To evaluate the role of ensemble learning techniques with deep learning in classifying diabetic retinopathy (DR) in optical coherence tomography angiography (OCTA) images and their corresponding co-registered structural images. Methods: A total of 463 volumes from 380 eyes were acquired using the 3 × 3-mm OCTA protocol on the Zeiss Plex Elite system. Enface images of the superficial and deep capillary plexus were exported from both the optical coherence tomography and OCTA data. Component neural networks were constructed using single data-types and fine-tuned using VGG19, ResNet50, and DenseNet architectures pretrained on ImageNet weights. These networks were then ensembled using majority soft voting and stacking techniques. Results were compared with a classifier using manually engineered features. Class activation maps (CAMs) were created using the original CAM algorithm and Grad-CAM. Results: The networks trained with the VGG19 architecture outperformed the networks trained on deeper architectures. Ensemble networks constructed using the four finetuned VGG19 architectures achieved accuracies of 0.92 and 0.90 for the majority soft voting and stacking methods respectively. Both ensemble methods outperformed the highest single data-type network and the network trained on hand-crafted features. Grad-CAM was shown to more accurately highlight areas of disease. Conclusions: Ensemble learning increases the predictive accuracy of CNNs for classifying referable DR on OCTA datasets. Translational Relevance: Because the diagnostic accuracy of OCTA images is shown to be greater than the manually extracted features currently used in the literature, the proposed methods may be beneficial toward developing clinically valuable solutions for DR diagnoses.

AimTo prospectively monitor subclinical changes in capillary perfusion and retinal layer thickness in patients with type 2 diabetes and early diabetic retinal disease over 2 years.MethodsIn this longitudinal study we performed biannual retinal vascular imaging using optical coherence tomography angiography (RTVue) to analyse the foveal avascular zone (FAZ) area, perimeter, acircularity index (AI) and parafoveal superficial/deep vessel density (VD). Spectral-domain optical coherence tomography (Spectralis) was used to measure the thickness of nine macular layers and the peripapillary nerve fibre layer.ResultsAmong 117 eyes (58 left) of 59 patients (21 female), 105 had no diabetic retinopathy (DR), 6 mild and 6 moderate non-proliferative DR at baseline. We found DR progression in 13 eyes at year 2. The FAZ area (+0.008±0.002 mm2/year, p<0.0001), perimeter (+0.036±0.010 mm/year, p=0.006) and AI (+0.005±0.002/year, p=0.0280) increased significantly. A pronounced decrease was found in the superficial (−1.425±0.290%/year, p<0.0001) but not the deep VD. Inner neuroretinal loss was confined to the ganglion cell (−0.539±0.150 µm/year, p=0.0004) and the inner plexiform layer (−0.361±0.127 µm/year, p=0.0045). In the outer retina, we observed a statistically significant decrease in thickness in the outer plexiform, photoreceptor layer and pigment epithelium of −0.921±0.161 µm/year, −0.325±0.139 µm/year and −0.385±0.084 µm/year, respectively.ConclusionSubclinical signs of microangiopathy and neurodegeneration appear in parallel and are highly progressive even in the earliest stages of diabetic retinal disease.Trial registration number EudraCT20156000239634.

No abstract

IMPORTANCE Anti-vascular endothelial growth factor treatment is the first-line therapy in the treatment of center-involving diabetic macular edema. Data on capillary perfusion changes under repeated treatment in a possibly compromised vascular network are limited.OBJECTIVE To evaluate the association of repeated ranibizumab injections on macular perfusion in patients with diabetic macular edema. DESIGN, SETTING, AND PARTICIPANTSThis study analyzed prospectively collected data from the 12-month RESTORE core study and the 24-month open label RESTORE extension study, which assessed the efficacy and safety of ranibizumab in patients with visual impairment due to diabetic macular edema. Of 345 patients with center-involving diabetic macular edema who had enrolled in the 12-month RESTORE core study, 240 entered the 24-month RESTORE extension study. Of these, 83 (34.6%) received ranibizumab, 83 (34.6%) received ranibizumab and laser combination therapy, and 74 (30.8%) received laser monotherapy in the first year of the study; 208 completed the 24-month extension study. Fluorescence angiography images were taken from each participant twice each year graded by Vienna Reading Center on severity of capillary loss in the parafoveal area, regularity of the foveal avascular zone outline, and measurement of the size of the foveal avascular zone, following a standardized protocol. Data analysis took place from July 2014 through December 2017.MAIN OUTCOMES AND MEASURES Change in 3 fluorescence angiography perfusion parameters over the course of treatment.RESULTS Mean (SD) patient age was 62.6 (8.8) years; 124 of 208 (59.2%) were male and 197 of 208 (94.6%) were white. The number of patients with definite altered foveal avascular zone regularity at baseline was 103 of 240 patients (42.9%); another 118 patients (49.2%) had questionably altered regularity at baseline. Definitive capillary loss was found in 65 of 240 patients (27.1%) at baseline. Mean (SD) foveal avascular zone size at baseline was 0.261 (0.232) mm 2 in ranibizumab monotherapy, 0.231 (0.219) mm 2 in ranibizumab and macular laser combination therapy, and 0.201 (0.13) mm 2 in laser monotherapy. No treatment arm experienced significant increase in foveal avascular zone size at any time in the study period. At month 36, ranibizumab monotherapy resulted in a mean increase of 0.073 mm 2 (95% CI, 0.005-0.142 mm 2 ) and combination therapy resulted in a mean increase of 0.117 mm 2 (95% CI, 0.045-0.188 mm2), but no changes were statistically significant. No changes occurred in foveal avascular zone regularity in any treatment group, and no differences were found in capillary loss around the fovea in the 3 treatment groups; neither element could be correlated with visual acuity or central retinal thickness.CONCLUSIONS AND RELEVANCE Repeated ranibizumab treatment was not associated with impaired macular perfusion in our study cohort. Because our data do not suggest a harmful effect of anti-vascular endothelial growth factor therapy on capillary integrity, patients with severe m...

Adaptive optics OCT imaging revealed that MAs located in the inner nuclear layer were connected to the intermediate and/or deep capillary plexus. Intraluminal hyperreflectivity seen on AO fundus camera images originated from a strong reflection from the vessel wall and only in a third of the cases from intraluminal clots. Currently, AOOCT is the most expedient in vivo imaging method to capture morphologic details of retinal microvasculature in 3D and in the context of the surrounding retinal anatomy.

PurposeOur purpose was to compare the impact in diabetic macula edema (DME) of two intravitreal drugs (0.5 mg ranibizumab vs. 8 mg triamcinolone) on changes in retinal morphology in spectral-domain optical coherence tomography (SD OCT) images, color fundus photography (CF) and fluorescein angiography (FA) images during a 1-year follow-up.MethodsPost hoc analysis was conducted of morphologic characteristics in OCT, FA and CF images of eyes with a center involving DME that were included in a prospective double-masked randomized trial. Eligible patients were divided at random into two groups receiving either pro re nata treatment with 0.5 mg ranibizumab or 8 mg triamcinolone after a fixed loading dose. OCT and CF images were acquired at monthly visits and FA images every three months.ResultsTwenty-five eyes of 25 patients (ranibizumab: n = 10; triamcinolone: n = 15) were included in this study. Patients treated with ranibizumab showed better visual acuity results after 12 months than patients receiving triamcinolone (p = 0.015) although edema reduction was similar (p = 0.426) in both groups. The initial effect on macular edema shedding after a single ranibizumab injection could be amplified with the following two injections of the loading dose. After a single injection of triamcinolone the beneficial initial effect on the macula edema faded within 3 months. Subretinal fluid and INL cystoid spaces diminished early in the course of treatment while fluid accumulation in the ONL seemed to be more persistent in both treatment arms. In FA, the area of leakage diminished significantly in both treatment arms. After repeated injections the morphologic OCT and FA characteristics of the treatment arms converged.ConclusionsDespite the higher dosage of triamcinolone, both therapies were safe and effective for treating diabetic macular edema. Fluid accumulation in the INL and subretinal space was more responsive to therapy than fluid accumulation in the ONL. Clinicaltrials.gov: NCT00682539.

No abstract

Optical coherence tomography angiography (OCT-A) permits visualization of the changes to the retinal circulation due to diabetic retinopathy (DR), a microvascular complication of diabetes. We demonstrate accurate segmentation of the vascular morphology for the superficial capillary plexus (SCP) and deep vascular complex (DVC) using a convolutional neural network (CNN) for quantitative analysis. Methods: The main CNN training dataset consisted of retinal OCT-A with a 6 × 6-mm field of view (FOV), acquired using a Zeiss PlexElite. Multiple-volume acquisition and averaging enhanced the vasculature contrast used for constructing the ground truth for neural network training. We used transfer learning from a CNN trained on smaller FOVs of the SCP acquired using different OCT instruments. Quantitative analysis of perfusion was performed on the resulting automated vasculature segmentations in representative patients with DR. Results: The automated segmentations of the OCT-A images maintained the distinct morphologies of the SCP and DVC. The network segmented the SCP with an accuracy and Dice index of 0.8599 and 0.8618, respectively, and 0.7986 and 0.8139, respectively, for the DVC. The inter-rater comparisons for the SCP had an accuracy and Dice index of 0.8300 and 0.6700, respectively, and 0.6874 and 0.7416, respectively, for the DVC. Conclusions: Transfer learning reduces the amount of manually annotated images required while producing high-quality automatic segmentations of the SCP and DVC that exceed inter-rater comparisons. The resulting intercapillary area quantification provides a tool for in-depth clinical analysis of retinal perfusion. Translational Relevance: Accurate retinal microvasculature segmentation with the CNN results in improved perfusion analysis in diabetic retinopathy.