To evaluate the effectiveness and safety of superselective ophthalmic artery thrombolysis (SOAT) for central retinal artery occlusion (CRAO) beyond 24h after onset.

This was a retrospective cohort study of CRAO patients treated from January 2019 to July 2025. Patients were divided into four groups by treatment (SOAT/conservative) and onset-to-treatment time (<24h/>24h). Main outcome measures were best-corrected visual acuity (BCVA, logMAR) and central macular thickness (CMT) assessed via spectral-domain optical coherence tomography (SD-OCT), recorded at baseline, 3d and 1mo after treatment. Ocular/systemic adverse events were documented.

A total of 109 CRAO participants were enrolled, including 74 males (67.89%) and 35 females (32.11%), with a mean age of 52.30±11.76y. Underlying diseases were hypertension (78 cases, 71.56%), diabetes (40 cases, 36.70%), arterial atherosclerosis with plaque formation (81 cases, 74.31%), hyperlipidemia (14 cases, 12.84%), and hypercholesterolemia (16 cases, 14.68%). Four groups included 25, 28, 26, and 30 cases in Groups 1 (SOAT<24h), 2 (SOAT>24h), 3 (conservative <24h), and 4 (conservative >24h), respectively. In <24h cohort, BCVA improved significantly in both Group 1 (2.36±0.53 to 1.71±0.81 logMAR, P<0.05) and Group 3 (2.42±0.40 to 1.92±0.76 logMAR, P<0.05). In >24h cohort, thrombolysis improved BCVA (1.84±0.88 to 1.31±0.53 logMAR, P<0.05), while conservative treatment showed no significant change (2.04±0.74 to 1.92±0.73 logMAR, P=0.808). Clinically significant improvement (≥0.3 logMAR) was more frequent with SOAT in both time windows (P<0.05). SOAT significantly reduced CMT in both <24h (256±25.65 to 209±21.22 μm, P<0.001) and >24h groups (242±23.33 to 204±27.22 μm, P<0.001), while conservative treatment had no significant effect on CMT (all P>0.05). Adverse events included orbital swelling (11.3%), new cerebral infarction (7.55%), dizziness/headache (7.55%), and nausea/vomiting (5.66%). No intracranial hemorrhage occurred.

SOAT provides meaningful visual and anatomical benefit even beyond 24h after symptom onset. However, potential ocular and systemic adverse events necessitate careful patient selection and individualized risk assessment.

To investigate the causal effect of obesity on cataract risk and explores the potential mediating roles of metabolites using Mendelian randomization (MR).

Summary-level data from large-scale genome-wide association studies to examine the relationship between obesity and cataract were utilized. Obesity-related traits, including body mass index (BMI), waist-to-hip ratio (WHR), and waist circumference (WC). A two-sample MR approach was employed to assess the causal effect of obesity on cataract risk, while potential mediators were identified from suitable genome-wide association studies (GWAS) datasets. Additionally, a metabolic pathway analysis was conducted.

An increase of 1 standard deviation (SD) in BMI, WHR, and WC was associated with a significantly higher risk of cataract (BMI: odds ratio (OR) 1.0017, 95% confidence interval (CI): 1.0001–1.0032, P=0.0320; WHR: OR 1.0029, 95%CI: 1.0006–1.0051, P=0.0129; WC: OR 1.0020, 95%CI: 1.0001–1.0038, P=0.0390]. These associations remained robust after adjusting for confounding factors in multivariable MR analysis. Furthermore, a two-step MR analysis identified eight potential metabolic mediators, with one mediator showing a significant causal role in the relationship between obesity and cataract.

This work highlights the importance of addressing obesity as a modifiable risk factor for cataracts, particularly through metabolic pathways.

To construct an intelligent segmentation scheme for precise localization of central serous chorioretinopathy (CSC) leakage points, thereby enabling ophthalmologists to deliver accurate laser treatment without navigational laser equipment.

A dataset with dual labels (point-level and pixel-level) was first established based on fundus fluorescein angiography (FFA) images of CSC and subsequently divided into training (102 images), validation (40 images), and test (40 images) datasets. An intelligent segmentation method was then developed, based on the You Only Look Once version 8 Pose Estimation (YOLOv8-Pose) model and segment anything model (SAM), to segment CSC leakage points. Next, the YOLOv8-Pose model was trained for 200 epochs, and the best-performing model was selected to form the optimal combination with SAM. Additionally, the classic five types of U-Net series models [i.e., U-Net, recurrent residual U-Net (R2U-Net), attention U-Net (AttU-Net), recurrent residual attention U-Net (R2AttU-Net), and nested U-Net (UNet++)] were initialized with three random seeds and trained for 200 epochs, resulting in a total of 15 baseline models for comparison. Finally, based on the metrics including Dice similarity coefficient (DICE), intersection over union (IoU), precision, recall, precision-recall (PR) curve, and receiver operating characteristic (ROC) curve, the proposed method was compared with baseline models through quantitative and qualitative experiments for leakage point segmentation, thereby demonstrating its effectiveness.

With the increase of training epochs, the mAP50-95, Recall, and precision of the YOLOv8-Pose model showed a significant increase and tended to stabilize, and it achieved a preliminary localization success rate of 90% (i.e., 36 images) for CSC leakage points in 40 test images. Using manually expert-annotated pixel-level labels as the ground truth, the proposed method achieved outcomes with a DICE of 57.13%, an IoU of 45.31%, a precision of 45.91%, a recall of 93.57%, an area under the PR curve (AUC-PR) of 0.78 and an area under the ROC curve (AUC-ROC) of 0.97, which enables more accurate segmentation of CSC leakage points.

By combining the precise localization capability of the YOLOv8-Pose model with the robust and flexible segmentation ability of SAM, the proposed method not only demonstrates the effectiveness of the YOLOv8-Pose model in detecting keypoint coordinates of CSC leakage points from the perspective of application innovation but also establishes a novel approach for accurate segmentation of CSC leakage points through the “detect-then-segment” strategy, thereby providing a potential auxiliary means for the automatic and precise real-time localization of leakage points during traditional laser photocoagulation for CSC.

To establish a risk prediction model for secondary cataract within 2y after pars plana vitrectomy (PPV) in patients with primary rhegmatogenous retinal detachment (RRD).

Clinical data of patients with primary RRD treated at the Shenzhen Eye Hospital were retrospectively collected. Twenty-four potential influencing factors, including patient characteristics and surgical factors, were selected for analysis. Independent risk factors for secondary cataract were identified through univariate comparisons and multivariate logistic regression analysis. A risk prediction model was constructed and evaluated using receiver operating characteristic (ROC) curves, area under the ROC curve (AUC), calibration plots, and decision curve analysis (DCA) curves.

The 386 cases (389 eyes) of patients who underwent PPV and had complete surgical records were ultimately included. Within a 2-year longitudinal observation, 41.39% of patients developed cataract secondary to PPV. Logistic regression results identified a history of hypertension [odds ratio (OR)=1.78, 95%CI: 1.002–3.163, P=0.049], silicone oil tamponade (OR=3.667, 95%CI: 2.373–5.667, P=0.000), and lens thickness (OR=1.978, 95%CI: 1.129–3.464, P=0.017) as independent risk factors for cataract secondary to PPV. The constructed nomogram achieved AUC=0.6974. Calibration plots indicated good agreement between predicted and observed outcomes, while DCA curves demonstrated the model’s clinical utility.

By incorporating a history of hypertension, vitreous substitute type, and lens thickness, this study constructs a prediction model with moderate discriminative ability. This model offers a valuable tool for clinicians to identify high-risk patients early, potentially allowing for more timely interventions and improved patient outcomes.

To measure the retinal vessels of primary open angle glaucoma (POAG) patients on spectral domain optical coherence tomography (SD-OCT) with a full-width at half-maximum (FWHM) algorithm to better explore their structural changes in the pathogenesis of POAG.

In this retrospective case-control study, the right eyes of 32 patients with POAG and 30 healthy individuals were routinely selected. Images of the supratemporal and infratemporal retinal vessels in the B zones were obtained by SD-OCT, and the edges of the vessels were identified by the FWHM method. The internal and external diameters, wall thickness (WT), wall cross-sectional area (WCSA) and wall-to-lumen ratio (WLR) of the blood vessels were studied.

Compared with the healthy control group, the POAG group showed a significantly reduced retinal arteriolar outer diameter (RAOD), retinal arteriolar lumen diameter (RALD) and WSCA in the supratemporal (124.22±12.42 vs 138.32±10.73 µm, 96.09±11.09 vs 108.53±9.89 µm, and 4762.02±913.51 vs 5785.75±1148.28 µm², respectively, all P<0.05) and infratemporal regions (125.01±15.55 vs 141.57±10.77 µm, 96.27±13.29 vs 110.83±10.99 µm, and 4925.56±1302.88 vs 6087.78±1061.55 µm², all P<0.05). The arteriolar WT and WLR were not significantly different between the POAG and control groups, nor were the retinal venular outer diameter (RVOD), retinal venular lumen diameter (RVLD) or venular WT in the supratemporal or infratemporal region. There was a positive correlation between the arteriolar parameters and visual function.

In POAG, narrowing of the supratemporal and infratemporal arterioles and a significant reduction in the WSCA is observed, while the arteriolar WT and WLR do not change. Among the venular parameters, the external diameter, internal diameter, WT, WLR, and WSCA of the venules are not affected.

To conduct a classification study of high myopic maculopathy (HMM) using limited datasets, including tessellated fundus, diffuse chorioretinal atrophy, patchy chorioretinal atrophy, and macular atrophy, and minimize annotation costs, and to optimize the ALFA-Mix active learning algorithm and apply it to HMM classification.

The optimized ALFA-Mix algorithm (ALFA-Mix+) was compared with five algorithms, including ALFA-Mix. Four models, including ResNet18, were established. Each algorithm was combined with four models for experiments on the HMM dataset. Each experiment consisted of 20 active learning rounds, with 100 images selected per round. The algorithm was evaluated by comparing the number of rounds in which ALFA-Mix+ outperformed other algorithms. Finally, this study employed six models, including EfficientFormer, to classify HMM. The best-performing model among these models was selected as the baseline model and combined with the ALFA-Mix+ algorithm to achieve satisfactory classification results with a small dataset.

ALFA-Mix+ outperforms other algorithms with an average superiority of 16.6, 14.75, 16.8, and 16.7 rounds in terms of accuracy, sensitivity, specificity, and Kappa value, respectively. This study conducted experiments on classifying HMM using several advanced deep learning models with a complete training set of 4252 images. The EfficientFormer achieved the best results with an accuracy, sensitivity, specificity, and Kappa value of 0.8821, 0.8334, 0.9693, and 0.8339, respectively. Therefore, by combining ALFA-Mix+ with EfficientFormer, this study achieved results with an accuracy, sensitivity, specificity, and Kappa value of 0.8964, 0.8643, 0.9721, and 0.8537, respectively.

The ALFA-Mix+ algorithm reduces the required samples without compromising accuracy. Compared to other algorithms, ALFA-Mix+ outperforms in more rounds of experiments. It effectively selects valuable samples compared to other algorithms. In HMM classification, combining ALFA-Mix+ with EfficientFormer enhances model performance, further demonstrating the effectiveness of ALFA-Mix+.

To evaluate the clinical application value of the artificial intelligence assisted pathologic myopia (PM-AI) diagnosis model based on deep learning.

A total of 1156 readable color fundus photographs were collected and annotated based on the diagnostic criteria of Meta-pathologic myopia (PM) (2015). The PM-AI system and four eye doctors (retinal specialists 1 and 2, and ophthalmologists 1 and 2) independently evaluated the color fundus photographs to determine whether they were indicative of PM or not and the presence of myopic choroidal neovascularization (mCNV). The performance of identification for PM and mCNV by the PM-AI system and the eye doctors was compared and evaluated via the relevant statistical analysis.

For PM identification, the sensitivity of the PM-AI system was 98.17%, which was comparable to specialist 1 (P=0.307), but was higher than specialist 2 and ophthalmologists 1 and 2 (P<0.001). The specificity of the PM-AI system was 93.06%, which was lower than specialists 1 and 2, but was higher than ophthalmologists 1 and 2. The PM-AI system showed the Kappa value of 0.904, while the Kappa values of specialists 1, 2 and ophthalmologists 1, 2 were 0.968, 0.916, 0.772 and 0.730, respectively. For mCNV identification, the AI system showed the sensitivity of 84.06%, which was comparable to specialists 1, 2 and ophthalmologist 2 (P>0.05), and was higher than ophthalmologist 1. The specificity of the PM-AI system was 95.31%, which was lower than specialists 1 and 2, but higher than ophthalmologists 1 and 2. The PM-AI system gave the Kappa value of 0.624, while the Kappa values of specialists 1, 2 and ophthalmologists 1 and 2 were 0.864, 0.732, 0.304 and 0.238, respectively.

In comparison to the senior ophthalmologists, the PM-AI system based on deep learning exhibits excellent performance in PM and mCNV identification. The effectiveness of PM-AI system is an auxiliary diagnosis tool for clinical screening of PM and mCNV.