Modern Approach to Diabetic Retinopathy Diagnostics.

This article reviews innovative diagnostic approaches for diabetic retinopathy as the prevalence of diabetes mellitus and its complications continue to escalate. Novel techniques focus on early disease detection. Technological innovations, such as teleophthalmology, smartphone-based photography, artificial intelligence with deep learning, or widefield photography, can enhance diagnostic accuracy and accelerate the treatment. The review highlights teleophthalmology and handheld photography as promising solutions for remote eye care. These methods revolutionize diabetic retinopathy screening, offering cost-effective and accessible solutions. However, the use of these techniques may be limited by insurance coverage in certain world regions. Ultra-widefield photography offers a comprehensive view of up to 80.0% of the retina in a single image, compared to the 34.0% coverage of the traditional seven-field imaging protocol. It allows retinal imaging without pupil dilation, especially for individuals with compromised mydriasis. However, they also have drawbacks, including high costs, artifacts from eyelashes, eyelid margins, and peripheral distortion. Recent advances in artificial intelligence and machine learning, particularly through convolutional neural networks, are revolutionizing diabetic retinopathy diagnostics, enhancing screening efficiency and accuracy. FDA-approved Artificial Intelligence-powered devices such as LumineticsCore™, EyeArt, and AEYE Diagnostic Screening demonstrate high sensitivity and specificity in diabetic retinopathy detection. While Artificial Intelligence offers the potential to improve patient outcomes and reduce treatment costs, challenges such as dataset biases, high initial costs, and cybersecurity risks must be considered to ensure safety and efficiency. Nanotechnology advancements further enhance diagnosis, offering highly branched polyethyleneimine particles with fluorescein sodium (PEI-NHAc-FS) for better fluorescein angiography or vanadium oxide-based metabolic fingerprinting for early detection.

Angiographic Characteristics in Mild Familial Exudative Vitreoretinopathy with Genetically Confirmed Autosomal Dominant Inheritance.

PURPOSE: To determine the ultra-widefield fluorescein angiographic (UWFA) characteristics of patients with mild familial exudative vitreoretinopathy (FEVR) who had been confirmed to have pathogenic variants of the autosomal dominant (AD) genes of FEVR. DESIGN: Single center, observational case series. SUBJECTS AND CONTROLS: Thirty-seven patients with mild FEVR from 27 families who had pathogenic variants of the Norrin/ß-catenin genes were studied. The controls consisted of 32 family members who had been confirmed not to carry the pathogenic variants or had heterozygous variants of the autosomal recessive inheritance gene. METHODS: Sixty-four UWFA images from the patients were compared with 60 UWFA images from the controls. The relative length of the temporal retina to the peripheral avascular retina was determined. The cut-off ratio of the relative lengths for a clinically significant avascular retina (csAR) associated with AD-FEVR was determined using the receiver operating characteristic (ROC) curves. MAIN OUTCOME MEASURES: The presence or absence of 6 peripheral vascular changes (csAR, V-shaped vascular notch, brushy vascular ends, vascular stain, loop vessels or anastomosis, and capillary telangiectasia) were compared between the patients and the controls. RESULTS: The csAR was set at > 12% of the length from the ora serrata to the optic disc. The patients with AD-FEVR had more frequent retinal changes than the controls for the V-shaped vascular notch (69% vs. 2%; P < 0.001), brushy vascular ends (78% vs. 3%; P < 0.001), csAR (83% vs. 22%; P < 0.001), and vascular stain (70% vs. 35%, P < 0.001). Loop vessels and/or anastomosis of peripheral vessels were found significantly less frequently in the patients than in the controls (39% vs. 73%; P < 0.001). No significant difference was found for capillary telangiectasia between the 2 groups. The combination of the V-shaped vascular notches, brushy vascular ends, and csAR had a sensitivity of 82.8% and specificity of 98.3%, with the highest ROC curve of 0.9. CONCLUSIONS: The combination of V-shaped vascular notch, brushy vascular ends, and csAR can be used as a biomarker for patients with AD-FEVR who have pathogenic variants of the Norrin/ß-catenin genes. These findings will allow more accurate segregation analysis in FEVR families and allow better genetic counseling. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Quantitative Biomarkers of Diabetic Retinopathy Using Ultra-Widefield Fluorescein Angiography.

Introduction: Diabetic retinopathy (DR) is a leading cause of blindness. Retinal imaging is an important tool to monitor the progression of DR. While seven-standard retinal fields are the traditional method for evaluating DR, ultra-widefield (UWF) imaging allows for improved visualization of peripheral areas of nonperfusion (NP) and neovascularization (NV), which could be used as biomarkers to monitor and predict progression of DR. Methods: A retrospective, cross-sectional study was conducted on 651 eyes from 363 patients diagnosed with type 1 or type 2 diabetes who received UWF-FA over 10 years. Fluorescein Angiography (FA) images were segmented, and surface areas of NP and NV were analyzed using multivariate regression to determine if biomarkers of DR and DR severity are associated with increasing areas of NP and NV. Results: Each additional year with a diagnosis of DR was associated with a 10.75 mm2 increase in the total NP (95% CI, 1.94-19.56; P = 0.02) and 7.87 mm2 increase in NP far-periphery (95% CI, 1.62-14.13; P = 0.01). A one-unit change in severity as defined by the Early Treatment of Diabetic Retinopathy Study (ETDRS) classification was associated with a 25.75 mm2 increase in total NP (95% CI, 11.16-40.33; P = 0.001), a 13.15 mm2 increase in mid-periphery NP (95% CI, 6.93-19.38; P < 0.0001), and a 12.29 mm2 increase in far-periphery NP (95% CI, 3.62-20.97; P = 0.01). Discussion: Biomarkers identified through UWF imaging such as total and regional areas of NP can be used to monitor and predict the progression of DR. This may provide a quantitative method for prognostication in patients with DR.

Automatic Detection of 30 Fundus Diseases Using Ultra-Widefield Fluorescein Angiography with Deep Experts Aggregation.

INTRODUCTION: Inaccurate, untimely diagnoses of fundus diseases leads to vision-threatening complications and even blindness. We built a deep learning platform (DLP) for automatic detection of 30 fundus diseases using ultra-widefield fluorescein angiography (UWFFA) with deep experts aggregation. METHODS: This retrospective and cross-sectional database study included a total of 61,609 UWFFA images dating from 2016 to 2021, involving more than 3364 subjects in multiple centers across China. All subjects were divided into 30 different groups. The state-of-the-art convolutional neural network architecture, ConvNeXt, was chosen as the backbone to train and test the receiver operating characteristic curve (ROC) of the proposed system on test data and external test date. We compared the classification performance of the proposed system with that of ophthalmologists, including two retinal specialists. RESULTS: We built a DLP to analyze UWFFA, which can detect up to 30 fundus diseases, with a frequency-weighted average area under the receiver operating characteristic curve (AUC) of 0.940 in the primary test dataset and 0.954 in the external multi-hospital test dataset. The tool shows comparable accuracy with retina specialists in diagnosis and evaluation. CONCLUSIONS: This is the first study on a large-scale UWFFA dataset for multi-retina disease classification. We believe that our UWFFA DLP advances the diagnosis by artificial intelligence (AI) in various retinal diseases and would contribute to labor-saving and precision medicine especially in remote areas.

Relationship between ischemic index, leakage index, and macular edema in branch retinal vein occlusion.

PURPOSE: To investigate the combined association of the ischemic index and leakage index with macular edema on ultra-widefield fluorescein angiography (UWFFA) in patients with branch retinal vein occlusion (BRVO). METHODS: Retrospective image analysis study. The leakage index and ischemic index were calculated using Fiji after aligning early and late UWFFA images. Differences in the ischemic index, leakage index, and central macular thickness (CMT) between ischemic and non-ischemic BRVO were compared. Moreover, the association between the ischemic index, leakage index, and macular edema was analyzed. RESULTS: Eighty-three patients with BRVO were enrolled, including 53 non-ischemic BRVO and 30 ischemic BRVO patients. No significant differences were observed in leakage index and CMT between ischemic BRVO and non-ischemic BRVO (all P > 0.05). In all included patients, CMT correlated with the panretina and all subregion leakage indexes (all P < 0.01), but not with the ischemic index (all P > 0.05). In the ischemic BRVO group, CMT showed a correlation with the leakage index in several regions, but not with the ischemic index. After adjusting for the ischemic index and other clinical features, CMT remained significantly correlated with the leakage index in all regions. CONCLUSION: The leakage index may be a more effective biomarker for monitoring BRVO-associated macular edema compared to the ischemic index. Further follow-up studies are warranted to validate these findings.

Distribution of leakage index using ultra-widefield fluorescein angiography in patients with non-ischemic branch retinal vein occlusion and its association with macular edema.

BACKGROUND: To investigate the distribution of leakage index in patients with non-ischemic branch retinal vein occlusion (BRVO) and its correlation with the severity of macular edema. METHODS: Retrospective observational study. Forty-five eyes of 45 patients with BRVO were included. Late ultra-widefield fluorescein angiography images of the affected eyes were processed and analyzed for their leakage index using Fiji software. The visible panretinal area was further divided into the peri­macular area (PMA), near-peripheral area (NPA), midperipheral area (MPA), and far-peripheral area (FPA). The relationship between the leakage index and central retinal thickness (CMT) was analyzed for the panretina and each subregion. RESULTS: The median (interquartile range) leakage indexes of the panretina, PMA, NPA, MPA, and FPA were 5.532% (7.667%), 23.127% (26.073%), 8.303% (16.807%), 1.588% (6.204%), and 0.408% (2.215%), respectively, with a mean CMT of 552.800 ± 183.335 µm. The CMT was positively correlated with the leakage index in the panretina, PMA, NPA, MPA and FPA (r = 0.468, 0.426, 0.463, 0.447, 0.320, respectively; all p < 0.05). CONCLUSIONS: The leakage index in non-ischemic BRVO patients is associated with macular edema severity. The leakage index has the potential to be a useful indicator for monitoring and guiding treatment of macular edema in BRVO patients.

Retinal Ischaemia in Diabetic Retinopathy: Understanding and Overcoming a Therapeutic Challenge.

BACKGROUND: Retinal ischaemia is present to a greater or lesser extent in all eyes with diabetic retinopathy (DR). Nonetheless, our understanding of its pathogenic mechanisms, risk factors, as well as other characteristics of retinal ischaemia in DR is very limited. To date, there is no treatment to revascularise ischaemic retina. METHODS: Review of the literature highlighting the current knowledge on the topic of retinal ischaemia in DR, important observations made, and underlying gaps for which research is needed. RESULTS: A very scarce number of clinical studies, mostly cross-sectional, have evaluated specifically retinal ischaemia in DR. Interindividual variability on its natural course and consequences, including the development of its major complications, namely diabetic macular ischaemia and proliferative diabetic retinopathy, have not been investigated. The in situ, surrounding, and distance effect of retinal ischaemia on retinal function and structure and its change over time remains also to be elucidated. Treatments to prevent the development of retinal ischaemia and, importantly, to achieve retinal reperfusion once capillary drop out has ensued, are very much needed and remain to be developed. CONCLUSION: Research into retinal ischaemia in diabetes should be a priority to save sight.

Research progress on the application of retinal vascular bed area in diabetic retinopathy / 国际眼科杂志(Guoji Yanke Zazhi)

Retinal vascular bed area(RVBA)is the total area of retinal vasculature segmented by ultra-widefield fluorescein angiography(UWFA)images, and is an objective absolute value in square millimeter. RVBA is mainly affected by the diameter and length of retinal vessels, and whether RVBA increases or decreases depends on the “competition” between ischemia and angiogenesis, indicating subtle changes in retinal vascular morphology. As a new indicator for the study of retinal vascular diseases, RVBA may have higher stability and accuracy than the ischemia index(ISI)and non-perfusion area(NPA). RVBA is currently mainly used to evaluate the progression and prognosis of diabetic retinopathy(DR). It was found that retinal total RVBA in DR eyes was greater than the normal eyes and it decreased in DR eyes after anti-vascular endothelial growth factor(VEGF)treatment. These findings provide favorable support for the study of microvascular lesions in DR. In this article, the application of RVBA in DR was reviewed to provide a reference for the clinical study of RVBA in other retinal vascular diseases such as retinal vein occlusion(RVO).

WF SS-OCTA for detecting diabetic retinopathy and evaluating the effect of photocoagulation on posterior vitreous detachment.

Purpose: This study aimed to assess the clinical usefulness of widefield swept source optical coherence tomography angiography (WF SS-OCTA) for detecting microvasculature lesions in diabetic retinopathy (DR) by comparing it with ultra-widefield fluorescein angiography (UWFFA) and to investigate the effect of panretinal photocoagulation (PRP) on posterior vitreous detachment (PVD) status. Methods: Patients with severe non-proliferative DR (NPDR) or proliferative DR (PDR) who were initially treated with PRP were enrolled. They underwent WF SS-OCTA with a 12×12-mm scan pattern of five visual fixations at baseline and at least a 3-month follow-up after PRP treatment. Patients with no contraindications underwent imaging with UWFFA within a week. Images were evaluated using two methods for the areas of the visible field of view (FOV), non-perfusion area (NPA), presence of neovascularization of the disc (NVD), neovascularization elsewhere (NVE), and PVD status. Results: In total, 44 eyes of 28 patients with DR that were initially treated with PRP were analyzed. The FOV of the UWFFA was significantly wider than that of the WF SS-OCTA. The quantitative measurement of the NPAs was consistent between the two methods. NPAs more than 5DA outside the panoramic OCTA imaging area were detected in 1 eye with NPDR (8.3%) and in 10 eyes with PDR (47.8%). WF SS-OCTA had high detection rates for NVDs and NVEs, with a low rate of false positives. After PRP treatment, no eyes indicated progression in the PVD stages around the macula, optical disc, or NVEs at the short follow-up. Conclusion: WF SS-OCTA is clinically useful for evaluating NPAs and neovascularization in DR. PRP treatment does not induce PVD development in the short term.

Quantitative analysis of ultra-widefield fluorescein angiography in uveitis associated with sarcoidosis.

Purpose: To quantitatively assess the angiographic features of uveitis associated with sarcoidosis on ultra-widefield fluorescein angiography (UWFA) and determine their correlations with clinical features. Design: A retrospective cohort study. Methods: Sixty-four eyes (64 patients) with sarcoidosis uveitis were included. On UWFA, presence of vasculitis, macular leakage, and optic disc leakage were assessed and features including peripheral ischemic area, vascular leakage area, and punched out lesions were quantitatively analyzed using FIJI (ImageJ2) and correlated with clinical features. Results: The mean peripheral ischemic area and leakage area were 0.0419 ± 0.113% and 0.0333 ± 0.0287% of the total retinal area, respectively. Macular and optic disc leakage were present in 18.8% and 59.4% of eyes, respectively. The average number of punched out lesions was 10.02 ± 21.95. Those changes were most abundant in the inferotemporal area. The presence of disc leakage correlated with all the other UWFA parameters (all r ≥ 0.260; all P ≤ 0.038). The leakage area correlated with vitreous cells, baseline and 6-month logMAR visual acuity, steroid dose and duration, erythrocyte sedimentation rate, and C-reactive protein (r = 0.472, 0.288, 0.321, 0.374, 0.250, 0.251, and 0.277; all P ≤ 0.46). Conclusions: This study quantitatively analyzed UWFA data in sarcoidosis uveitis. Angiographic changes were most frequent in the inferotemporal area. UWFA parameters correlated with one another and clinical variables. These quantitative imaging results warrant a subjective analysis of sarcoidosis uveitis.

Use of Ultra-Widefield Fluorescein Angiography to Guide the Treatment to Idiopathic Retinal Vasculitis, Aneurysms, and Neuroretinitis-Case Report and Literature Review.

PURPOSE: To review the clinical features, diagnosis, and treatment of idiopathic retinal vasculitis, aneurysms, and neuroretinitis (IRVAN) and to report a case with the use of ultra-widefield fluorescein angiography (UWFA) for confirming the precise staging of IRVAN and aid in early treatment. The patient improved after being treated with intravitreal aflibercept injection. RESULTS: A 26-year-old female complained of progressive blurred vision OD for one week. Her BCVA was 0.6 OD and 1.0 OS. Fundus examination showed vitritis, retinal hemorrhage, and vasculitis over bilateral eyes. Fluorescein angiography (FA) with a 55 degree of view revealed aneurysmal dilations of the peripapillary arteriole, peripapillary focal leakage, venous leakage, and capillary nonperfusion area. Stage 2 IRVAN was impressed OU. Oral prednisolone was administered. After four months, she experienced decreased visual acuity OS. Optical coherence tomography (OCT) revealed subretinal and intraretinal fluid with hyperreflective material. One posterior subtenon triamcinolone and one intravitreal aflibercept injection were performed OS, and macular edema subsided. A 105-degree ultra-widefield fluorescein angiography (UWFA) showed multiple peripheral background hypofluorescence areas corresponding to capillary nonperfusion. Retinal neovascularization (NV) was found OS, which had not been revealed by the previous 55-degree FA. Stage 3 IRVAN was made OS and panretinal laser photocoagulation (PRP) was performed. Oral prednisone and cyclosporine were prescribed. Her vision improved to 1.0 OU. CONCLUSION: UWFA provides visualization of peripheral retinal pathology and for precise staging. It also had direct implications in the follow-up and treatment strategy.

Computational Imaging Biomarker Correlation with Intraocular Cytokine Expression in Diabetic Macular Edema: Radiomics Insights from the IMAGINE Study.

Purpose: Various pathways and cytokines are implicated in pathogenesis of diabetic macular edema (DME). Computational imaging biomarkers (CIBs) of vessel tortuosity from ultra-widefield fluorescein angiography (UWFA) and texture patterns from OCT images have been associated with anti-vascular endothelial growth factor (VEGF) therapy treatment response in DME. This analysis was a radiogenomic assessment of the association between underlying cytokines, UWFA, and OCT-based DME CIBs. Design: Biclustering analysis based on UWFA and OCT CIBs to identify a common imaging phenotype across patients with subsequent assessment of underlying cytokine signatures and treatment response attributes. Participants: The IMAGINE DME study was a post hoc study of cytokine expressions that included 24 eyes with sufficient baseline aqueous humor samples and an in-depth assessment of the imaging studies obtained during the phase I/II DmeAntiVEgf study (DAVE) that measured different cytokine expressions. Methods: A total of 151 graph or morphologic features quantifying leakage shape, size, density, interobject distance, and architecture of leakage spots and 5 vessel tortuosity features were extracted from the baseline UWFA scans, and 494 texture-based radiomics features were extracted from each of the fluid and retinal tissue compartments of OCT images. Biclustering enables simultaneous clustering of patients and features and was used to aggregate patients in terms of their commonality of phenotypes (based on similar imaging attributes) and to identify commonality in terms of cytokine expression and treatment response to anti-VEGF therapy. Main Outcome Measures: Identification of eyes with similar imaging phenotypes to evaluate commonalities of patterns and underlying cytokine expression. Results: Strong correlations between VEGF and 7 UWFA leakage morphologic features (Pearson correlation coefficient [PCC], 0.45-0.51; P < 0.05), 1 vascular tortuosity-based UWFA feature (PCC, 0.45; P = 0.00016), and 2 OCT-derived intraretinal fluid texture features (PCC, 0.58-0.63; P < 0.05) were identified. Strong correlation between intraretinal fluid features and other cytokines (PCC, 0.41-0.59; P < 0.05) were also observed. Conclusions: This study identified groups of eyes with similar imaging phenotypes as defined by UWFA and OCT CIBs that demonstrated similar treatment response patterns and cytokine expression, including a strong association between VEGF with UWFA-derived leakage morphologic and vessel tortuosity features.

[Biomarkers in the treatment of retinal vein occlusion]. / Biomarker in der Therapie venöser retinaler Gefäßverschlüsse.

BACKGROUND: Retinal vein occlusion, subdivided into central retinal and branch retinal vein occlusion, is one of the most frequent vascular diseases of the retina. Biomarkers of optical coherence tomography (OCT), OCT-angiography and (ultra-widefield) fluorescein angiography are of exceptional importance in the initial diagnosis and also in the treatment of complications associated with retinal vascular occlusion, particularly macular edema. METHODS: A systematic literature review was carried out in PubMed with the keywords central retinal vein occlusion, branch retinal vein occlusion, biomarker, OCT, OCT angiography, ultra-widefield fluorescein angiography with prioritization of the most important aspects. RESULTS: Relevant biomarkers in OCT include central retinal thickness (CRT), macular fluid, the integrity of the photoreceptor bands (external limiting membrane and ellipsoid zone), disorganization of retinal inner layers (DRIL), hyperreflective foci, choroidal thickness and signs of ischemia, such as a prominent middle limiting membrane (p-MLM), paracentral acute middle maculopathy (PAMM) as well as hyperreflectivity of inner retinal layers (HIRL). The importance of OCT-angiography lies particularly in the assessment of microvascular alterations, especially vessel density in the deep retinal vascular plexus, the foveal avascular zone and of areas with no capillary perfusion. Biomarkers of ultra-widefield angiography, such as peripheral ischemia (ischemic index) and neovascularízation are essential with respect to treatment decisions for retinal laser. CONCLUSION: A multitude of simple and complex biomarkers currently enable an effective individualized evaluation of treatment and prognosis in retinal vein occlusion. A shift from invasive to noninvasive biomarkers can be observed.

Optical Coherence Tomography Angiography in Central Retinal Vein Occlusion: Macular Changes and Their Correlation with Peripheral Nonperfusion at Ultra-Widefield Fluorescein Angiography.

INTRODUCTION: The aim of this study was to investigate the correlation between ischemic index (ISI) measured on ultra-widefield (UWF) fluorescein angiography (FA) images and macular parameters obtained by optical coherence tomography angiography (OCT-A) in eyes affected by central retinal vein occlusion (CRVO). METHODS: Retrospective study of data from 12 eyes affected by treatment-naïve CRVO. All patients underwent a comprehensive ocular examination including structural OCT, OCT-A, and UWF FA. Variables analyzed included best corrected visual acuity (BCVA) measured with the ETDRS chart; foveal avascular zone (FAZ) area at full-thickness OCT-A angiogram; perfusion density (PD) in the superficial (SCP) and deep capillary plexus (DCP); ISI; and central macular thickness (CMT). RESULTS: ISI showed a significant positive correlation with FAZ area (r = 0.63, p = 0.019) and a significant negative correlation with PD in the SCP (r = -0.62, p = 0.022), PD in the DCP (r = -0.66, p = 0.011), and BCVA (r = -0.75, p = 0.002). FAZ area also negatively correlated to PD in the SCP (r = -0.75, p = 0.002) and DCP (r = -0.64, p = 0.016). BCVA positively correlated to PD in the SCP (r = 0.67, p = 0.009) and DCP (r = 0.68, p = 0.008), while a negative correlation was found with FAZ area (r = -0.65, p = 0.013) and CMT (r = -0.70, p = 0.006). DISCUSSION/CONCLUSION: OCT-A macular parameters (namely, FAZ area and PD of SCP and DCP) significantly correlated with ISI, a quantitative way to assess peripheral retinal nonperfusion on UWF FA. Macular OCT-A analysis may help in assessing the need for additional UWF FA testing in eyes affected by CRVO.

Ischemic index and distribution of retinal capillary non-perfusion in neovascular glaucoma.

INTRODUCTION: Neovascular Glaucoma (NVG) is a condition normally caused by hypoxic posterior ocular disease, which produces angiogenic factors such as vascular endothelial growth factor (VEGF) that stimulate new vessel proliferation of the anterior segment and angle, eventually leading to angle closure, reduced outflow of aqueous humor and increased intraocular pressure. Without treatment elevated intraocular pressure can rapidly progress to loss of vision. Treatment includes addressing the intraocular pressure and reducing the ischemic drive with panretinal photocoagulation (PRP) of the ischemic retina. Recent imaging advancements allow for ultra-widefield fluorescein angiography (UWFA) which expand the amount of peripheral retina that can be evaluated for non-perfusion. Here we aim to study patterns of non-perfusion in NVG using a group of PRP naïve patients with recent onset NVG. METHODS: This study is a retrospective single-center cross-sectional study of patients seen at LAC + USC Medical Center from January 2015 to April 2020 with new onset NVG, without PRP and with UWFA completed. The percentage of ischemic index of the retina was calculated from the UWFA and evaluated in three distinct zones centered on the fovea: the posterior pole, the mid periphery, and far periphery. To increase sample size, a confirmatory group was included, with PRP allowed prior to UWFA but not before diagnosis. In addition, the time between diagnosis and UWFA was increased to 6 months. RESULTS: A total of 11 eyes met inclusion criteria for the primary group. Ischemic index was found to be 91% in the far periphery, 77% in the mid periphery, and 42% at the posterior pole. The total average ischemic index was 76%. There was a statistically significant difference between the far periphery and posterior pole and mid periphery and posterior pole. A total of 24 eyes met criteria for the confirmatory group. Ischemic index for the confirmatory group was found to be 93% in the far periphery, 75% in the mid periphery, and 35% at the posterior pole. There was a statistically significant difference between the far periphery, posterior pole and mid-periphery. CONCLUSION: This knowledge can be used to further guide treatment and understand risk for NVG.

Evaluating the utility of deep learning for predicting therapeutic response in diabetic eye disease.

Purpose: Deep learning (DL) is a technique explored within ophthalmology that requires large datasets to distinguish feature representations with high diagnostic performance. There is a need for developing DL approaches to predict therapeutic response, but completed clinical trial datasets are limited in size. Predicting treatment response is more complex than disease diagnosis, where hallmarks of treatment response are subtle. This study seeks to understand the utility of DL for clinical problems in ophthalmology such as predicting treatment response and where large sample sizes for model training are not available. Materials and Methods: Four DL architectures were trained using cross-validated transfer learning to classify ultra-widefield angiograms (UWFA) and fluid-compartmentalized optical coherence tomography (OCT) images from a completed clinical trial (PERMEATE) dataset (n=29) as tolerating or requiring extended interval Anti-VEGF dosing. UWFA images (n=217) from the Anti-VEGF study were divided into five increasingly larger subsets to evaluate the influence of dataset size on performance. Class activation maps (CAMs) were generated to identify regions of model attention. Results: The best performing DL model had a mean AUC of 0.507 ± 0.042 on UWFA images, and highest observed AUC of 0.503 for fluid-compartmentalized OCT images. DL had a best performing AUC of 0.634 when dataset size was incrementally increased. Resulting CAMs show inconsistent regions of interest. Conclusions: This study demonstrated the limitations of DL for predicting therapeutic response when large datasets were not available for model training. Our findings suggest the need for hand-crafted approaches for complex and data scarce prediction problems in ophthalmology.

Ultra-Widefield Fluorescein Angiography to Monitor Therapeutic Response to Adalimumab in Behcet's Uveitis.

PURPOSE: To investigate the role of ultra-widefield fluorescein angiography (UWFA) for monitoring therapeutic response to adalimumab in patients with Behcet's uveitis. METHODS: Patients with Behcet's uveitis treated with adalimumab for ≥30 weeks were included. Intraocular inflammation, best-corrected visual acuity, systemic medications, and UWFA scores were evaluated. RESULTS: Thirty-eight eyes of 20 patients were included. Significant decreases in grading of anterior chamber cells and vitreous haze were observed at 6, 14, and 30 weeks after adalimumab administration (p < .001 for all). UWFA scores on vascular and capillary leakage were decreased at week 6 and further improved at weeks 14 and 30. Moreover, UWFA score further decreased at 14 and 30 weeks, even after manifest inflammation became quiescent at 6 weeks. (p = .004 and 0.001, respectively). CONCLUSION: UWFA scores significantly improved in Behcet's uveitis patients treated with adalimumab, and further improvement of UWFA scores was found in patients with a clinically quiescent inflammatory state.

Quantitative analysis of retinal vasculature in normal eyes using ultra-widefield fluorescein angiography.

AIM: To quantify the area and density of retinal vascularity by ultra-widefield fluorescein angiography (UWFA). METHODS: In a retrospective study, UWFA images were obtained using an ultra-widefield imaging device in 42 normal eyes of 42 patients. Central and peripheral steered images were used to define the edge of retinal vasculature by a certified grader. The length from the center of the optic disc to the edge of retinal vascularity (RVL) in each quadrant and the total retinal vascular perfusion area (RVPA) were determined by the grader using OptosAdvance software. The density of retinal vascularity (RVD) was quantified in different zones of central-steered images using Image J software. RESULTS: Among 42 healthy eyes, the values for mean RVL in each quadrant were 19.007±0.781 mm (superior), 18.467±0.869 mm (inferior), 17.738±0.622 mm (nasal) and 24.241±1.336 mm (temporal). The mean RVPA was 1140.117±73.825 mm2. The mean RVD of the total retina was 4.850%±0.638%. RVD varied significantly between different retina zones (P<0.001), and significant differences existed in the RVD values for total retinal area in patients over 50 years old compared to those under 50 years old (P=0.033). No gender difference was found. CONCLUSION: The UWFA device can be a promising tool for analyzing the overall retinal vasculature and may provide a better understanding of retinal vascular morphology in normal eyes. Aging may be related to lower RVD.

The 2-Year Leakage Index and Quantitative Microaneurysm Results of the RECOVERY Study: Quantitative Ultra-Widefield Findings in Proliferative Diabetic Retinopathy Treated with Intravitreal Aflibercept.

Eyes with proliferative diabetic retinopathy (PDR) have been shown to improve in the leakage index and microaneurysm (MA) count after intravitreal aflibercept (IAI) treatment. The authors investigated these changes via automatic segmentation on ultra-widefield fluorescein angiography (UWFA). Forty subjects with PDR were randomized to receive either 2 mg IAI every 4 weeks (Arm 1) or every 12 weeks (Arm 2) through Year 1. After Year 1, Arm 1 switched to quarterly IAI and Arm 2 to monthly IAI through Year 2. By Year 2, the Arm 1 leakage index decreased by 43% from Baseline (p = 0.03) but increased by 59% from Year 1 (p = 0.04). Arm 2 decreased by 61% from Baseline (p = 0.008) and by 31% from Year 1 (p = 0.12). Both cohorts exhibited a significant decline in MAs from Baseline to Year 2 (871 to 410; p < 0.001; 776 to 207; p < 0.001, respectively). Subjects with an improved leakage and MA count showed a more significant improvement in the Diabetic Retinopathy Severity Scale (DRSS) score. Moreover, central subfield thickness (CST) was positively associated with changes in the leakage index. In conclusion, the leakage index and MA counts significantly improved from Baseline following IAI treatment, and monthly injections provided a more rapid and sustained reduction in these parameters compared with quarterly injections.