%, and specificity = 91%) and the testing set (AUC = 0.77, sensitivity = 61%, and specificity = 92%). 110 T2DM patients with mild NPDR, the high-risk population of STDR, were enrolled for external validation. Based on the SVM, the risk of each patient was calculated. More STDR occurred in the high-risk group than in the low-risk group, which were grouped by the median value of APN, FABP4, and leptin, respectively. The model was validated in an individual cohort using SVM with the AUC, sensitivity, and specificity reaching 0.77, 64%, and 91%, respectively. Adiponectin, leptin, and FABP4 were demonstrated to be associated with the severity of DR and maybe good predictors for STDR, suggesting that adipokines may play an important role in the pathophysiology of DR development.

THE ROLE OF E-SELECTIN IN THE DEVELOPMENT OF MACULAR EDEMA IN DIABETIC RETINOPATHY DURING TYPE 2 DIABETES

Background. Diabetic retinopathy (DR) and diabetic macular edema (DME) are frequent complications of type 2 diabetes (T2D). Implementation of their effective diagnosis and prognosis by identifying new biomarkers is an important task of modern ophthalmology.&#x0D; Aim: is to establish the role of E-selectin in the development of DME in DR of various degrees in patients with T2D.&#x0D; Materials and methods. The study included 124 patients (124 eyes) with T2D who had mild (29 eyes, group 1), moderate or severe (35 eyes, group 2) non-proliferative DR and proliferative DR (31 eyes, 3rd group); the control group consisted of 29 eyes without diabetes. All patients underwent standard ophthalmological examinations, spectral domain optical coherence tomography (OCT) with determination of central retinal thickness (CRT, μm). The DME set more values of the regulatory database on the ETDRS fields of the spectral-domain OKT software when the CRT is increased. The content of E-selectin in the blood was determined by the immunoenzymatic method (Invitrogen ThermoFisher Scientific, USA). MedStat and MedCalc v.15.1 software packages (MedCalc Software bvba) were used for statistical research.&#x0D; Results. The content of E-selectin in the blood in DR and T2D was significantly increased in all stages of DR (1.2-1.3 times; p&lt;0.01), with a maximum in proliferative DR, which directly correlated with indicators that reflected glycemic control (HbA1c), retinal edema (CRT) and visual acuity deterioration. The content of E-selectin when dividing patients according to the presence of DMN was higher than without it (1.3 times; p&lt;0.001), which was preserved for all stages of DR. The existence of a pathogenetic connection between an increase in the content of E-selectin and the development of DME and the possibility of its use as a biomarker of DME was confirmed in a univariate regression analysis: an increase in the DME risk with an increase in the content of E-selectin was found (OR=1.19; 95% CI 1.12-1.26). The model had satisfactory performance criteria - AUC=0.89 (95% CI 0.83-0.94) with a sensitivity of 89.8% and a specificity of 80.0%.&#x0D; Conclusion. The results of the study confirmed the concept of the significant importance of increasing the content of E-selectin in the blood for the development of DME in DM and T2D.

Mendelian Randomization Analysis Reveals Causal Effects of Polyunsaturated Fatty Acids on Subtypes of Diabetic Retinopathy Risk.

Polyunsaturated fatty acids (PUFAs) affect several physiological processes, including visual acuity, but their relationship with diabetic retinopathy (DR) remains elusive. The aim of this study was to determine whether PUFAs have a causal effect on DR. PUFAs- (total and omega-3 [FAw3] and omega-6 [FAw6] fatty acids and their ratio) and DR-associated single nucleotide polymorphisms derived from genome-wide association studies; sample sizes were 114,999 for fatty acids and 216,666 for any DR (ADR), background DR (BDR), severe non-proliferative DR (SNPDR), and proliferative DR (PDR). We hypothesized that the intra-body levels of PUFAs have an impact on DR and conducted a two-sample Mendelian randomization (MR) study to assess the causality. Pleiotropy, heterogeneity, and sensitivity analyses were performed to verify result reliability. High levels of PUFAs were found to be associated with reduced risk of both ADR and PDR. Moreover, FAw3 was associated with a decreased risk of PDR, whereas FAw6 demonstrated an association with lowered risks of both BDR and PDR. Our findings provide genetic evidence, for the first time, for a causal relationship between PUFAs and reduced DR risk. Consequently, our comprehensive MR analysis strongly urges further investigation into the precise functions and long-term effects of PUFAs, FAw3, and FAw6 on DR.

Perfused and Nonperfused Microaneurysms Identified and Characterized by Structural and Angiographic OCT

Microaneurysms (MAs) have distinct, oval-shaped, hyperreflective walls on structural OCT, and inconsistent flow signal in the lumen with OCT angiography (OCTA). Their relationship to regional macular edema in diabetic retinopathy (DR) has not been quantitatively explored. Retrospective, cross-sectional study. A total of 99 participants, including 23 with mild, nonproliferative DR (NPDR), 25 with moderate NPDR, 34 with severe NPDR, and 17 with proliferative DR. We obtained 3× 3-mm scans with a commercial device (Solix, Visionix/Optovue) in 99 patients with DR. Trained graders manually identified MAs and their location relative to the anatomic layers from cross-sectional OCT. Microaneurysms were first classified as perfused if flow signal was present in the OCTA channel. Then, perfused MAs were further classified into fully and partially perfused MAs based on the flow characteristics in en face OCTA. The presence of retinal fluid based on OCT near MAs was compared between perfused and nonperfused types. We also compared OCT-based MA detection to fundus photography (FP)- and fluorescein angiography (FA)-based detection. OCT-identified MAs can be classified according to colocalized OCTA flow signal into fully perfused, partially perfused, and nonperfused types. Fully perfused MAs may be more likely to be associated with diabetic macular edema (DME) than those without flow. We identified 308 MAs (166 fully perfused, 88 partially perfused, 54 nonperfused) in 42 eyes using OCT and OCTA. Nearly half of the MAs identified in this study straddle the inner nuclear layer and outer plexiform layer. Compared with partially perfused and nonperfused MAs, fully perfused MAs were more likely to be associated with local retinal fluid. The associated fluid volumes were larger with fully perfused MAs compared with other types. OCT/OCTA detected all MAs found on FP. Although not all MAs seen with FA were identified with OCT, some MAs seen with OCT were not visible with FA or FP. OCT-identified MAs with colocalized flow on OCTA are more likely to be associated with DME than those without flow. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Risk Factors and Outcomes of Delayed Presentation of Diabetic Retinopathy Patients to a County Hospital.

To identify risk factors and evaluate outcomes of patients with delayed presentation and advanced diabetic retinopathy in our safety-net county hospital population. A retrospective study was performed on 562 patients who presented with a new diagnosis of diabetic retinopathy (DR). Delayed presentation was defined as moderate or severe nonproliferative diabetic retinopathy (NPDR) or proliferative diabetic retinopathy (PDR) at the initial visit. Comparisons between patient groups were performed with chi-square or Fisher's exact test for categorical variables and multinomial logistic regression for multivariable analysis. Linear and logistic regression modeling with general estimating equations to account for patients having two eyes was used to compare eye-level outcomes. Lack of a primary care provider (PCP) was highest in patients who presented initially with PDR (28.8%), compared to 14.3% in moderate/severe NPDR, 12.4% in mild NPDR, and 7.6% in no DR groups (P < 0.001). Only 69.4% of patients with a PCP had an ophthalmology screening referral. Highest lack of referral (47.2%) was seen in the PDR group (P = 0.002). Patients with PDR were more likely to be uninsured (19.2%) compared to no and mild DR groups, with rates of 7.6% and 9.0%, respectively (P = 0.001). The PDR group had worse initial and final visual acuities (P < 0.001). Several risk factors were noted for delayed DR presentation, including lack of PCP, lack of screening referral, and uninsured/underinsured status. Patients with advanced DR at presentation had worse final visual outcomes despite aggressive treatment. Screening programs targeting populations with identified risk factors are essential for improving outcomes.

A hybrid approach for diagnosing diabetic retinopathy from fundus image exploiting deep features

One of the major causes of blindness in human beings is the diabetic retinopathy (DR). To prevent blindness, early detection of DR is therefore necessary. In this paper, a hybrid model is proposed for diagnosing DR from fundus images. A combination of morphological image processing and Inception v3 deep learning techniques are exploited to detect DR as well as to classify healthy, mild non-proliferative DR (NPDR), moderate NPDR, severe NPDR, and proliferative DR (PDR). The proposed algorithm was carried out in several steps such as segmentation of blood vessels, localization and removal of optic disc, and macula, abnormal features detection (microaneurysms, hemorrhages, and neovascularization), and classification. Microaneurysms and hemorrhages that appear in the retina are the early signs of DR. In this work, we have detected microaneurysms and hemorrhages by applying dynamic contrast limited adaptive histogram equalization and threshold value on overlapping patched images. An overall accuracy of 96.83% is obtained to classify DR into five different stages. The better performance demonstrates the effectiveness and novelty of the proposed work as compared to the recent reported work.

Assessment of macular thickness following cataract surgery in diabetic patients

Background: Cataracts and diabetes very commonly coexist. While the results of cataract extraction (CE) procedure are astounding, patients with diabetes may have more unfortunate visual outcomes in comparison to their counterparts. Aims and Objectives: This study is planned to see the frequency of development of macular oedema (ME) in diabetic patients as compared to non-diabetics and also to see the progression of ME after cataract surgery. Materials and Methods: This prospective comparative study enrolled 100 diabetics and 100 non-diabetics undergoing cataract surgery fulfilling inclusion criteria. Complete ocular examination was done for both the groups preoperatively and postoperatively at 1 week, 1 month, and 3 months including central macular thickness evaluation using optical coherence tomography (OCT). Results: Improvement in visual acuity was observed in both the group but, non-diabetics achieved better visual acuity in comparison to diabetics. A significant increase in mean central foveal thickness (CFT) in diabetics and in non-diabetics post 1 month of surgery was observed; however, at 3 month, the difference was not significant. All the patients with mild, moderate, and severe non-proliferative diabetic retinopathy (NPDR) showed increment in the CFT from the baseline value but none of the patient of mild NPDR grade presented with new development of clinically significant macular edema on OCT. Conclusion: Cataract surgery causes a significant increase in macular thickness post 1 month of surgery in both diabetic and non-diabetics. Cataract surgery did not lead to the progression of stages of DR, although patients with all the three grades of DR showed increment in CFT from the baseline reference value.

Hybrid Fusion of High-Resolution and Ultra-Widefield OCTA Acquisitions for the Automatic Diagnosis of Diabetic Retinopathy.

Optical coherence tomography angiography (OCTA) can deliver enhanced diagnosis for diabetic retinopathy (DR). This study evaluated a deep learning (DL) algorithm for automatic DR severity assessment using high-resolution and ultra-widefield (UWF) OCTA. Diabetic patients were examined with 6×6 mm2 high-resolution OCTA and 15×15 mm2 UWF-OCTA using PLEX®Elite 9000. A novel DL algorithm was trained for automatic DR severity inference using both OCTA acquisitions. The algorithm employed a unique hybrid fusion framework, integrating structural and flow information from both acquisitions. It was trained on data from 875 eyes of 444 patients. Tested on 53 patients (97 eyes), the algorithm achieved a good area under the receiver operating characteristic curve (AUC) for detecting DR (0.8868), moderate non-proliferative DR (0.8276), severe non-proliferative DR (0.8376), and proliferative/treated DR (0.9070). These results significantly outperformed detection with the 6×6 mm2 (AUC = 0.8462, 0.7793, 0.7889, and 0.8104, respectively) or 15×15 mm2 (AUC = 0.8251, 0.7745, 0.7967, and 0.8786, respectively) acquisitions alone. Thus, combining high-resolution and UWF-OCTA acquisitions holds the potential for improved early and late-stage DR detection, offering a foundation for enhancing DR management and a clear path for future works involving expanded datasets and integrating additional imaging modalities.

Early Sign of Retinal Neovascularization Evolution in Diabetic Retinopathy: A Longitudinal OCT Angiography Study

To assess whether the combination of en face OCT and OCT angiography (OCTA) can capture observable, but subtle, structural changes that precede clinically evident retinal neovascularization (RNV) in eyes with diabetic retinopathy (DR). Retrospective, longitudinal study. Patients with DR that had at least 2 visits. We obtained wide-field OCTA scans of 1 eye from each participant and generated en face OCT, en face OCTA, and cross-sectional OCTA. We identified eyes with RNV sprouts, defined as epiretinal hyperreflective materials on en face OCT with flow signals breaching the internal limiting membrane on the cross-sectional OCTA without recognizable RNV on en face OCTA and RNV fronds, defined as recognizable abnormal vascular structures on the en face OCTA. We examined the corresponding location from follow-up or previous visits for the presence or progression of the RNV. The characteristics and longitudinal observation of early signs of RNV. From 71 eyes, we identified RNV in 20 eyes with the combination of OCT and OCTA, of which 13 (65%) were photographically graded as proliferative DR, 6 (30%) severe nonproliferative DR, and 1 (5%) moderate nonproliferative diabetic retinopathy. From these eyes, we identified 38 RNV sprouts and 26 RNV fronds at the baseline. Thirty-four RNVs (53%) originated from veins, 24 (38%) were from intraretinal microabnormalities, and 6 (9%) were from a nondilated capillary bed. At the final visit, 53 RNV sprouts and 30 RNV fronds were detected. Ten eyes (50%) showed progression, defined as having a new RNV lesion or the development of an RNV frond from an RNV sprout. Four (11%) RNV sprouts developed into RNV fronds with a mean interval of 7.0 months. Nineteen new RNV sprouts developed during the follow-up, whereas no new RNV frond was observed outside an identified RNV sprout. The eyes with progression were of younger age (P= 0.014) and tended to be treatment naive (P= 0.07) compared with eyes without progression. Longitudinal observation demonstrated that a combination of en face OCT and cross-sectional OCTA can identify an earlier form of RNV before it can be recognized on en face OCTA. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

SUPPORT VECTOR MACHINE MODELS FOR DIABETIC RETINOPATHY DIAGNOSIS AND GRADING

This work applies five variants of the support vector machine to the classification of the various stages of nonproliferative diabetic retinopathy. Four hundred eye fundus images from the Messidor repository are preprocessed and thirteen features extracted. The features best suited as inputs for support vector machine classification are identified. Initially, binary classification of severe nonproliferative diabetic retinopathy alone versus a normal eye is performed, achieving an accuracy of 97.44% using the standard support vector machine with Gaussian kernel and when optimized for accuracy. When optimized for sensitivity, the twin bounded support vector machine achieves the highest sensitivity of 99.06%. Then multiclass grading into all four stages of nonproliferative diabetic retinopathy is performed. Best performance with regards to four performance metrics, namely accuracy, sensitivity, specificity, and precision is achieved with the twin bounded support vector machine variant, when one-versus-one decision configuration is used in combination with a novel decision strategy that includes accumulated distances from the decision hyperplanes in the decision algorithm. The results compare favorably with data published in the literature.

Overcoming Nonlinear Dynamics in Diabetic Retinopathy Classification: A Robust AI-Based Model with Chaotic Swarm Intelligence Optimization and Recurrent Long Short-Term Memory

Diabetic retinopathy (DR), which is seen in approximately one-third of diabetes patients worldwide, leads to irreversible vision loss and even blindness if not diagnosed and treated in time. It is vital to limit the progression of DR disease in order to prevent the loss of vision in diabetic patients. It is therefore essential that DR disease is diagnosed at an early phase. Thanks to retinal screening at least twice a year, DR disease can be diagnosed in its early phases. However, due to the variations and complexity of DR, it is really difficult to determine the phase of DR disease in current clinical diagnoses. This paper presents a robust artificial intelligence (AI)-based model that can overcome nonlinear dynamics with low computational complexity and high classification accuracy using fundus images to determine the phase of DR disease. The proposed model consists of four stages, excluding the preprocessing stage. In the preprocessing stage, fractal analysis is performed to reveal the presence of chaos in the dataset consisting of 12,500 color fundus images. In the first stage, two-dimensional stationary wavelet transform (2D-SWT) is applied to the dataset consisting of color fundus images in order to prevent information loss in the images and to reveal their characteristic features. In the second stage, 96 features are extracted by applying statistical- and entropy-based feature functions to approximate, horizontal, vertical, and diagonal matrices of 2D-SWT. In the third stage, the features that keep the classifier performance high are selected by a chaotic-based wrapper approach consisting of the k-nearest neighbor (kNN) and chaotic particle swarm optimization algorithms (CPSO) to cope with both chaoticity and computational complexity in the fundus images. At the last stage, an AI-based classification model is created with the recurrent neural network-long short-term memory (RNN-LSTM) architecture by selecting the lowest number of feature sets that can keep the classification performance high. The performance of the DR disease classification model was tested on 2500 color fundus image data, which included five classes: no DR, mild non-proliferative DR (NPDR), moderate NPDR, severe NPDR, and proliferative DR (PDR). The robustness of the DR disease classification model was confirmed by the 10-fold cross-validation. In addition, the classification performance of the proposed model is compared with the support vector machine (SVM), which is one of the machine learning techniques. The results obtained show that the proposed model can overcome nonlinear dynamics in color fundus images with low computational complexity and is very effective and successful in precisely diagnosing all phases of DR disease.

Improved Invasive Weed Social Ski-Driver Optimization-Based Deep Convolution Neural Network for Diabetic Retinopathy Classification

The eye-related problem of diabetes is called diabetic retinopathy (DR), which is the main factor contributing to visual loss. This research develops an enhanced deep model for DR classification. Here, deep convolutional neural network (Deep CNN) is trained with the improved invasive weed social ski-driver optimization (IISSDO), which is generated by fusing improved invasive weed optimization (IIWO) and social ski-driver (SSD). The IISSDO-based Deep CNN classifies DR severity into normal, mild, non-proliferative DR (NPDR), moderate NPDR, severe NPDR, and proliferative. Initially, a type 2 fuzzy and cuckoo search (T2FCS) filter performs pre-processing and the quality of the data is improved by data augmentation. The lesion is then divided using DeepJoint segmentation. Then, the Deep CNN determines the DR. The analysis uses the Indian DR image database. The IISSDO-based Deep CNN has the highest accuracy, sensitivity, and specificity of 96.566%, 96.773%, and 96.517%, respectively.

Automatic diagnosis of diabetic retinopathy using vision transformer based on wide-field optical coherence tomography angiography

Diabetic retinopathy (DR) is one of the major causes of visual impairment in adults with diabetes. Optical coherence tomography angiography (OCTA) is nowadays widely used as the golden criterion for diagnosing DR. Recently, wide-field OCTA (WF-OCTA) provided more abundant information including that of the peripheral retinal degenerative changes and it can contribute in accurately diagnosing DR. The need for an automatic DR diagnostic system based on WF-OCTA pictures attracts more and more attention due to the large diabetic population and the prevalence of retinopathy cases. In this study, automatic diagnosis of DR using vision transformer was performed using WF-OCTA images (12[Formula: see text]mm × 12[Formula: see text]mm single-scan) centered on the fovea as the dataset. WF-OCTA images were automatically classified into four classes: No DR, mild nonproliferative diabetic retinopathy (NPDR), moderate to severe NPDR, and proliferative diabetic retinopathy (PDR). The proposed method for detecting DR on the test set achieves accuracy of 99.55%, sensitivity of 99.49%, and specificity of 99.57%. The accuracy of the method for DR staging reaches up to 99.20%, which has been proven to be higher than that attained by classical convolutional neural network models. Results show that the automatic diagnosis of DR based on vision transformer and WF-OCTA pictures is more effective for detecting and staging DR.