Corneal Microaneurysm-A Vascular Feature of Conjunctival Squamous Intraepithelial Neoplasia.

PURPOSE: The diagnosis of conjunctival squamous intraepithelial neoplasia (CSIN) can be difficult because of the heterogeneous appearance. Despite established risk factors and diagnostic support by high-resolution optical coherence tomography (hrOCT) and indocyanine green angiography (ICGA), the only reliable diagnostic method is a histological work-up. This case report is the first to describe corneal microaneurysms in CSIN as a vascular feature for conjunctival tumor angiogenesis. METHODS: An 84-year-old male patient was referred with a suspected diagnosis of pterygium. Biomicroscopic examination revealed a whitish epithelial lesion of conjunctival origin with centripetal corneal growth and extension over 5 limbal hours. Intralesional vascularization showed highly altered morphology with aneurysmal changes. After imaging with hrOCT and ICGA, excision was performed in a "no-touch double-freeze and thaw" technique, followed by histological and immunohistochemical work-up. RESULTS: hrOCT showed an epithelial, hyperreflective lesion with a maximum thickness of 272 µm and sharp central border. ICGA confirmed active perfusion and partial thrombosis of the aneurysmal terminal vascular buds dilated to 405 µm with early dye leakage within the first minute. Histological examination confirmed the clinical diagnosis of CSIN with focal high-grade dysplasia. Postoperatively, there was no recurrence during the observation period of 5 months. CONCLUSIONS: Intralesional terminal microaneurysms are a feature of tumor angiogenesis in CSIN. The relevance and frequency of this potential new risk factor for malignancy should be investigated in further studies.

Resilient back-propagation machine learning-based classification on fundus images for retinal microaneurysm detection.

BACKGROUND: The timely diagnosis of medical conditions, particularly diabetic retinopathy, relies on the identification of retinal microaneurysms. However, the commonly used retinography method poses a challenge due to the diminutive dimensions and limited differentiation of microaneurysms in images. PROBLEM STATEMENT: Automated identification of microaneurysms becomes crucial, necessitating the use of comprehensive ad-hoc processing techniques. Although fluorescein angiography enhances detectability, its invasiveness limits its suitability for routine preventative screening. OBJECTIVE: This study proposes a novel approach for detecting retinal microaneurysms using a fundus scan, leveraging circular reference-based shape features (CR-SF) and radial gradient-based texture features (RG-TF). METHODOLOGY: The proposed technique involves extracting CR-SF and RG-TF for each candidate microaneurysm, employing a robust back-propagation machine learning method for training. During testing, extracted features from test images are compared with training features to categorize microaneurysm presence. RESULTS: The experimental assessment utilized four datasets (MESSIDOR, Diaretdb1, e-ophtha-MA, and ROC), employing various measures. The proposed approach demonstrated high accuracy (98.01%), sensitivity (98.74%), specificity (97.12%), and area under the curve (91.72%). CONCLUSION: The presented approach showcases a successful method for detecting retinal microaneurysms using a fundus scan, providing promising accuracy and sensitivity. This non-invasive technique holds potential for effective screening in diabetic retinopathy and other related medical conditions.

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

PURPOSE: 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. DESIGN: Retrospective, cross-sectional study. PARTICIPANTS: 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. METHODS: 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. MAIN OUTCOME MEASURES: 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. RESULTS: 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. CONCLUSIONS: OCT-identified MAs with colocalized flow on OCTA are more likely to be associated with DME than those without flow. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Turnover of Microaneurysms After Intravitreal Injections of Faricimab for Diabetic Macular Edema.

Purpose: Microaneurysm (MA) plays an important role in the pathogenesis of diabetic macular edema (DME) progression and response to anti-vascular endothelial growth factor (VEGF) therapy. This study aimed to investigate the effect of faricimab, a bispecific antibody against angiopoietin-2 and VEGF, on the number of MAs and their turnover in the treatment of DME. Methods: We included that patients with DME who underwent three monthly injections of faricimab in one eye, with the other eye as control. We examined central retinal thickness (CRT) based on optical coherence tomography (OCT) and best-corrected visual acuity. Turnover, including loss and newly formed MAs, and the total number of MAs were counted based on merged images of the OCT map and fluorescein angiography. Results: We enrolled 28 patients with DME. After 3 monthly injections of faricimab, CRT significantly improved, 66.0 ± 16.2% of MAs disappeared, and 6.71 ± 5.6% of new MAs were generated, resulting in total reduction to 40.7 ± 15.2%. In the treated eyes, MA disappearance (P < 0.0001) and turnover (P = 0.007) were significantly greater, and new formation was smaller (P < 0.0001) than in non-treated eyes. The size of the retained MAs decreased after treatment. Microaneurysm turnover was not significantly different between areas with and without edema before treatment. Conclusions: In the process of improving edema in DME with faricimab, MAs shrink and disappear, and formation of MAs are inhibited, resulting in decreased total number of MAs. Intravitreal administration of faricimab suppresses vascular permeability and improves vascular structure.

Optical coherence tomography angiography analysis of microvascular abnormalities and vessel density in treatment-naïve eyes with diabetic macular edema.

BACKGROUND: The aim of this study was to evaluate the structural retinal vascular integrity using optical coherence tomography angiography (OCTA) in treatment-naïve eyes with diabetic macular edema (DME) and to compare it with findings in diabetic eyes without DME. METHODS: In this prospective study, 70 eyes with diabetic retinopathy were included (37 eyes with DME and 33 eyes without DME). The medical records, including swept-source optical coherence tomography and 9 × 9 mm swept-source OCTA images were reviewed and compared between DME and non-DME groups. Microaneurysms, intraretinal microvascular abnormalities (IRMA), areas of capillary non perfusion, foveal avascular zone (FAZ), and capillary vascular density (CVD) were analyzed in the superficial capillary plexus (SCP) and the deep capillary plexus (DCP). RESULTS: Compared to the non-DME eyes, DME eyes had more microaneurysms in the SCP and the DCP (p = 0,039 and p = 0,024 respectively), more IRMA in the SCP (p = 0,005), larger areas of capillary non perfusion in the SCP and the DCP (p = 0,026 and p = 0,02 respectively) and larger FAZ in both plexuses (p = 0,048 in the SCP and p = 0,012 in the DCP). The CVD in the DCP was lower in DME eyes compared to non-DME eyes (p = 0,007). The severity of DME was significantly correlated to the number of microaneurysms and to the FAZ surface. Central macular thickness was significantly correlated with the number of microaneurysms in the DCP, the surface of capillary non perfusion areas and the FAZ area in both plexuses. CONCLUSIONS: OCTA with a 9 × 9 mm field of view showed that the retinal vascular integrity regarding the number of microaneurysms, the number of IRMA, the surface of capillary non perfusion areas, the FAZ area and the CVD, was significantly more impaired in DME eyes compared to diabetic eyes without DME. The DCP seemed to be more affected in diabetic eyes with and without DME than the SCP.

Morphology and fluorescein leakage in diabetic retinal microaneurysms: a study using multiple en face OCT angiography image averaging.

PURPOSE: To investigate the relevance of microaneurysm morphology in optical coherence tomography angiography (OCTA) image averaging and fluorescein leakage in diabetic retinopathy (DR). METHODS: In 38 consecutive patients with DR, ten consecutive 3- × 3-mm fovea-centered OCTA (HS100, Canon Inc., Tokyo, Japan) and fluorescein angiography (FA) were performed, and averaged OCTA images were created based on the 10 images. After detecting all microaneurysms in FA images, the morphology was classified into four types (focal bulge, saccular/pedunculated, fusiform, and mixed) using averaged OCTA images. The correlation between microaneurysm leakage in FA, retinopathy stage, and microaneurysm morphology was estimated. RESULTS: Thirty-eight eyes (50.0%) of the 33 patients were available for analysis, and 370 (63.5%) of the 583 FA-detected microaneurysms were morphologically classifiable (focal bulge, 46; saccular/pedunculated, 143; fusiform, 29; and mixed, 152) in OCTA. There was a significant correlation between stage and percentage of microaneurysm morphology and between morphology and the presence of leakage (P < 0.0001 and P < 0.01, respectively). The proportion of focal bulges decreased with stage progression, while the other three types increased with stage progression. The percentage of FA leakage for focal bulge, saccular/pedunculated, fusiform, and mixed was 41.3%, 66.4%, 82.8%, and 66.4%, respectively, and the fusiform type showed significant FA leakage. CONCLUSION: Microaneurysm morphology is correlated with the DR stage and FA leakage. Microaneurysm morphology recognition using OCTA image averaging may be useful for the clinical evaluation of DR.

Charcot-Bouchard aneurysms revisited: clinicopathologic correlations.

Intracerebral hemorrhage (ICH) is a significant cause of morbidity and mortality worldwide. Hypertension and cerebral amyloid angiopathy (CAA) are the most common causes of primary ICH, but the mechanism of hemorrhage in both conditions is unclear. Although fibrinoid necrosis and Charcot-Bouchard aneurysms (CBAs) have been postulated to underlie vessel rupture in ICH, the role and significance of CBAs in ICH has been controversial. First described as the source of bleeding in hypertensive hemorrhage, they are also one of the CAA-associated microangiopathies along with fibrinoid necrosis, fibrosis and "lumen within a lumen appearance." We describe clinicopathologic findings of CBAs found in 12 patients out of over 2700 routine autopsies at a tertiary academic medical center. CBAs were rare and predominantly seen in elderly individuals, many of whom had multiple systemic and cerebrovascular comorbidities including hypertension, myocardial and cerebral infarcts, and CAA. Only one of the 12 subjects with CBAs had a large ICH, and the etiology underlying the hemorrhage was likely multifactorial. Two CBAs in the basal ganglia demonstrated associated microhemorrhages, while three demonstrated infarcts in the vicinity. CBAs may not be a significant cause of ICH but are a manifestation of severe cerebral small vessel disease including both hypertensive arteriopathy and CAA.

Detection of microaneurysms and hemorrhages based on improved Hessian matrix.

PURPOSE: Knowing the early lesion detection of fundus images is very important to prevent blindness, and accurate lesion segmentation can provide doctors with diagnostic evidence. This study proposes a method based on improved Hessian matrix eigenvalue analysis to detect microaneurysms and hemorrhages in the fundus images of diabetic patients. METHODS: A two-step method including identification of lesion candidate regions and classification of candidate regions is adopted. In the first step, the method of eigenvalue analysis based on the improved hessian matrix was applied to enhance the image preprocessed. A dual-threshold method was used for segmentation. Then, blood vessels were gradually removed to obtain the lesion candidate regions. In the second step, all candidates were classified into three categories: microaneurysms, hemorrhages and the others. RESULTS: The proposed method has achieved a better performance compared with the existing algorithms on accuracy rates. The classification accuracy rates of microaneurysms and hemorrhages obtained by using our method were 94.4% and 94.0%, respectively, while the classification accuracy rates obtained by using Frangi's filter based on the Hessian matrix to enhance the image were 90.9% and 92.1%. CONCLUSION: This study demonstrated a methodology for enhancing images by using eigenvalue analysis based on the improved Hessian matrix and segmentation by using double thresholds. The proposed method is beneficial to improve the detection accuracy of microaneurysms and hemorrhages in fundus images.

Artificial intelligence velocimetry and microaneurysm-on-a-chip for three-dimensional analysis of blood flow in physiology and disease.

Understanding the mechanics of blood flow is necessary for developing insights into mechanisms of physiology and vascular diseases in microcirculation. Given the limitations of technologies available for assessing in vivo flow fields, in vitro methods based on traditional microfluidic platforms have been developed to mimic physiological conditions. However, existing methods lack the capability to provide accurate assessment of these flow fields, particularly in vessels with complex geometries. Conventional approaches to quantify flow fields rely either on analyzing only visual images or on enforcing underlying physics without considering visualization data, which could compromise accuracy of predictions. Here, we present artificial-intelligence velocimetry (AIV) to quantify velocity and stress fields of blood flow by integrating the imaging data with underlying physics using physics-informed neural networks. We demonstrate the capability of AIV by quantifying hemodynamics in microchannels designed to mimic saccular-shaped microaneurysms (microaneurysm-on-a-chip, or MAOAC), which signify common manifestations of diabetic retinopathy, a leading cause of vision loss from blood-vessel damage in the retina in diabetic patients. We show that AIV can, without any a priori knowledge of the inlet and outlet boundary conditions, infer the two-dimensional (2D) flow fields from a sequence of 2D images of blood flow in MAOAC, but also can infer three-dimensional (3D) flow fields using only 2D images, thanks to the encoded physics laws. AIV provides a unique paradigm that seamlessly integrates images, experimental data, and underlying physics using neural networks to automatically analyze experimental data and infer key hemodynamic indicators that assess vascular injury.

Survey on recent developments in automatic detection of diabetic retinopathy.

Diabetic retinopathy (DR) is a disease facilitated by the rapid spread of diabetes worldwide. DR can blind diabetic individuals. Early detection of DR is essential to restoring vision and providing timely treatment. DR can be detected manually by an ophthalmologist, examining the retinal and fundus images to analyze the macula, morphological changes in blood vessels, hemorrhage, exudates, and/or microaneurysms. This is a time consuming, costly, and challenging task. An automated system can easily perform this function by using artificial intelligence, especially in screening for early DR. Recently, much state-of-the-art research relevant to the identification of DR has been reported. This article describes the current methods of detecting non-proliferative diabetic retinopathy, exudates, hemorrhage, and microaneurysms. In addition, the authors point out future directions in overcoming current challenges in the field of DR research.

Microaneurysms visualisation using five different optical coherence tomography angiography devices compared to fluorescein angiography.

BACKGROUND: To compare fluorescein angiography (FA) and five different optical coherence tomography angiography (OCTA) devices and to test their reproducibility in the evaluation of retinal microaneurysms (MAs) secondary to diabetic retinopathy (DR). METHODS: On the same day, patients with DR were imaged with FA and five OCTA devices: prototype Spectralis OCTA, prototype PlexElite, RTVue XR Avanti, AngioPlex and DRI OCT Triton. For all OCTA devices, a 3×3 volume scan pattern was performed. MAs were evaluated for the superficial capillary plexus (SCP) and deep capillary plexus (DCP). RESULTS: Twenty eyes of 15 patients with DR were included. FA counted a significantly higher number of MAs compared to OCTA devices. Spectralis OCTA obtained a significantly higher number of MAs compared to PlexElite, RTVue XR Avanti, AngioPlex and DRI OCT Triton (p<0.0001). PlexElite and AngioPlex showed a greater number of MAs in the SCP, Spectralis OCTA, RTVue XR Avanti and DRI OCT Triton in the DCP. Higher sensitivity (43.3%) but lowest specificity (54.4%) was observed for Spectralis OCTA compared to other devices. The higher specificity (78.5%) and positive predictive value (83.3%) were observed for DRI OCT Triton. CONCLUSIONS: FA remains the best imaging modality to visualise retinal MAs. Spectralis OCTA was able to detect more MAs compared to other devices, likely due to the higher number of B-scans in the scanned area as well as due to the higher number of repeated B-scans. The high variability between OCTA devices should be taken into account for future clinical trials as in clinical practice.

Microaneurysm density in residual oedema after anti-vascular endothelial growth factor therapy for diabetic macular oedema.

PURPOSE: To investigate the relationship between microaneurysm (MA) density and residual oedema after intravitreal injection of an anti-vascular endothelial growth factor agent for the treatment of diabetic macular oedema (DMO). METHODS: Patients with DMO were divided into those with residual oedema (RO) and those with no residual oedema (NRO) by the presence and absence of oedema at 1 month after intravitreal injection of either aflibercept or ranibizumab. We then compared MA density, best corrected visual acuity (BCVA), central retinal thickness (CRT) and size of the severely thickened area, as indicated by a white area (WA) on optical coherence tomography. RESULTS: We examined 48 eyes in the RO group and 25 eyes in the NRO group (n = 73). In both groups, the CRT and WA size significantly decreased and BCVA improved at 1 month and thereafter. CRT was significantly higher and BCVA was poor in the RO group at 1 and 3 months, while WA size was larger at 1, 3 and 6 months compared with the NRO group (p < 0.05). The number of injections in the RO group (3.62 ± 1.75) was larger than the NRO group (1.89 ± 0.97; p < 0.0001). At 1 and 6 months, the MA density in the area with persistent oedema was significantly higher than in the area with improved oedema (1 month: p = 0.0001, 6 months: p = 0.029). CONCLUSION: High MA density and extensive swelling may be characteristic of RO following treatment for DMO with intravitreal injection of either aflibercept or ranibizumab.

Longitudinal panretinal microaneurysm dynamics on ultra-widefield fluorescein angiography in eyes treated with intravitreal aflibercept for proliferative diabetic retinopathy in the recovery study.

BACKGROUND/AIMS: Quantifying microaneurysms (MAs) turnover may be an objective measure for therapeutic response in diabetic retinopathy. This study assesses changes in MA counts on ultra-widefield fluorescein angiography (UWFA) in subjects undergoing treatment with intravitreal aflibercept injection (IAI) for proliferative diabetic retinopathy (PDR) in the Intravitreal Aflibercept for Retinal Non-Perfusion in Proliferative Diabetic Retinopathy(RECOVERY) study using an automated MA detection platform. METHODS: RECOVERY is a prospective study that enrolled 40 subjects with PDR randomised 1:1 to receive 2 mg IAI every 4 weeks(q4wk) or every 12 weeks (q12wk). UWFA images were obtained at baseline, 6 months and 1 year. Images were analysed using an automated segmentation platform to detect and quantify MAs. Zones 1, 2 and 3 correspond to the macula, mid-periphery and far-periphery, respectively. RESULTS: The q4wk cohort demonstrated a significant decline in MAs in all zones and panretinally at baseline versus month 6, baseline versus year 1, and month 6 versus year 1 (-20.0% to -61.8%; all p<0.001). In the q12wk cohort, baseline versus month 6 showed a significant decline panretinally (mean: -34.2%; p<0.001) and in zone 3 (mean -44.18%; p<0.001). Addiitonally, baseline to year 1 in the q12wk group demonstrated significant decline panretinally (mean: -47.7%; p<0.001) and in zone 3 (mean: -59.8%; p<0.001). All zones demonstrated significantly decline from month 6 to year 1 in the q12wk group. CONCLUSION: Therapy with IAI demonstrates significantly reduced panretinal MA counts in PDR at 1 year in both treatment groups. The use of automated platforms to detect and quantify MAs may provide a novel imaging marker for evaluating disease activity and therapeutic impact. TRIAL REGISTRATION NUMBER: NCT02863354.

Visualization of microaneurysms in macular telangiectasia type 1 on optical coherence tomography angiography before and after photocoagulation.

PURPOSE: To evaluate changes in the visualization of microaneurysms (MAs) in cases of macular telangiectasia (Mac Tel) type 1 on optical coherence tomography angiography (OCTA) before and after treatment with direct photocoagulation and to evaluate their relationship with treatment efficacy. METHODS: The study included 12 eyes from 12 patients (8 men, 4 women; mean age 72.1 years) with Mac Tel type 1 accompanied by cystoid macular edema. OCTA for the evaluation of MAs was performed before and 15 min and 6, 12, and 24 weeks after photocoagulation. The best-corrected visual acuity (BCVA) and central retinal thickness (CRT) were also evaluated. RESULTS: A total of 73 MAs were detected within the areas of macular edema on OCTA, and 39 of these underwent photocoagulation. At 15 min after treatment, 17 MAs were no longer visible on OCTA. At 6 weeks, two MAs had reappeared, whereas five additional MAs were no longer visible. The CRT in eyes with resolved MA was significantly less than that in eyes with persistent MAs (p = 0.016). At 24 weeks, seven eyes had no visible MAs, and the BCVA was not significantly different from baseline. CONCLUSION: OCTA can monitor changes in the visualization of MAs associated with Mac Tel type 1 after direct photocoagulation. Eyes in which MAs disappeared after treatment could recover from cystoid macular edema.

Detection rate of diabetic macular microaneurysms comparing dye-based angiography and optical coherence tomography angiography.

Diabetic maculopathy (DM) is a microvascular dysfunction clinically characterized by microaneurysms (MA) leading to edema and central visual deprivation. This prospective explorative study investigated 27 eyes of 17 patients with DM by fluorescein/indocyanine green angiography (FA/ICGA; SPECTRALIS HRA-OCT, Heidelberg Engineering) and by swept source-optical coherence tomography angiography (SS-OCTA; DRI-OCT Triton Plus, Topcon) to identify clinically relevant MAs. The SS-OCTA cubes were split into the superficial capillary plexus (SCP) and the deep capillary plexus (DCP) according to the automated segmentation. The images of all modalities were superimposed for alignment by an Early Treatment Diabetic Retinopathy Study grid overlay and compared to each other. In total, the mean number of MAs in FA was 33.4 ± 22 (standard deviation) (median 27.5 [q1:21.75;q3:38.25]), in ICGA 24.9 ± 16.9 (17.5 [14;35]), in the SCP 6.5 ± 3.7 (5.5 [3.75;9.25]) and in the DCP 18.1 ± 10.5 (18.5 [10.75;23.5]). Mixed effects models between ICGA and the DCP were borderline significant (p = 0.048; 95% confidence interval 0.21 to 13.49), whereas all other imaging methods differed significantly. Quantitative analysis of MAs in DM showed a plausible agreement between ICGA and the DCP in SS-OCTA. These findings contribute to the imaging methodology in DM.

Miliary microaneurysms: An angiographic biomarker of leukemic retinopathy?

A 16-year-old girl was referred as retinitis and vasculitis post-typhoid fever. Fundus examination revealed bilateral pseudo-sheathing, scattered hemorrhages with retinal infiltrates. Wide-field fundus fluorescein angiography (FFA) showed peripheral vascular hyperfluorescence; 55° FFA images showed a "firecracker-like" peripheral vasculature, but a closer look revealed miliary microaneurysms (MAs). Peripheral smear examination clinched the diagnosis of chronic myeloid leukemia. MAs on FFA in leukemic retinopathy have been frequently described in the literature. Our report emphasizes its presence, miliary nature, and need for closer inspection of FFA images. We believe that this angiographic sign has potential to become one of the imaging biomarkers of leukemic retinopathy.

Automatic Grading System for Diabetic Retinopathy Diagnosis Using Deep Learning Artificial Intelligence Software.

Purposes: To describe the development and validation of an artificial intelligence-based, deep learning algorithm (DeepDR) for the detection of diabetic retinopathy (DR) in retinal fundus photographs. Methods: Five hundred fundus images, which had detailed labelling of DR lesions, were transmitted to be analysed, including localization of the optic disk and macular, vessel segmentation, detection of lesions, and grading of DR. The multi-level iterative method of convolutional neural network and the strategy of enhanced learning were used to improve the accuracy of the system (DeepDR) for grading DR. Three public data sets were used to further train the software. The final grading results were tested based on the fundus images provided by the hospitals. Results: For 6788 fundus images (both macular and disc centred) of two Hospital Eye Center, the detection of microaneurysm, haemorrhage and hard exudates had an accuracy of 99.7%, 98.4% and 98.1%, respectively. The current algorithm accuracy was 0.96. Another 20,000 fundus images from community screening were selected, and 7593 photos of poor quality were excluded according to quality standards. Accuracy for accurate staging of fundus photos: accuracy was 0.9179. The sensitivity, specificity and area under the curve (AUC) were 80.58%, 95.77% and 0.9327, respectively. Conclusions: This artificial intelligence-based DeepDR can be used with high accuracy for the detection of DR in retinal images. This technology offers the potential to increase the efficiency and accessibility of DR screening programs.

Quantitative Assessment of the Severity of Diabetic Retinopathy.

PURPOSE: To determine whether a quantitative approach to assessment of the severity of diabetic retinopathy (DR) lesions on ultrawide field (UWF) images can provide new parameters to predict progression to proliferative diabetic retinopathy (PDR). METHODS: One hundred forty six eyes from 73 participants with DR and 4 years of follow-up data were included in this post hoc analysis, which was based on a cohort of 100 diabetic patients enrolled in a previously published prospective, comparative study of UWF imaging at the Joslin Diabetes Center. Diabetic Retinopathy Severity Score level was determined at baseline and 4-year follow-up visits using mydriatic 7-standard field Early Treatment Diabetic Retinopathy Study (ETDRS) photographs. All individual DR lesions (hemorrhage [H], microaneurysm [ma], cotton wool spot [CWS], intraretinal microvascular abnormality [IRMA]) were manually segmented on stereographic projected UWF. For each lesion type, the frequency/number, surface area, and distances from the optic nerve head (ONH) were computed. These quantitative parameters were compared between eyes that progressed to PDR in 4 years and eyes that did not progress. Univariable and multivariable logistic regression analyses were performed to identify parameters that were associated with an increased risk for progression to PDR. RESULTS: A total of 146 eyes of 73 subjects were included in the final analysis. The mean age of the study cohort was 53.1 years, and 42 (56.8%) subjects were female. The number and surface area of H/ma's and CWSs were significantly (P ≤ .05) higher in eyes that progressed to PDR compared with eyes that did not progress by 4 years. Similarly, H/ma's and CWSs were located further away from the ONH (ie, more peripheral) in eyes that progressed (P < .05). DR lesion parameters that conferred a statistically significant increased risk for proliferative diabetic retinopathy in the multivariate model included hemorrhage area (odds ratio [OR], 2.63; 95% confidence interval [CI], 1.25-5.53), and greater distance of hemorrhages from the ONH (OR, 1.24; 95% CI, 0.97-1.59). CONCLUSIONS: Quantitative analysis of DR lesions on UWF images identifies new risk parameters for progression to PDR including the surface area of hemorrhages and the distance of hemorrhages from the ONH. Although these risk factors will need to be confirmed in larger, prospective studies, they highlight the potential for quantitative lesion analysis to inform the design of a more precise and complete staging system for diabetic retinopathy severity in the future. NOTE: Publication of this article is sponsored by the American Ophthalmological Society.