Diabetic Retinopathy Severity Level Research Articles

Feasibility of Diagnosing Both Severity and Features of Diabetic Retinopathy in Fundus Photography

Diabetic retinopathy (DR) diagnosis methods in the literature are usually criticized as being limit in diagnosing DR-related features or being lack of interpretability. To deal with these issues, this paper investigates the feasibility of diagnosing both DR severity levels and the presence of DR-related features in a two-step procedure. Specifically, this paper first analyzes the quality of annotations in DR grading by measuring inter-grader variability. Cosine similarity is considered to evaluate the inter-grader variability of the presence of DR-related features, and quadratic weighted Cohen's kappa is employed to assess the inter-grader variability of DR severity levels. Next, different annotation methods as follows are compared to DR severity prediction performance using logistic regression: 1) single annotations by single grader (SASG); 2) single annotations from multiple graders (SAMG); 3) multiple annotations by voting (MAV); and 4) double annotations with adjudication of disagreement (DAAD). Based on the comparison results, the feasibility of diagnosing both DR severity and features is investigated. In the experiments, 1589 fundus images graded by three retinal specialists and four general ophthalmologists are considered. The results demonstrate that retinal specialists are more consistent than general ophthalmologists in grading both the presence of DR-related features and DR severity. The SASG and MAV should be avoided if possible while the DAAD is the good option when prediction performance is the highest priority and the SAMG is especially beneficial when both prediction performance and grading costs are considered. The upper limit performance of DR severity prediction gets accuracy 95.6% and kappa 0.962. When DR-related feature prediction achieves average cosine similarity 0.823, it is potential to get accuracy 91.2% and kappa 0.905 for DR severity prediction in real applications. These results together suggest the potential of diagnosis of both DR severity and the presence of DR-related features in a two-step procedure.

Accuracy of Detection and Grading of Diabetic Retinopathy and Diabetic Macular Edema Using Teleretinal Screening

To determine the accuracy of a county teleretinal screening program of detecting referable diabetic retinopathy (DR) and treatable diabetic macular edema (DME), as well as to evaluate patient compliance with clinic follow-up after referral from teleretinal screening. Retrospective observational study. Patients in the Harris Health System (HHS, Houston, TX) older than 18 years of age who underwent teleretinal screening between July 2014 and July2016. Teleretinal imaging (TRI) consisting of single-field 45-degree nonmydriatic color fundus photography with referral thresholds of severe nonproliferative DR, proliferative DR, and significant DME. Teleretinal imaging results for all referred subjects were obtained and cross-referenced with dilated fundus examination findings with regard to DR severity and the presence of DME. Follow-up status was also noted. Subjects underwent OCT if deemed necessary by the examining specialist. Agreement between TRI and dilated fundus examination (DFE) findings was determined by calculating the Cohen κ coefficient. The primary outcome measure is agreement between TRI results and DFE findings with regard to DR severity and the presence of DME. The secondary outcome measure is compliance with follow-up. Of 1767 patients who were screened and referred for clinical examination, 935 (52.9%) attended their clinic appointment. Overall agreement between DFE and TRI was moderate (weighted κ 0.45) in terms of DR severity. There was agreement within one DR severity level in 86.2% of patients. The positive predictive value for detecting referable disease was 71.3%. Of patients referred for DME, 30.4% were deemed to have treatable DME. The HHS teleretinal screening program demonstrates a high level of accuracy in the detection and classification of referable DR, but a lesser degree of accuracy in the detection of treatable DME. Only slightly more than half of participants were compliant with follow-up after a TRI referral. This large-scale study provides insight into the utility of teleretinal screening in a county health care system.

Ranibizumab Induces Regression of Diabetic Retinopathy in Most Patients at High Risk of Progression to Proliferative Diabetic Retinopathy

To evaluate diabetic retinopathy (DR) outcomes with ranibizumab (Lucentis, Genentech, Inc., South San Francisco, CA) treatment in patients with DR and diabetic macular edema (DME) at high risk of progression to proliferative disease. Post hoc analysis of the phase 3 RIDE (ClinicalTrials.gov identifier, NCT00473382) and RISE (ClinicalTrials.gov identifier, NCT00473330) clinical trials of ranibizumab for the treatment of DME. Seven hundred forty-six patients with baseline fundus photographs and randomized for treatment. Diabetic retinopathy outcomes were assessed through month 36 by baseline DR severity level. Diabetic retinopathy severity was quantified using the Early Treatment Diabetic Retinopathy Study (ETDRS) Diabetic Retinopathy Severity Scale (DRSS). Two-step or more or 3-step or more improvement or worsening on the ETDRS DRSS and time to new proliferative event (composite end point). At baseline, most patients were distributed evenly among mild or moderate nonproliferative DR (NPDR; ETDRS DRSS, 35/43), moderately severe or severe NPDR (ETDRS DRSS, 47/53), and proliferative DR (ETDRS DRSS, 60-75; 28.8%, 33.2%, and 31.1%, respectively). At month 24, rates of 2-step or more improvement with ranibizumab 0.3 mg, ranibizumab 0.5 mg, and sham treatment were highest among patients with baseline DR levels 47/53 (78.4%, 81.1%, and 11.6%, respectively) compared with patients with baseline DR levels 35/43 (10.3%, 15.8%, and 1.4%, respectively) or 60 through 75 without panretinal photocoagulation (31.0%, 36.4%, and 6.7%, respectively; all ranibizumab vs. sham comparisons, P < 0.05). In patients with baseline DR levels 47/53, ranibizumab treatment reduced the probability of patients experiencing a new proliferative event at month 36 by 3 times compared with sham treatment (12.4% and 11.9% vs. 35.2% for ranibizumab 0.3 mg, ranibizumab 0.5 mg, and sham, respectively). In patients with baseline DR levels 47/53 who achieved 2-step or more DR improvement, improvements were independent of all assessed baseline characteristics (P > 0.4). Ranibizumab treatment resulted in DR improvements in all 3 baseline DR severity subsets examined. The greatest benefits in DR improvement occurred in patients with baseline moderately severe to severe NPDR (DR levels 47/53). Diabetic retinopathy improvements were rapid, clinically meaningful, and sustained through month36.

Ranibizumab-Induced Diabetic Retinopathy Improvement—Results from Patients at High Risk for Vision Loss in RIDE/RISE and Protocol S

Purpose: To examine diabetic retinopathy (DR) outcomes in patients (pts) at high risk for negative outcomes using data from RIDE/RISE and Protocol S. In RIDE/RISE, pts with moderately severe to severe nonproliferative DR (NPDR) at baseline were assessed due to their high risk for progression to proliferative disease (ETDRS Report 12. Ophthalmology. 1991). In Protocol S, the majority of pts had proliferative DR (PDR) at baseline, which is associated with vision loss (Moss. Ophthalmology. 1998), and DR outcomes were assessed according to diabetic macular edema (DME) status at baseline. Methods: In the randomized phase 3 RIDE (NCT00473382)/RISE (NCT00473330) studies, pts with DME (N = 759) received monthly ranibizumab (RBZ) (0.3 mg or 0.5 mg) or sham treatment through the month (M) 24 primary end point. In the randomized phase 3 Protocol S (NCT01489189) study, eyes with and without DME received either prompt pan-retinal photocoagulation or RBZ 0.5 mg (as needed after 3 monthly treatments) (N = 394 eyes). M24 DR outcomes are retrospectively evaluated herein. Results: In RIDE/RISE, ∼ 30% of pts in each arm had high-risk NPDR at baseline (DR severity level 47/53) (35.9%, 30.0%, and 33.9% for RBZ 0.3 mg, RBZ 0.5 mg, and sham, respectively). A significant majority of these pts (78.4% and 81.1% of RBZ 0.3 mg- and 0.5 mg-treated, respectively) achieved ≥ 2-step DR improvement at M24 vs. only 11.6% of sham-treated pts (P &amp;lt; .0001). Notably, these rates of ≥ 2-step DR improvement with RBZ were more than 2 times higher than the overall population at M24 (37.2% and 35.9% for RBZ 0.3 mg and 0.5 mg, respectively) (Ip. Arch Ophthalmol. 2012). In Protocol S, 87% of eyes had PDR and 22% of eyes had DME at baseline. At M24, RBZ treatment resulted in ≥ 2-step DR improvement in eyes with (58.5%) and without (37.8%) DME at baseline. Conclusions: RBZ treatment was effective at significantly improving DR in pts at high risk for DR-related vision loss, irrespective of baseline DME status. Disclosure V. Hershberger: None. L.F. Hill: Employee; Self; Genentech, Inc. L.L. Tuomi: Employee; Self; Genentech, Inc. A. Ghanekar: Employee; Self; Roche Pharma. Stock/Shareholder; Self; Roche Pharma.

Clinical Association between Diabetic Peripheral Neuropathy and Diabetic Retinopathy

Purpose: To quantify the association between diabetic peripheral neuropathy (DPN) and diabetic retinopathy (DR), as expressed in terms of thermal regulation of the plantar foot and vascular abnormalities in the retina. Background: DPN accounts for around 73,000 lower-limb amputations in diabetics annually in the U.S., partially due to low compliance with periodic screening for DPN. Similarly, annual retinal screening for DR in diabetics is recommended by ADA and others. Identifying and referring individuals at risk for DPN by using biomarkers in retina could improve compliance for DPN screening. Methods: Subjects (55-75 years) clinically diagnosed with DPN (N=20) and a set of age-matched controls (N=29) were selected. Thermal videos and retinal images were collected for all subjects. Subjects’ feet were imaged with an infrared (thermal) imager to obtain: 1) baseline temperature for 3 min, and 2) thermal recovery temperature for 10 min after a cold-patch provocation. Presence of DPN was determined by clinical examination. Retinal imaging was performed on each eye to obtain macula- and disc-centered images. A certified grader read the retinal images for severity level of DR and other retinal abnormalities. A logistic regression analysis was performed to compare retinal and thermal features, with the clinical diagnosis of DPN. Results: A logistic regression determined a statistically significant difference (p &amp;lt; 0.05) in DR severity levels between DPN subjects and controls. The association between thermal features and DPN was demonstrated by statistically significant difference in recovery temperatures for both feet obtained in 1 min after cold provocation (p &amp;lt; 0.01), between DPN and controls. Discussion: This study demonstrates the value of using characteristics of DR screening to identify individuals also at risk for DPN. A thermal imager located at the same screening site as a retinal camera could improve compliance with DPN screening and potentially prevent unnecessary foot complications. Disclosure Z. Jarry: None. V. Joshi: None. M. Vahtel: None. M.R. Burge: Research Support; Self; VisionQuest Biomedical LLC.. P. Soliz: None.

The Relationship of Retinal Vessel Geometric Characteristics to the Incidence and Progression of Diabetic Retinopathy

To examine the relationships of retinal vessel geometric characteristics (RVGCs) to the incidence and progression of diabetic retinopathy (DR). Observational, prospective cohort study. Nine hundred ninety-six persons with type 1 diabetes mellitus (T1DM) and 1370 persons with type 2 diabetes mellitus (T2DM) seen at a baseline examination who were eligible for follow-up examinations at subsequent 5-year intervals. A total of 3846 person-interval data from these follow-up examinations are the basis for the analyses. Diabetic retinopathy and macular edema were assessed by grading of 30° stereoscopic color fundus photographs. Retinal vessel geometric characteristics were assessed using the Singapore I Vessel Assessment program from a digitized copy of 1 of the field 1 fundus photographs obtained at baseline and follow-up. The 5-year incidence of any DR, progression of DR, and incidence of proliferative diabetic retinopathy (PDR) and clinically significant macular edema (CSME) in right eyes. Incident DR occurred in 45%, progression in 32%, PDR in 10%, and CSME in 5%. While adjusting for glycated hemoglobin, duration of diabetes, and other factors, retinal arteriolar simple tortuosity was associated significantly with the incidence of any DR (odds ratio [OR], 1.17; 95% confidence interval [CI], 1.01-1.35). Retinal venular branching angle was associated significantly with progression of DR (OR, 1.18; 95% CI, 1.03-1.36), retinal venular curvature tortuosity was associated significantly with the incidence of PDR (OR, 1.15; 95% CI, 1.01-1.30), and retinal venular branching angle (OR, 1.41; 95% CI, 1.10-1.82) was associated significantly with the incidence of CSME. There were no significant associations of other RVGCs with any of the DR outcomes in the full multivariate model. Inclusion of all possible RVGCs did not improve the predictive value of the models that already included retinal vessel diameter and baseline DR severity level. Retinal vessel geometric characteristics of the retinal venules were associated with progression of DR; however, most of the RVGCs measured from digitized fundus photographs added little to the assessment of risk of incidence and progression of DR when other risk factors were considered in T1DM and T2DM.

An automated grading system for diabetic retinopathy using curvelet transform and hierarchical classification

In this paper, an automated system for grading the severity level of Diabetic Retinopathy (DR) disease based on fundus images is presented. Features are extracted using fast discrete curvelet transform. These features are applied to hierarchical support vector machine (SVM) classifier to obtain four types of grading levels, namely, normal, mild, moderate and severe. These grading levels are determined based on the number of anomalies such as microaneurysms, hard exudates and haemorrhages that are present in the fundus image. The performance of the proposed system is evaluated using fundus images from the Messidor database. Experiment results show that the proposed system can achieve an accuracy rate of 86.23%.

Estimation of severity level of non-proliferative diabetic retinopathy for clinical aid

Diabetic retinopathy, a symptomless complication of diabetes, is one of the significant causes of vision impairment in the world. The early detection and diagnosis can reduce the occurrence of severe vision loss due to diabetic retinopathy. The diagnosis of diabetic retinopathy depends on the reliable detection and classification of bright and dark lesions present in retinal fundus images. Therefore, in this work, reliable segmentation of lesions has been performed using iterative clustering irrespective of associated heterogeneity, bright and faint edges. Afterwards, a computer-aided severity level detection method is proposed to aid ophthalmologists for appropriate treatment and effective planning in the diagnosis of non-proliferative diabetic retinopathy. This work has been performed on a composite database of 5048 retinal fundus images having varying attributes such as position, dimensions, shapes and color to make a reasonable comparison with state-of-the-art methods and to establish generalization capability of the proposed method. Experimental results on per-lesion basis show that the proposed method outperforms state-of-the-methods with an average sensitivity/specificity/accuracy of 96.41/96.57/94.96 and 95.19/96.24/96.50 for bright and dark lesions respectively on composite database. Individual per-image based class accuracies delivered by the proposed method: No DR-95.9%, MA-98.3%, HEM-98.4%, EXU-97.4% and CWS-97.9% demonstrate the clinical competence of the method. Major contribution of the proposed method is that it efficiently grades the severity level of diabetic retinopathy in spite of huge variations in retinal images of different databases. Additionally, the substantial combined performance of these experiments on clinical and open source benchmark databases support a strong candidature of the proposed method in the diagnosis of non-proliferative diabetic retinopathy.

Impact of intravitreal pharmacotherapies including antivascular endothelial growth factor and corticosteroid agents on diabetic retinopathy.

Diabetic retinopathy is common and increasing in prevalence. Pharmacologic management of diabetic macular edema (DME) has improved tremendously over the last decade with the use of two families of intravitreally administered medications: antivascular endothelial growth factor-specific agents and corticosteroids. Clinical evaluation of these pharmaceuticals has demonstrated that they can have a substantial impact on diabetic retinopathy severity levels and the underlying retinal vasculature itself. Phase 3 trials employing ranibizumab, aflibercept, and fluocinolone acetonide enrolling eyes with center-involving DME causing visual acuity loss have demonstrated impressive alteration of the natural history of progressive diabetic retinopathy worsening over time through blunted progression to proliferative diabetic retinopathy, improving diabetic retinopathy severity levels, and slowing progressive retinal nonperfusion, the underlying disease process central to diabetic retinopathy itself. Accumulating data indicate that the threshold to initiate ocular-specific pharmacologic treatment for diabetic retinopathy, previously predominately limited to eyes with visual loss because of center-involved DME or proliferative diabetic retinopathy, is being lowered to earlier stages of diabetic retinopathy. Ongoing clinical trials and secondary analyses continue to further explore the impact and durability of vascular endothelial growth factor blockade and corticosteroids on modification of diabetic retinopathy and the underlying retinal vasculature itself.

Automatic recognition of severity level for diagnosis of diabetic retinopathy using deep visual features.

Diabetic retinopathy (DR) is leading cause of blindness among diabetic patients. Recognition of severity level is required by ophthalmologists to early detect and diagnose the DR. However, it is a challenging task for both medical experts and computer-aided diagnosis systems due to requiring extensive domain expert knowledge. In this article, a novel automatic recognition system for the five severity level of diabetic retinopathy (SLDR) is developed without performing any pre- and post-processing steps on retinal fundus images through learning of deep visual features (DVFs). These DVF features are extracted from each image by using color dense in scale-invariant and gradient location-orientation histogram techniques. To learn these DVF features, a semi-supervised multilayer deep-learning algorithm is utilized along with a new compressed layer and fine-tuning steps. This SLDR system was evaluated and compared with state-of-the-art techniques using the measures of sensitivity (SE), specificity (SP) and area under the receiving operating curves (AUC). On 750 fundus images (150 per category), the SE of 92.18%, SP of 94.50% and AUC of 0.924 values were obtained on average. These results demonstrate that the SLDR system is appropriate for early detection of DR and provide an effective treatment for prediction type of diabetes.

Optical Coherence Tomographic Angiography in Type 2 Diabetes and Diabetic Retinopathy

ImportanceOptical coherence tomographic angiography (OCT-A) is able to visualize retinal microvasculature without the need for injection of fluorescein contrast dye. Nevertheless, it is only able to capture a limited view of macula and does not show leakage.ObjectivesTo evaluate the retinal microvasculature using OCT-A in patients with type 2 diabetes as well as the association of OCT-A characteristics with diabetic retinopathy (DR) and systemic risk factors.Design, Setting, and ParticipantsA prospective, observational study was conducted from January 1 to June 30, 2016, at medical retina clinics at the Singapore National Eye Center among 50 patients with type 2 diabetes with and without DR (n = 100 eyes). We examined the retinal microvasculature with swept-source OCT-A and a semiautomated software to measure the capillary density index (CDI) and fractal dimension (FD) at the superficial vascular plexus (SVP) and deep retinal vascular plexus (DVP). We collected data on histories of patients’ glycated hemoglobin A1c, hypertension, hyperlipidemia, smoking, and renal impairment.Main Outcomes and MeasuresThe CDI and FD at the SVP and DVP for each severity level of DR and the association of systemic risk factors vs the CDI and FD.ResultsThe mean (SD) glycated hemoglobin A1c of the 50 patients (26 men and 24 women; 35 Chinese; mean [SD] age, 59.5 [8.9] years) was 7.9% (1.7%). The mean (SD) CDI at the SVP decreased from 0.358 (0.017) in patients with no DR to 0.338 (0.012) in patients with proliferative DR (P < .001) and at the DVP decreased in patients with no DR from 0.361 (0.019) to 0.345 (0.020) in patients with proliferative DR (P = .04). The mean (SD) FD at the SVP increased from 1.53 (0.05) in patients with no DR to 1.60 (0.05) in patients with proliferative DR (P < .01) and at the DVP increased from 1.55 (0.06) in patients with no DR to 1.61 (0.05) in patients with proliferative DR (P = .02). For systemic risk factors, hyperlipidemia (odds ratio [OR], 9.82; 95% CI, 6.92-11.23; P < .001), smoking (OR, 10.90; 95% CI, 8.23-12.34; P < .001), and renal impairment (OR, 3.72; 95% CI, 1.80-4.81; P = .05) were associated with reduced CDI, while increased glycated hemoglobin A1c (≥8%) (OR, 8.77; 95% CI, 5.23-10.81; P < .01) and renal impairment (OR, 10.30; 95% CI, 8.21-11.91; P < .001) were associated with increased FD.Conclusions and RelevanceOptical coherence tomographic angiography is a novel imaging modality to quantify the retinal capillary microvasculature in patients with diabetes. It can be potentially used in interventional trials to study the effect of systemic risk factors on the microvasculature that was previously not accessible in a noninvasive manner. The relevance of these findings relative to visual acuity, however, remains largely unknown at this time.

Type 2 Diabetes Genetic Variants and Risk of Diabetic Retinopathy

Genetic association studies to date have not identified any robust risk loci for diabetic retinopathy (DR). We hypothesized that individuals with more diabetes genetic risk alleles have a higher risk of developing DR. Case-control genetic association study. We evaluated the aggregate effects of multiple type 2 diabetes-associated genetic variants on the risk of DR among 1528 participants with diabetes from the Singapore Epidemiology of Eye Diseases Study, of whom 547 (35.8%) had DR. Participants underwent a comprehensive ocular examination, including dilated fundus photography. Retinal photographs were graded using the modified Airlie House classification system to assess the presence and severity of DR following a standardized protocol. We identified 76 previously discovered type 2 diabetes-associated single nucleotide polymorphisms (SNPs) and constructed multilocus genetic risk scores (GRSs) for each individual by summing the number of risk alleles for each SNP weighted by the respective effect estimates on DR. Two GRSs were generated: an overall GRS that included all 76 discovered type 2 diabetes-associated SNPs, and an Asian-specific GRS that included a subset of 55 SNPs previously found to be associated with type 2 diabetes in East and/or South Asian ancestry populations. Associations between the GRSs with DR were determined using logistic regression analyses. Discriminating ability of the GRSs was determined by the area under the receiver operating characteristic curve (AUC). Odds ratios on DR. Participants in the top tertile of the overall GRS were 2.56-fold more likely to have DR compared with participants in the lowest tertile. Participants in the top tertile of the Asian-specific GRS were 2.00-fold more likely to have DR compared with participants in the bottom tertile. Both GRSs were associated with higher DR severity levels. However, addition of the GRSs to traditional risk factors improved the AUC only modestly by 3% to 4%. Type 2 diabetes-associated genetic loci were significantly associated with higher risks of DR, independent of traditional risk factors. Our findings may provide new insights to further our understanding of the genetic pathogenesis of DR.

Visual and Anatomic Outcomes in Patients with Diabetic Macular Edema with Limited Initial Anatomic Response to Ranibizumab in RIDE and RISE

To explore the visual acuity and anatomic outcomes over 24 months of patients with diabetic macular edema (DME) who showed a delayed anatomic response after 3 ranibizumab injections in the RIDE and RISE trials. Analysis of data from RIDE and RISE, 2 phase III, parallel, randomized, multicenter, double-masked trials (ClinicalTrials.gov identifiers, NCT00473382 and NCT00473330). Patients with DME (n= 681) who received monthly intravitreal ranibizumab 0.3-mg injections, ranibizumab 0.5-mg injections, or sham injections. Patients were separated into 3 groups: delayed responders (ranibizumab-treated patients with ≤10% central foveal thickness [CFT] reduction after 3 injections), immediate responders (ranibizumab-treated patients with >10% CFT reduction after 3 injections), and sham recipients. Central foveal thickness was measured by time-domain optical coherence tomography, best-corrected visual acuity (BCVA) was measured by Early Treatment Diabetic Retinopathy Study (ETDRS) letter scores, and diabetic retinopathy (DR) was measured by the standardized ETDRS severity scale (using fundus photographs). Month-24 CFT, BCVA, and DR severity levels. In RIDE and RISE, 9% to 10% of ranibizumab-treated eyes were delayed responders. At month 24, delayed responders had less CFT reduction (median,-102 μm) from baseline compared with immediate responders (median,-274 μm; P < 0.0001). Delayed responders gained a median of 10 letters at 24 months, similar to immediate responders (14 letters; P= 0.15). At month 24, DR improvement among the delayed responders (31% and 22% of patients with ≥2- or ≥3-step DR improvement, respectively) was comparable with that among immediate responders (42% and 17%, respectively; P= 0.21 and P= 0.48, respectively). With continued treatment, at month 24, patients with DME with delayed anatomic response (≤10% CFT reduction) after 3 ranibizumab injections had visual acuity gains and DR improvement similar to those of patients with DME who had immediate anatomic response.

RANIBIZUMAB PLUS PROMPT OR DEFERRED LASER FOR DIABETIC MACULAR EDEMA IN EYES WITH VITRECTOMY BEFORE ANTI-VASCULAR ENDOTHELIAL GROWTH FACTOR THERAPY.

The approach to managing diabetic macular edema in eyes with previous vitrectomy is based on limited evidence. Therefore, an exploratory post hoc assessment of 3-year data from eyes with and without vitrectomy before randomization in a DRCR.net trial that evaluated ranibizumab + prompt or deferred laser for diabetic macular edema is presented. Visual acuity and optical coherence tomography outcomes were compared between eyes with and without previous vitrectomy. At baseline, eyes with previous vitrectomy (n = 25) had longer duration of diabetes, worse visual acuity, less thickened central subfield measurements on optical coherence tomography and were more apt to have worse diabetic retinopathy severity level or previous treatment for macular edema or cataract surgery than eyes without a history of vitrectomy (n = 335). Analyses adjusted for these baseline imbalances did not identify substantial differences between eyes with and without previous vitrectomy at each annual visit through 3 years for the favorable visual acuity, optical coherence tomography central subfield thickness, or volume outcomes, although optical coherence tomography improvement appeared slower in vitrectomy eyes during the first year. This study provides little evidence that the beneficial clinical outcomes for patients with center-involved diabetic macular edema treated with anti-vascular endothelial growth factor are affected in the long term by previous vitrectomy.

Peripheral Lesions Identified on Ultrawide Field Imaging Predict Increased Risk of Diabetic Retinopathy Progression over 4 Years

To determine whether peripheral diabetic retinopathy (DR) lesions identified on ultrawide field (UWF) imaging are associated with increased DR progression. Prospective, longitudinal cohort. Two hundred eyes of 100 participants previously enrolled in a comparative instrument validation study. Baseline mydriatic 7-standard field Early Treatment Diabetic Retinopathy Study (ETDRS) photographs and UWF images were obtained. On UWF images, DR lesions with a greater extent outside versus inside standard ETDRS fields were defined as predominantly peripheral lesions (PPLs). Follow-up ETDRS photographs were obtained 4.2±0.3 years after baseline. Baseline and follow-up DR severity were graded from ETDRS photographs. Rates of 2-step or more progression and progression to proliferative DR (PDR) in eyes with PPLs compared with eyes without PPLs identified on UWF imaging at baseline. In eyes without PDR (n = 109) at baseline, 56 (51%) had at least 1 field with PPLs and 43 (39%) had DR progression. Compared with eyes without PPLs, eyes with PPLs had a 3.2-fold increased risk of 2-step or more DR progression (6 [11%] vs. 19 [34%]; P = 0.005) and a 4.7-fold increased risk for progression to PDR (3 [6%] vs. 14 [25%]; P = 0.005). These findings remained statistically significant after adjusting for gender, diabetes type, diabetes duration, hemoglobin A1c (HbA1c) levels, and baseline DR severity. Increasing extent of fields with PPLs increased the risk for 2-step or more DR progression (P = 0.004) and progression to PDR (P = 0.009). Presence and increasing extent of PPLs were associated with increased risk of DR progression over 4 years, independent of baseline DR severity and HbA1c levels. Increasing extent of PPLs substantially increased the risk of DR progression and progression to PDR, especially with less severe DR at baseline. These findings demonstrate that detailed peripheral retinal evaluation provides important information that is necessary to assess completely the risk of DR progression.

Investigation of the severity level of diabetic retinopathy using supervised classifier algorithms

Diabetic retinopathy is a condition that occurs in individuals with several years of diabetes mellitus and causes a characteristic group of lesions in the retina and progressively damages it. Detecting retinal fundus diseases in advance helps ophthalmologists to apply proper treatments that may cure the disease or decrease its severity and thus protect patients from vision loss. Diabetic retinopathy is usually diagnosed by ophthalmologists using dilated images that are captured by pouring a chemical solution into the patient’s eye, which causes inconvenience and irritation to the patient. In this paper, we propose a method to detect lesion exudates automatically with the aid of a non-dilated retinal fundus image to help ophthalmologists diagnose the disease. The exudates from the low contrast images are detected and localised using a neighbourhood based segmentation technique. A support vector machine (SVM) and probabilistic neural network (PNN) classifiers are proposed to assess the severity of the disease, and the results are compared with the same segmentation technique. The average classification accuracy for the SVM and PNN classifiers are determined to be 97.89% and 94.76%, respectively.

Development of Algorithm for Dual Stage Classification to Estimate Severity Level of Diabetic Retinopathy in Retinal Images using Soft Computing Techniques

Diabetic Retinopathy is a general origin of sight-threatening complication to which the condition occurring in persons with diabetes and which makes progressive damage to the retina. Retina is a back of eye with the light sensitive lining. The severity of this Diabetic Retinopathy in retina has four stages. The identification of the severity level of Diabetic Retinopathy in retina is a critical task. In order to make ease this task, a severity analysis method is proposed in this paper. The proposed method contains the 5 stages - (1) Pre-processing phase (2) Segmentation Phase (3) Feature Extraction Phase (4) Classification Phase I and (5) Classification Phase II. The retinal images are subjected to pre-processing phase for removing the noises from the image and make clear visible image of retina. Then the optic disks and the blood vessels in the retina are segmented using Modified Region Growing method and morphological operations, respectively. Before analyzing the severity in retinal images, it is necessary to classify the images into normal and abnormal images using Neural Network classifier. For this classification of images, the features mean, variance, entropy and area are extracted from the segmented optic disk of retinal images and also the features mean, variance, entropy, area, diameter and number of regions are extracted from the segmented blood vessels of retinal images. From the abnormal images, the severity of Diabetic Retinopathy can be evaluated by using SVM classifier based on area and intensity level of Hard Exudates and Hemorrhages. These techniques are implemented on publicly available database such as STARE and on real datasets using MATLAB 7.12. The performance of our proposed method is analyzed by Sensitivity, Specificity and Accuracy. From the results, it is proved that our work outperforms other works by providing very much better accuracy by classifying the severity level in Diabetic Retinopathy.

Effect of doxycycline vs placebo on retinal function and diabetic retinopathy progression in mild to moderate nonproliferative diabetic retinopathy: a randomized proof-of-concept clinical trial.

Microglia have been associated with inflammatory changes underlying diabetic retinopathy. To investigate whether low-dose oral doxycycline monohydrate, a drug capable of inhibiting microglial activation, can improve or slow the deterioration of retinal function and whether it can induce regression or slow progression of diabetic retinopathy in patients with mild to moderate nonproliferative diabetic retinopathy (NPDR). Randomized, double-masked, 24-month proof-of-concept clinical trial. We randomized 33 patients (from the Penn State Hershey Eye Center) with at least 1 eye with mild to moderate NPDR (Early Treatment Diabetic Retinopathy Study level 20-43) to doxycycline monohydrate, 50 mg/d, or daily placebo for 24 months. Mean change at 24 months compared with baseline in the foveal sensitivity of matrix frequency-doubling perimetry in each treatment group. We also compared the 2 groups with respect to change from baseline to 24 months in functional variables (Humphrey photopic visual field testing using the Swedish interactive thresholding algorithm 24-2 strategy, contrast sensitivity, dark adaptation, visual acuity, and quality of life) and anatomical variables (diabetic retinopathy severity level, area of retinal thickening, central subfield thickness on optical coherence tomography, and macular volume on optical coherence tomography). From baseline to month 24, no significant difference was detected between groups with respect to all visual function and anatomical outcomes assessed. Although a link between low-dose oral anti-inflammatory agents and subclinical improvement in inner retinal function has been suggested in patients with severe NPDR or non-high-risk proliferative diabetic retinopathy, the same association was not found in the present study of patients with mild to moderate NPDR. The different findings in the 2 patient populations may relate to a differential effect of doxycycline on different stages of diabetic retinal dysfunction, or the sample size of the present study may be too small to detect a treatment effect of doxycycline in patients with mild to moderate NPDR. clinicaltrials.gov Identifier: NCT00917553.

Effect of Doxycycline vs Placebo on Retinal Function and Diabetic Retinopathy Progression in Patients With Severe Nonproliferative or Non–High-Risk Proliferative Diabetic Retinopathy

Inflammation may contribute to the pathogenesis of diabetic retinopathy (DR). To investigate, in a proof-of-concept clinical trial, whether low-dose oral doxycycline monohydrate can (1) slow the deterioration of, or improve, retinal function or (2) induce regression or slow the progression of DR in patients with severe nonproliferative DR (NPDR) or non-high-risk proliferative (PDR), and to determine the potential usefulness of visual function end points to expedite the feasibility of conducting proof-of-concept clinical trials in patients with DR. We conducted a randomized, double-masked, 24-month proof-of-concept clinical trial. Thirty patients (from hospital-based retina practices) with 1 or more eyes with severe NPDR or PDR less than Early Treatment Diabetic Retinopathy Study-defined high-risk PDR. Patients were randomized to receive 50 mg of doxycycline monohydrate or placebo daily for 24 months. Change at 24 months compared with baseline in functional factors (frequency doubling perimetry [FDP], Humphrey photopic Swedish Interactive Thresholding Algorithm 24-2 testing, contrast sensitivity, dark adaptation, visual acuity, and quality of life) and anatomic factors (Early Treatment Diabetic Retinopathy Study DR severity level, area of retinal thickening, central macular thickness, macular volume, and retinal vessel diameters). From baseline to month 24, mean FDP foveal sensitivity decreased in the placebo group (-1.9 dB) and increased in the doxycycline group (+1.8 dB) (P = .02). A higher mean FDP foveal sensitivity in the doxycycline group compared with the placebo group was detected at 6 months (P = .04), and this significant difference persisted at 12 and 24 months. A difference between the groups was not detected with respect to the other visual function outcomes and all anatomic outcomes assessed. To our knowledge, this is the first observation suggesting a link between a low-dose oral anti-inflammatory agent and subclinical improvement in inner retinal function. Oral doxycycline may be a promising therapeutic strategy targeting the inflammatory component of DR. Furthermore, study results suggest that FDP, which primarily measures inner retinal function, is responsive to intervention and may be a useful clinical trial end point for proof-of-concept studies in patients with DR. clinicaltrials.gov Identifier: NCT00511875.

Comparison of Low-Light Nonmydriatic Digital Imaging with 35-mm ETDRS Seven-Standard Field Stereo Color Fundus Photographs and Clinical Examination

To compare agreement between diagnosis of clinical level of diabetic retinopathy (DR) and diabetic macular edema (DME) derived from nonmydriatic fundus images using a digital camera back optimized for low-flash image capture (MegaVision) compared with standard seven-field Early Treatment Diabetic Retinopathy Study (ETDRS) photographs and dilated clinical examination. Subject comfort and image acquisition time were also evaluated. In total, 126 eyes from 67 subjects with diabetes underwent Joslin Vision Network nonmydriatic retinal imaging. ETDRS photographs were obtained after pupillary dilation, and fundus examination was performed by a retina specialist. There was near-perfect agreement between MegaVision and ETDRS photographs (κ=0.81, 95% confidence interval [CI] 0.73-0.89) for clinical DR severity levels. Substantial agreement was observed with clinical examination (κ=0.71, 95% CI 0.62-0.80). For DME severity level there was near-perfect agreement with ETDRS photographs (κ=0.92, 95% CI 0.87-0.98) and moderate agreement with clinical examination (κ=0.58, 95% CI 0.46-0.71). The wider MegaVision 45° field led to identification of nonproliferative changes in areas not imaged by the 30° field of ETDRS photos. Field area unique to ETDRS photographs identified proliferative changes not visualized with MegaVision. Mean MegaVision acquisition time was 9:52 min. After imaging, 60% of subjects preferred the MegaVision lower flash settings. When evaluated using a rigorous protocol, images captured using a low-light digital camera compared favorably with ETDRS photography and clinical examination for grading level of DR and DME. Furthermore, these data suggest the importance of more extensive peripheral images and suggest that utilization of wide-field retinal imaging may further improve accuracy of DR assessment.