Fluorescein Angiography Images Research Articles

Deep learning segmentation of non-perfusion area from color fundus images and AI-generated fluorescein angiography

The non-perfusion area (NPA) of the retina is an important indicator in the visual prognosis of patients with branch retinal vein occlusion (BRVO). However, the current evaluation method of NPA, fluorescein angiography (FA), is invasive and burdensome. In this study, we examined the use of deep learning models for detecting NPA in color fundus images, bypassing the need for FA, and we also investigated the utility of synthetic FA generated from color fundus images. The models were evaluated using the Dice score and Monte Carlo dropout uncertainty. We retrospectively collected 403 sets of color fundus and FA images from 319 BRVO patients. We trained three deep learning models on FA, color fundus images, and synthetic FA. As a result, though the FA model achieved the highest score, the other two models also performed comparably. We found no statistical significance in median Dice scores between the models. However, the color fundus model showed significantly higher uncertainty than the other models (p < 0.05). In conclusion, deep learning models can detect NPAs from color fundus images with reasonable accuracy, though with somewhat less prediction stability. Synthetic FA stabilizes the prediction and reduces misleading uncertainty estimates by enhancing image quality.

The factors associated with retinal pigment epithelium tear development in the early phase after treatment initiation for age-related macular degeneration.

This study aimed to evaluate the factors associated with retinal pigment epithelium (RPE) tear development in the early phase after anti-vascular endothelial growth factor (VEGF) drug initiation in eyes with neovascular age-related macular degeneration (nAMD) and retinal pigment epithelial detachment (PED). Treatment-naive eyes with nAMD and PED for which anti-VEGF drug injections had been initiated and followed up for at least 3months after the 1st anti-VEGF drug injection, were retrospectively investigated. Baseline characteristics of the PEDs, including type, height, and area, were evaluated using fundus photographs, fluorescein angiography, and optical coherence tomography images. The association between patient age, sex, medical history, PED characteristics, and the development of RPE tears within 3months of starting anti-VEGF therapy was examined. This study included 244 eyes (230 patients; mean age 75.0years, 159 males and 71 females). RPE tears occurred in 13 eyes (5.3%) within 3months of the start of anti-VEGF therapy. Multivariate analysis showed an association of the development of RPE tears with PED height (every 100µm, odds ratio [OR]: 1.50, 95% confidence interval [CI]: 1.07-2.12, p = 0.019), PED area (every 10 mm2, OR: 3.02, CI: 1.22-7.46, p = 0.016), and the presence of fibrovascular PED (OR: 59.22, CI: 4.12-850.59, p = 0.002). Eyes with cleft (the hypo-reflective space beneath the fibrovascular PED) were more likely to develop an RPE tear (p = 0.01, χ-square test). Fibrovascular PED, large PED area, high PED height, and the cleft finding are independent risk factors for the development of RPE tears early after the administration of anti-VEGF drugs.

Invasive Ductal Carcinoma with Choroidal Metastases

Choroidal metastases, along with choroidal melanoma, are common ocular malignancies. We report a case of a 47-year-old woman with metastatic breast carcinoma to the bone and lung, undergoing chemotherapy, who presented with a rapidly declining visual acuity in her right eye. The diagnosis of right unilateral choroidal metastasis was confirmed using fluorescein angiography, ocular ultrasound, and magnetic resonance imaging. Choroidal metastases typically manifest in advanced stages of disseminated disease and have a poor prognosis. Early detection and appropriate management are crucial for these patients. The treatment approach remains palliative, focusing on systemic disease control and preserving vision when possible.

Reliability of Clinical Grading of Diabetic Retinopathy Compared to Grading of Ultra-widefield Images

Purpose: Evaluate the reliability of clinical grading of diabetic retinopathy (DR) severity compared to grading on ultra-widefield pseudocolor fundus (UWF-CF) and ultra-widefield fluorescein angiography (UWF-FA) images and their relative detection of sight-threatening DR (STDR) and referable DR. Methods: We analyzed 184 diabetic eyes. UWF-CF and UWF-FA images were graded based on the International Clinical Diabetic Retinopathy (ICDR) severity scale. Agreement between clinical and UWF-based severity grading was evaluated using Cohen’s kappa coefficient. The rate of STDR and referable DR was evaluated for each grading method. Results: We found moderate agreement between clinical grading and UWF-CF (k=.456, p &lt;.001) and between UWF-CF and UWF-FA (k= .443, p &lt;.001). Agreement between clinical grading and UWF-FA was fair (k=.397, p &lt;.001). UWF-based grading identified a higher DR grade in 56 eyes (30%) on UWF-CF and 85 eyes (46.2%) on UWF-FA. Compared to clinical grading, UWF-FA detected a higher rate of STDR (44%; 81/184 vs 22.3%; 41/184), while UWF-CF detected more referable eyes (58.1%;107/184 vs 45.65%;84/184). Conclusion: UWF-CF is a valuable tool for identifying referable eyes and can be a useful, non-invasive adjunct to clinical grading. Our results suggest that UWF-FA is particularly useful for detecting unsuspected STDR in eyes with clinically referable DR.

Validation of retinal oximetry vessel selection using fluorescein angiography in patients with optic disc drusen

Retinal oximetry could provide insights into the pathophysiology of optic nerve disease, including optic disc drusen (ODD). Vessel selection for oximetry analysis is based on morphological characteristics of arterioles and venules and supported by an overlay of estimated blood oxygen saturations. The purpose of this cross-sectional study was to determine the validity of this vessel selection procedure by comparing it with vessel selection supported by video fluorescein angiography (FA).The study included 36 eyes of 36 patients with ODD who underwent retinal oximetry (Oxymap retinal oximeter T1) followed by FA (Heidelberg Spectralis). Two trained graders selected vessel segments in a pre-defined measurement area around the optic disc. One of these graders additionally performed the vessel segment selection with the support of FA images. When performed by the same grader, FA-supported and non-FA-supported vessel selection did not lead to significant differences in total vessel segment length, estimated oxygen saturations or vessel diameters (all p > 0.05). Inter-grader differences were found for arterial and venous segment lengths and arterial saturation (p < 0.05). A similar tendency was found for the arteriovenous saturation difference (p = 0.10). In conclusion, identifying vessel segments for retinal oximetry analysis based on vessel morphology and supported by a color-coded saturation overlay appears to be a valid method without the need for invasive angiography. A numerically small inter-grader variation may influence oximetry results. Further studies of retinal oximetry in ODD are warranted.

ASSOCIATION OF INTRAVENOUS FLUORESCEIN ANGIOGRAPHY AND ADAPTIVE OPTICS IMAGING IN DIABETIC RETINOPATHY: A Prospective Case Series.

To our knowledge, we present the first case series investigating the relationship between adaptive optics (AO) imaging and intravenous fluorescein angiography (IVFA) parameters in patients with diabetic retinopathy. Consecutive patients with diabetic retinopathy older than age 18 years presenting to a single center in Toronto, Canada, from 2020 to 2021 were recruited. Adaptive optics was performed with the RTX1 camera (Imagine Eyes, Orsay, France) at retinal eccentricities of 2° and 4°. Intravenous fluorescein angiography was assessed with the artificial intelligence-based RETICAD system to extract blood flow, perfusion, and blood-retinal-barrier (BRB) permeability at the same retinal locations. Correlations between AO and IVFA parameters were calculated using Pearson's correlation coefficient. Across nine cases, a significant positive correlation existed between photoreceptor spacing on AO and BRB permeability (r = 0.303, P = 0.027), as well as perfusion (r = 0.272, P = 0.049) on IVFA. When stratified by location, a significant positive correlation between photoreceptor dispersion and both BRB permeability and perfusion (r = 0.770, P = 0.043; r = 0.846, P = 0.034, respectively) was observed. Cone density was also negatively correlated with BRB permeability (r = -0.819, P = 0.046). Photoreceptor spacing on AO was significantly correlated with BRB permeability and perfusion on IVFA in patients with diabetic retinopathy. Future studies with larger sample sizes are needed to understand the relationship between AO and IVFA parameters in diverse patient populations.

Unified deep learning model for predicting fundus fluorescein angiography image from fundus structure image

The prediction of fundus fluorescein angiography (FFA) images from fundus structural images is a cutting-edge research topic in ophthalmological image processing. Prediction comprises estimating FFA from fundus camera imaging, single-phase FFA from scanning laser ophthalmoscopy (SLO), and three-phase FFA also from SLO. Although many deep learning models are available, a single model can only perform one or two of these prediction tasks. To accomplish three prediction tasks using a unified method, we propose a unified deep learning model for predicting FFA images from fundus structure images using a supervised generative adversarial network. The three prediction tasks are processed as follows: data preparation, network training under FFA supervision, and FFA image prediction from fundus structure images on a test set. By comparing the FFA images predicted by our model, pix2pix, and CycleGAN, we demonstrate the remarkable progress achieved by our proposal. The high performance of our model is validated in terms of the peak signal-to-noise ratio, structural similarity index, and mean squared error.

Macula vs periphery in diabetic retinopathy: OCT-angiography and ultrawide field fluorescein angiography imaging of retinal non perfusion.

To investigate the association between peripheral non-perfusion index (NPI) on ultrawide-field fluorescein angiography (UWF-FA) and quantitative OCT-Angiography (OCT-A) metrics in the macula. In total, 48 eyes with UWF-colour fundus photos (CFP), UWF-FA (California, Optos) and OCT-A (Spectralis, Heidelberg) were included. OCT-A (3 × 3 mm) was used to determine foveal avascular zone (FAZ) parameters and vessel density (VD), perfusion density (PD), fractal dimension (FD) on superficial capillary plexus (SCP). NPI's extent and distribution was determined on UWF-FA within fovea centred concentric rings corresponding to posterior pole (<10 mm), mid-periphery (10-15 mm), and far-periphery (>15 mm) and within the total retinal area, the central macular field (6×6 mm), ETDRS fields and within each extended ETDRS field (P3-P7). Macular PD was correlated to NPI in total area of retina (Spearman ρ = 0.69, p < 0.05), posterior pole (ρ = 0.48, p < 0.05), mid-periphery (ρ = 0.65, p < 0.05), far-periphery (ρ = 0.59, p < 0.05), P3-P7 (ρ = 0,55 at least, p < 0.05 for each), central macula (ρ = 0.47, p < 0.05), total area in ETDRS (ρ = 0.55, p < 0.05). Macular VD and FD were correlated to NPI of total area of the retina (ρ = 0.60 and 0.61, p < 0.05), the mid-periphery (ρ = 0.56, p < 0.05) and far-periphery (ρ = 0.60 and ρ = 0.61, p < 0.05), and in P3-P7 (p < 0.05). FAZ perimeter was significantly corelated to NPI at posterior pole and central macular area (ρ = 0.37 and 0.36, p < 0.05), and FAZ area to NPI in central macular area (ρ = 0.36, p < 0.05). Perfusion macular metrics on OCT-A correlated with UWF-FA's non-perfusion (NP), particularly in the retina's mid and far periphery, suggesting that OCT-A might be a useful non-invasive method to estimate peripheral retinal NP.

Controllable editing via diffusion inversion on ultra-widefield fluorescein angiography for the comprehensive analysis of diabetic retinopathy.

By incorporating multiple indicators that facilitate clinical decision making and effective management of diabetic retinopathy (DR), a comprehensive understanding of the progression of the disease can be achieved. However, the diversity of DR complications poses challenges to the automatic analysis of various information within images. This study aims to establish a deep learning system designed to examine various metrics linked to DR in ultra-widefield fluorescein angiography (UWFA) images. We have developed a unified model based on image generation that transforms input images into corresponding disease-free versions. By incorporating an image-level supervised training process, the model significantly reduces the need for extensive manual involvement in clinical applications. Furthermore, compared to other comparative methods, the quality of our generated images is significantly superior.

FA4SANS-GAN: A Novel Machine Learning Generative Adversarial Network to Further Understand Ophthalmic Changes in Spaceflight-Associated Neuro-Ocular Syndrome (SANS)

PurposeTo provide automated system for synthesizing fluorescein angiography (FA) images from color fundus (CF) photographs for averting risks associated with fluorescein dye and extend its future application to Space-associated neuro-ocular syndrome (SANS) detection in spaceflight where resources are limited. DesignDevelopment and validation of a novel conditional generative adversarial network (GAN) trained on limited amount of fluorescein angiography and color fundus images with diabetic retinopathy and control cases. ParticipantsColor fundus and fluorescein angiography paired images for unique patients were collected from a publicly available study. MethodsFA4SANS-GAN was trained to generate fluorescein angiography images from color fundus photographs using two multi-scale generators coupled with two patch-GAN discriminators. 850 CF and FA images were utilized for training by augmenting images from 17 unique patients. The model was evaluated on 56 fluorescein images collected from 14 unique patients. In addition, it was compared with three other GAN architectures trained on the same dataset. Furthermore, we test the robustness of the models against acquisition noise and retaining structural information when introduced to artificially created biological markers. Main Outcome MeasureFor GAN synthesis metric Fréchet Inception Distance (FID) and Kernel Inception Distance (KID). Also, two one-sided tests (TOST) based on Welch's t-test for measuring statistical significance. ResultsOn test FA images, mean FID for FA4SANS-GAN was 39.8 (SD 9.9), which is better than GANgio model’s mean of 43.2 (SD 13.7), Pix2PixHD’s mean of 57.3 (SD 11.5) and Pix2Pix’s mean of 67.5 (SD 11.7). Similarly for KID, FA4SANS-GAN achieved mean of 0.00278 (SD 0.00167) which is better than other three model’s mean KID of 0.00303 (SD 0.00216), 0.00609 (SD 0.00238), 0.00784 (SD 0.00218). For TOST measurement, FA4SANS-GAN has proven to be statistically significant vs. GANgio (p = 0.006); vs Pix2PixHD (p < 0.00001); and vs. Pix2Pix (p < 0.00001). ConclusionOur study has shown FA4SANS-GAN to be statistically significant for two GAN synthesis metrics. Moreover, it is robust against acquisition noise, and can retain clear biological markers compared to the other three GAN architectures. This deployment of this model can be crucial in International Space Station (ISS) for detecting Spaceflight-associated neuro-ocular syndrome (SANS).

Comparison of Widefield OCT Angiography Features Between Severe Non-Proliferative and Proliferative Diabetic Retinopathy.

There is a high and ever-increasing global prevalence of diabetic retinopathy (DR) and invasive imaging techniques are often required to confirm the presence of proliferative disease. The aim of this study was to explore the images of a rapid and non-invasive technique, widefield optical coherence tomography angiography (OCT-A), to study differences between patients with severe non-proliferative and proliferative DR (PDR). We conducted an observational longitudinal study from November 2022 to March 2023. We recruited 75 patients who were classified into a proliferative group (28 patients) and severe non-proliferative group (47 patients). Classification was done by specialist clinicians who had full access to any multimodal imaging they required to be confident of their diagnosis, including fluorescein angiography. For all patients, we performed single-shot 4 × 4 and 10 × 10mm (widefield) OCT-A imaging and when possible, the multiple images required for mosaic 17.5 × 17.5mm (ultra widefield) OCT-A imaging. We assessed the frequency with which proliferative disease was identifiable solely from these OCT-A images and used custom-built MATLAB software to analyze the images and determine computerized metrics such as density and intensity of vessels, foveal avascular zone, and ischemic areas. On clinically assessing the OCT-A 10 × 10 fields, we were only able to detect new vessels in 25% of known proliferative images. Using ultra-widefield mosaic images, however, we were able to detect new vessels in 100% of PDR patients. The image analysis metrics of 4 × 4 and 10 × 10mm images did not show any significant differences between the two clinical groups. For mosaics, however, there were significant differences in the capillary density in patients with PDR compared to severe non-PDR (9.1% ± 1.9 in the PDR group versus 11.0% ± 1.9 for severe group). We also found with mosaics a significant difference in the metrics of ischemic areas; average area of ischemic zones (253,930.1 ± 108,636 for the proliferative group versus 149,104.2 ± 55,101.8 for the severe group. Our study showed a high sensitivity for detecting PDR using only ultra-widefield mosaic OCT-A imaging, compared to multimodal including fluorescein angiography imaging. It also suggests that image analysis of aspects such as ischemia levels may be useful in identifying higher risk groups as a warning sign for future conversion to neovascularization.

Using Deep Learning to Segment Retinal Vascular Leakage and Occlusion in Retinal Vasculitis

ABSTRACT Purpose Retinal vasculitis (RV) is characterised by retinal vascular leakage, occlusion or both on fluorescein angiography (FA). There is no standard scheme available to segment RV features. We aimed to develop a deep learning model to segment both vascular leakage and occlusion in RV. Methods Four hundred and sixty-three FA images from 82 patients with retinal vasculitis were used to develop a deep learning model, in 60:20:20 ratio for training:validation:testing. Parameters, including deep learning architectures (DeeplabV3+, UNet++ and UNet), were altered to find the best binary segmentation model separately for retinal vascular leakage and occlusion, using a Dice score to determine the reliability of each model. Results Our best model for vascular leakage had a Dice score of 0.6279 (95% confidence interval (CI) 0.5584–0.6974). For occlusion, the best model achieved a Dice score of 0.6992 (95% CI 0.6109–0.7874). Conclusion Our RV segmentation models could perform reliable segmentation for retinal vascular leakage and occlusion in FAs of RV patients.

Microvascular flow ultrasound imaging for retinoblastoma

PurposeTo present the results of a pilot study of microvascular flow imaging (MFI) in characterizing tumor vasculature of retinoblastoma. MethodsThe medical records of consecutive patients with retinoblastoma presenting at our institution between July 2019 and June 2022 that were imaged using MFI were reviewed retroactively. Each patient underwent diagnostic evaluation according to standard of care by examination under anesthesia with fluorescein angiography and ocular ultrasound imaging, including color Doppler and MFI. ResultsThirteen eyes of 10 patients with retinoblastoma were included. MFI showed a prominent feeder vessel in 8 eyes, basket vasculature in 6 eyes and tumor bed vascularity in 10 eyes. MFI showed a more extensive vascular branching pattern that was not visible on color Doppler and fluorescein angiography in all eyes. ConclusionsMFI of retinoblastoma patients could add information about tumor vascularity not detectable by color Doppler or fluorescein angiography. Further study is needed to determine whether this information could be used to predict prognosis for ocular salvage and tumor response to treatment.

Update on AMD imaging ‐ Initial diagnosis, follow‐up

AMD is a clinical entity in which diagnostic and therapeutic recommendations are the subject of constant change and up‐date. During this course a basic knowledge on AMD diagnosis will be presented along with the employment of modern diagnostic techniques such as OCT‐angiography. Disease characteristics obtained from OCT, OCTA and fluorescein angiography imaging will be depicted in the context of modern recommendations for its treatment, especially anti‐VEGF treatment schedules. Management algorithms will be outlined along with most frequent therapeutic dilemmas occurring in that clinical entity.

Microaneurysm detection using high-speed megahertz optical coherence tomography angiography in advanced diabetic retinopathy.

To compare detection rates of microaneurysms (MAs) on high-speed megahertz optical coherence tomography angiography (MHz-OCTA), fluorescein angiography (FA) and colour fundus photography (CF) in patients with diabetic retinopathy (DR). For this exploratory cross-sectional study, MHz-OCTA data were acquired with a swept-source OCT prototype (A-scan rate: 1.7 MHz), and FA and CF imaging was performed using Optos® California. MA count was manually evaluated on en face MHz-OCTA/FA/CF images within an extended ETDRS grid. Detectability of MAs visible on FA images was evaluated on corresponding MHz-OCTA and CF images. MA distribution and leakage were correlated with detectability on OCTA and CF imaging. 47 eyes with severe DR (n = 12) and proliferative DR (n = 35) were included. MHz-OCTA and CF imaging detected on average 56% and 36% of MAs, respectively. MHz-OCTA detection rate was significantly higher than CF (p < 0.01). The combination of MHz-OCTA and CF leads to an increased detection rate of 70%. There was no statistically significant association between leakage and MA detectability on OCTA (p = 0.13). For CF, the odds of detecting leaking MAs were significantly lower than non-leaking MAs (p = 0.012). Using MHz-OCTA, detection of MAs outside the ETDRS grid was less likely than MAs located within the ETDRS grid (outer ring, p < 0.01; inner ring, p = 0.028). No statistically significant difference between rings was observed for CF measurements. More MAs were detected on MHz-OCTA than on CF imaging. Detection rate was lower for MAs located outside the macular region with MHz-OCTA and for leaking MAs with CF imaging. Combining both non-invasive modalities can improve MA detection.

Multimodal photoacoustic microscopy, optical coherence tomography, and fluorescence imaging of USH2A knockout rabbits

Usher syndrome type 2A (USH2A) is a genetic disorder characterized by retinal degeneration and hearing loss. To better understand the pathogenesis and progression of this syndrome, animal models such as USH2A knockout (USH2AKO) rabbits have been developed. In this study, we employed multimodal imaging techniques, including photoacoustic microscopy (PAM), optical coherence tomography (OCT), fundus autofluorescence (FAF), fluorescein angiography (FA), and indocyanine green angiography (ICGA) imaging to evaluate the retinal changes in the USH2AKO rabbit model. Twelve New Zealand White rabbits including USH2AKO and wild type (WT) were used for the experiments. Multimodal imaging was implemented at different time points over a period of 12 months to visualize the progression of retinal changes in USH2AKO rabbits. The results demonstrate that ellipsoid zone (EZ) disruption and degeneration, key features of Usher syndrome, began at the age of 4 months old and persisted up to 12 months. The EZ degeneration areas were clearly observed on the FAF and OCT images. The FAF images revealed retinal pigment epithelium (RPE) degeneration, confirming the presence of the disease phenotype in the USH2AKO rabbits. In addition, PAM images provided high-resolution and high image contrast of the optic nerve and the retinal microvasculature, including retinal vessels, choroidal vessels, and capillaries in three-dimensions. The quantification of EZ fluorescent intensity using FAF and EZ thickness using OCT provided comprehensive quantitative data on the progression of degenerative changes over time. This multimodal imaging approach allowed for a comprehensive and non-invasive assessment of retinal structure, microvasculature, and degenerative changes in the USH2AKO rabbit model. The combination of PAM, OCT, and fluorescent imaging facilitated longitudinal monitoring of disease progression and provided valuable insights into the pathophysiology of USH2A syndrome. These findings contribute to the understanding of USH2A syndrome and may have implications for the development of diagnostic and therapeutic strategies for affected individuals. The multimodal imaging techniques employed in this study offer a promising platform for preclinical evaluation of potential treatments and may pave the way for future clinical applications in patients with Usher syndrome.

An Improved Microaneurysm Detection Model Based on SwinIR and YOLOv8.

Diabetic retinopathy (DR) is a microvascular complication of diabetes. Microaneurysms (MAs) are often observed in the retinal vessels of diabetic patients and represent one of the earliest signs of DR. Accurate and efficient detection of MAs is crucial for the diagnosis of DR. In this study, an automatic model (MA-YOLO) is proposed for MA detection in fluorescein angiography (FFA) images. To obtain detailed features and improve the discriminability of MAs in FFA images, SwinIR was utilized to reconstruct super-resolution images. To solve the problems of missed detection of small features and feature information loss, an MA detection layer was added between the neck and the head sections of YOLOv8. To enhance the generalization ability of the MA-YOLO model, transfer learning was conducted between high-resolution images and low-resolution images. To avoid excessive penalization due to geometric factors and address sample distribution imbalance, the loss function was optimized by taking the Wise-IoU loss as a bounding box regression loss. The performance of the MA-YOLO model in MA detection was compared with that of other state-of-the-art models, including SSD, RetinaNet, YOLOv5, YOLOX, and YOLOv7. The results showed that the MA-YOLO model had the best performance in MA detection, as shown by its optimal metrics, including recall, precision, F1 score, and AP, which were 88.23%, 97.98%, 92.85%, and 94.62%, respectively. Collectively, the proposed MA-YOLO model is suitable for the automatic detection of MAs in FFA images, which can assist ophthalmologists in the diagnosis of the progression of DR.

A Rare Condition: The Impact of Coats Disease on Vision

Coats disease is an attenuate ocular vasculopathy illustrated by the accumulation of fluid in the intra-retinal along subretinal space, primarily affecting young males. Although the underlying cause of the disease remains unknown, research has made significant progress in understanding its prevalence, morphology, patient variables, and history. Diagnosis can be challenging, but a range of imaging techniques, including optical coherence tomography (OCT), OCT angiography, ultrasonography, fluorescein angiography, Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) can assist in differential diagnosis and management. Mutations in the norrin deficiency protein (NDP) gene, causing norrin deficiency, are linked to the disorder, with the high male-to-female ratio due to incomplete X-inactivation in females. New therapeutic options, including investigational and standard therapies, have been developed, with ranibizumab showing promising results in previous studies. Standard therapies include cryotherapy, laser photocoagulation, and intravitreal steroids and/or vascular endothelial growth factor (VEGF) injections. Surgical intervention is recommended for retinal detachment (stage 3A or above), with asymptomatic, blind, and depressed stage 5 Coats patients monitored but not requiring treatment. Further research is needed to develop more effective treatments and improve patient outcomes.

OCT-angiography based artificial intelligence-inferred fluorescein angiography for leakage detection in retina [Invited

Optical coherence tomography angiography (OCTA) covers most functions of fluorescein angiography (FA) when imaging the retina but lacks the ability to depict vascular leakage. Based on OCTA, we developed artificial intelligence-inferred-FA (AI-FA) to delineate leakage in eyes with diabetic retinopathy (DR). Training data of 19,648 still FA images were prepared from FA-photo and videos of 43 DR eyes. AI-FA images were generated using a convolutional neural network. AI-FA images achieved a structural similarity index of 0.91 with corresponding real FA images in DR. The AI-FA generated from OCTA correctly depicted vascular occlusion and associated leakage with enough quality, enabling precise DR diagnosis and treatment planning. A combination of OCT, OCTA, and AI-FA yields more information than real FA with reduced acquisition time without risk of allergic reactions.

Deep learning for precision medicine: Guiding laser therapy in ischemic retinal diseases

In this issue of Cell Reports Medicine, Zhao and colleagues1 report a multi-tasking artificial intelligence system that can assist the whole process of fundus fluorescein angiography (FFA) imaging and reduce the reliance on retinal specialists in FFA examination.