Deep learning techniques were used in ophthalmology to develop artificial intelligence (AI) models for predicting the short-term effectiveness of anti-VEGF therapy in patients with macular edema secondary to branch retinal vein occlusion (BRVO-ME). 180 BRVO-ME patients underwent pre-treatment FFA scans. After 3 months of ranibizumab injections, CMT measurements were taken at baseline and 1-month intervals. Patients were categorized into good and poor prognosis groups based on macular edema at the 4th month follow-up. FFA-Net, a VGG-based classification network, was trained using FFA images from both groups. Class activation heat maps highlighted important locations. Benchmark models (DesNet-201, MobileNet-V3, ResNet-152, MansNet-75) were compared for training results. Performance metrics included accuracy, sensitivity, specificity, F1 score, and ROC curves. FFA-Net predicted BRVO-ME treatment effect with an accuracy of 88.63% and an F1 score of 0.89, with a sensitivity and specificity of 79.40% and 71.34%, respectively.The AUC of the ROC curve for the FFA-Net model was 0.71. The use of FFA based on deep learning technology has feasibility in predicting the treatment effect of BRVO-ME. The FFA-Net model constructed with the VGG model as the main body has good results in predicting the treatment effect of BRVO-ME. The typing of BRVO in FFA may be an important factor affecting the prognosis.

BACKGROUND: The study was designed to investigate microvascular and morphological changes in retinal vein occlusion (RVO) using multimodal imaging after intravitreal ranibizumab (IVR) with or without triamcinolone acetonide (IVTA) injections.
METHODS: This was a retrospective and observational study. Fifty patients (52 eyes) diagnosed with RVO were enrolled. Best corrected visual acuity (BCVA), ophthalmoscopy, fundus fluorescein angiography (FFA), spectral domain optical coherence tomography (SDOCT), and optical coherence tomography angiography (OCTA) were employed sequentially both before treatment and at the last visit after treatment.
RESULTS: The mean logMAR VAs in BRVO eyes decreased significantly after treatment (P = 0.029). OCTA showed there was a significant difference in foveal avascular zone (FAZ) in BRVO eyes (P = 0.024), superificial foveal vessel density in both CRVO (P = 0.0004) and BRVO eyes (P = 0.02155). OCT showed the foveal thickness had significant differences after treatment in both CRVO (P < 0.0001) and BRVO eyes (P = 0.0001). BCVA was associated most commonly with ellipsoid zone integrity (P = 0.022). The BCVA in eyes treated with IVR and IVTA was significantly decreased compared with IVR only in BRVO group (P = 0.021). However, the combination of IVR + IVTA significantly improved intraocular pressure (IOP) compared with IVR only in BRVO group (P = 0.037).
CONCLUSIONS: Both IVR and IVR + IVTA can significantly improve the central vision, macular structure, and functions in BRVO group. Simultaneous IVR with IVTA can significantly increase BCVA compared with IVR only in BRVO group.

OBJECTIVE: To explore the sensitive components of full-field electroretinography (ERG) as indicators of retina function at the onset of acute ischaemic central retinal vein occlusion (CRVO).
METHODS: 11 patients (11 eyes) with ischaemic CRVO and 32 patients (32 eyes) with non-ischaemic CRVO who presented with first-episode unilateral CRVO within 1 month of symptom onset and with no previous intervention were examined by the International Society for Clinical Electrophysiology of Vision standard ERG.
RESULTS: A significant amplitude decline and peak time delay in light-adapted (LA) 3 ERG and LA 30 Hz flicker ERG (p<0.05 for all) was found in the ischaemic CRVO eyes, compared with the non-ischaemic CRVO eyes. The b/a amplitude ratio of dark-adapted (DA) 3 ERG, DA 10 ERG and LA 3 ERG was significantly different between the ischaemic and non-ischaemic groups (p<0.05 for all). Regarding oscillatory potentials (OPs), the amplitudes of OP1, OP2 and OP3 as well as the sum of DA 3 OP1-4 amplitudes (∑OPs) showed significant changes (p<0.01 for all) between two groups. No peak time delay of OPs was found between the ischaemic and non-ischaemic CRVO eyes.
CONCLUSIONS: The amplitude of DA 0.01 ERG, components of LA 3 ERG and LA 30 Hz flicker ERG, and the b/a amplitude ratio could be among the most sensitive indicators in patients with acute ischaemic CRVO. The amplitudes of OP1, OP2, OP3 and ∑OPs in the CRVO eyes were reduced to 40% of the control values, showing that this quantitative method is reliable for detecting ischaemic retinal diseases, even in early stage.

OBJECTIVE: The aim of this study was to analyze the incidence of retinal vein occlusion (RVO) in patients with and without diabetes in the population and compare the influencing factors.
METHODS: The community-based Kailuan Eye Study included 14,440 participants (9835 male, 4605 female) with a mean age of 54.0 ± 13.3 years (range, 20-110 years). They underwent a systemic and ophthalmologic examination. RVO were diagnosed on fundus photographs.
RESULTS: By matching for age and gender, we included a total of 2767 patients each with diabetes and non-diabetes. The prevalence of RVO among patients with and without diabetes was 1.5% and 0.8%, respectively. The prevalence of RVO was higher in patients with diabetes than in patients without diabetes in all age groups. Multifactorial regression analysis showed that only fasting blood glucose levels were significantly different between patients with RVO with or without DM. The occurrence of RVO in the group with diabetes was mainly associated with higher fasting glucose and systolic blood pressure; in the group without diabetes, RVO was mainly associated with higher diastolic blood pressure, Body Mass Index, and lower low-density lipoprotein cholesterol levels.
CONCLUSIONS: We found that patients with diabetes have increased risks of RVO. In addition to blood pressure control, we recommend educating patients with diabetes about RVO, to prevent its subsequent occurrence.

Branch retinal vein occlusion (BRVO) is the most prevalent retinal vascular disease that constitutes a threat to vision due to increased venous pressure caused by venous effluent in the space, leading to impaired visual function. Optical Coherence Tomography Angiography (OCTA) is an innovative non-invasive technique that offers high-resolution three-dimensional structures of retinal blood vessels. Most publicly available datasets are collected from single visits with different patients, encompassing various eye diseases for distinct tasks and areas. Moreover, due to the intricate nature of eye structure, professional labeling not only relies on the expertise of doctors but also demands considerable time and effort. Therefore, we have developed a BRVO-focused dataset named Soul (Source of ocular vascular) and propose a human machine collaborative annotation framework (HMCAF) using scrambled retinal blood vessels data. Soul is categorized into 6 subsets based on injection frequency and follow-up duration. The dataset comprises original images, corresponding blood vessel labels, and clinical text information sheets which can be effectively utilized when combined with machine learning.

OBJECTIVE: This study aimed to assess the efficacy and safety of anti-VEGF combined with dexamethasone implant for the retinal vein occlusion patients with macular edema.
METHODS: In this prospective, case-controlled, cohort clinical trial (Register ID: ChiCTR2400080048), patients with non-ischemic retinal vein occlusion were enrolled from the Sanmenxia Central Hospital from August 2020 to April 2023. The patients were randomized into two groups. All the patients received ranibizumab intravitreal injection in the first 3 consecutive months. For the ranibizumab group, anti-VEGF injections were as needed thereafter in case of recurrence of macular edema; For the combination group, the patients received an intravitreal dexamethasone implant injection at 15 days after the first ranibizumab injection. The primary outcome measurements were improvement in best corrected visual acuity (BCVA) and reduction in central macular thickness (CMT). The secondary outcomes were recurrence of macular edema, number of intravitreal injections, and injection interval. Safety profiles were also recorded.
RESULTS: A total of 124 patients were included, of which 73 patients completed all follow-ups. Both the ranibizumab monotherapy and the combination therapy significantly improved BCVA at all time points, compared to the baseline. The combined group achieved more BCVA improvement in 3 months, 6 months, and 12 months, compared to the ranibizumab alone group. Compared to the baseline, both groups achieved significant reductions in CMT at all follow-ups. However, the combination group showed more CMT reduction at 1 week post injection, compared to the ranibizumab group. The combination group had a significantly longer injection interval, lower injection time, and recurrence of macular edema. Ocular hypertension was the most common adverse events. Lastly, intraocular pressure was all well controlled by 1-3 glaucoma medications without surgical intervention.
CONCLUSIONS: The combination therapy could significantly improve the BCVA and reduce the CMT with a good safety profile.

UNASSIGNED: Fundus fluorescein angiography (FFA) is the gold standard for retinal vein occlusion (RVO) diagnosis. This study aims to develop a deep learning-based system to diagnose and classify RVO using FFA images, addressing the challenges of time-consuming and variable interpretations by ophthalmologists.
UNASSIGNED: 4028 FFA images of 467 eyes from 463 patients were collected and annotated. Three convolutional neural networks (CNN) models (ResNet50, VGG19, InceptionV3) were trained to generate the label of image quality, eye, location, phase, lesions, diagnosis, and macular involvement. The performance of the models was evaluated by accuracy, precision, recall, F-1 score, the area under the curve, confusion matrix, human-machine comparison, and Clinical validation on three external data sets.
UNASSIGNED: The InceptionV3 model outperformed ResNet50 and VGG19 in labeling and interpreting FFA images for RVO diagnosis, achieving 77.63%-96.45% accuracy for basic information labels and 81.72%-96.45% for RVO-relevant labels. The comparison between the best CNN and ophthalmologists showed up to 19% accuracy improvement with the inceptionV3.
UNASSIGNED: This study developed a deep learning model capable of automatically multi-label and multi-classification of FFA images for RVO diagnosis. The proposed system is anticipated to serve as a new tool for diagnosing RVO in places short of medical resources.

OBJECTIVE: To evaluate the clinical efficacy of dexamethasone (DEX) implant, for the treatment of macular edema (ME) caused by retinal vein occlusion (RVO) and diabetic retinopathy (DR) through a systematic review and meta-analysis.
METHODS: The PubMed, Embase and Cochrane Library databases were comprehensively searched from inception to November 21, 2022, for studies evaluating the clinical efficacy of DEX implant for patients with retinal vein occlusion macular edema (RVO-ME) or diabetic macular edema (DME). Randomized controlled trials (RCTs) published in English were considered eligible. The Cochrane Collaboration tool was applied to assess the risk of bias in each study. Effect estimates with 95% confidence intervals (CIs) were pooled using the random effects model. We also conducted subgroup analyses to explore the sources of heterogeneity and the stability of the results.
RESULTS: This meta-analysis included 8 RCTs (RVO-ME [n = 2] and DME [n = 6]) assessing a total of 336 eyes. Compared with anti-VEGF therapy, DEX implant treatment achieved superior outcomes in terms of best corrected visual acuity (BCVA) (mean difference [MD] = -3.68 ([95% CI, -6.11 to -1.25], P = 0.003), and no heterogeneity was observed (P = 0.43, I2 = 0%). DEX implant treatment also significantly reduced central macular thickness (CMT) compared with anti-VEGF treatment (MD = -31.32 [95% CI, -57.92 to -4.72], P = 0.02), and there was a high level of heterogeneity between trials (P = 0.04, I2 = 54%). In terms of severe adverse events, DEX implant treatment had a higher risk of elevated intraocular pressure than anti-VEGF therapy (RR = 6.98; 95% CI: 2.16 to 22.50; P = 0.001), and there was no significant difference in cataract progression between the two groups (RR = 1.83; 95% CI: 0.63 to 5.27, P = 0.31).
CONCLUSIONS: Compared with anti-VEGF therapy, DEX implant treatment is more effective in improving BCVA and reducing ME. Additionally, DEX implant treatment has a higher risk of elevated intraocular pressure. Due to the small number of studies and the short follow-up period, the results should be interpreted with caution. The long-term effects of the two treatments need to be further determined.
BACKGROUND: Prospero Registration Number CRD42021243185.

Retinal vein occlusion (RVO) refers to the occlusion of the central retinal vein or primary and secondary branches caused by multiple factors. Clinical treatments for it include intravitreal or systemic vasodilator application, local usage of steroids and NSAID (non-steroidal anti-inflammatory drugs), thrombolysis, hemodilution, retinal laser photocoagulation, vitrectomy with vascular sheath incision, chorioretinal venous anastomosis (CRVA), and so on. At present, most treatments are aimed at RVO complications, while chorioretinal vein anastomosis can fundamentally reflux retinal vein blood through the choroid by venous vascular remodeling. Reports on the treatment of retinal vein occlusion by chorioretinal anastomosis are numerous in various countries. As a treatment means, CRVA can drain the venous blood, skipping the thrombosis spot, thus partially relieving anatomical vascular occlusion to achieve a therapeutic purpose. In this study, CRVA is evaluated from the aspects of indications, implementation process, postoperative effect evaluation, complications, and combination with anti-VEGF treatment. Based on the development of laser technology and vitrectomy, we hope to further review this treatment and provide a new reference for the clinical treatment of RVO.

This study aims to explore the link between retinal vein occlusion (RVO), a blinding ocular condition, and alterations in gut microbiota composition, to offer insights into the pathogenesis of RVO. Fecal samples from 25 RVO patients and 11 non-RVO individuals were analyzed using 16S rRNA sequencing and liquid chromatography-mass spectrometry (LC-MS). Significant differences in the abundance of gut microbial species were noted between RVO and non-RVO groups. At the phylum level, the RVO group showed an elevation in the ratio of Firmicutes to Bacteroidetes. At the genus level, the RVO group showed higher abundance in Escherichia_Shigella (P < 0.05) and less abundance in Parabacteroides (P < 0.01) than the non-RVO group. Functional predictions indicated reduced folate synthesis, biotin metabolism, and oxidative phosphorylation, with an increase in butyric acid metabolism in the RVO group. LC-MS analysis showed significant differences in purine metabolism, ABC transporters, and naphthalene degradation pathways, especially purine metabolism. Pearson correlation analysis revealed significant associations between bacterial genera and fecal metabolites. Enrichment analysis highlighted connections between specific metabolites and bacterial genera. The findings showed that the dysregulation of gut microbiota was observed in RVO patients, suggesting the gut microbiota as a potential therapeutic target. Modulating the gut microbiota could be a novel strategy for managing RVO and improving patient outcomes. Furthermore, the study findings suggest the involvement of gut microbial dysbiosis in RVO development, underscoring the significance of understanding its pathogenesis for effective treatment development.
OBJECTIVE: Retinal vein occlusion (RVO) is a blinding ocular condition, and understanding its pathogenesis is crucial for developing effective treatments. This study demonstrates significant differences in gut microbiota composition between RVO patients and non-RVO individuals, implicating the involvement of gut microbial dysbiosis in RVO development. Functional predictions and metabolic profiling provide insights into the underlying mechanisms, highlighting potential pathways for therapeutic intervention. These findings suggest that modulating the gut microbiota might be a promising strategy for managing RVO and improving patient outcomes.