Background: Lattice degeneration and/or retinal breaks, defined as notable peripheral retinal lesions (NPRLs), are prone to evolving into rhegmatogenous retinal detachment which can cause severe visual loss. However, screening NPRLs is time-consuming and labor-intensive. Therefore, we aimed to develop and evaluate a deep learning (DL) system for automated identifying NPRLs based on ultra-widefield fundus (UWF) images. Methods: A total of 5,606 UWF images from 2,566 participants were used to train and verify a DL system. All images were classified by 3 experienced ophthalmologists. The reference standard was determined when an agreement was achieved among all 3 ophthalmologists, or adjudicated by another retinal specialist if disagreements existed. An independent test set of 750 images was applied to verify the performance of 12 DL models trained using 4 different DL algorithms (InceptionResNetV2, InceptionV3, ResNet50, and VGG16) with 3 preprocessing techniques (original, augmented, and histogram-equalized images). Heatmaps were generated to visualize the process of the best DL system in the identification of NPRLs. Results: In the test set, the best DL system for identifying NPRLs achieved an area under the curve (AUC) of 0.999 with a sensitivity and specificity of 98.7% and 99.2%, respectively. The best preprocessing method in each algorithm was the application of original image augmentation (average AUC =0.996). The best algorithm in each preprocessing method was InceptionResNetV2 (average AUC =0.996). In the test set, 150 of 154 true-positive cases (97.4%) displayed heatmap visualization in the NPRL regions. Conclusions: A DL system has high accuracy in identifying NPRLs based on UWF images. This system may help to prevent the development of rhegmatogenous retinal detachment by early detection of NPRLs.

Purpose: This study investigated the effects of microRNA-483-3p (miR-483-3p) on extracellular matrix (ECM) production, and clarified the regulatory mechanism of microRNA-483-3p in human trabecular meshwork cells (HTMCs) under oxidative stress. Methods: The expression levels of ECM (fibronectin, laminin, collagen I) in HTMCs under oxidative stress were measured by Western blot. Changes of miR-483-3p expression in HTMCs were evaluated by quantitative polymerase chain reaction (qPCR). After using lentivirus stably expressing pri-miR-483, the effects of miR-483-3p on the ECM were assessed by qPCR and Western blot. Smad4, the potential target of miR-483-3p according to mRNA target-predicting algorithms, was confirmed by luciferase assay and Western blot. Furthermore, the effects of Smad4 knockdown on ECM expression were investigated by qPCR and Western blot. Results: The mRNA and protein levels of ECM (fibronectin, laminin, collagen I) were upregulated in HTMCs induced by oxidative stress. The expression level of miR-483-3p decreased in HTMCs under oxidative stress, and the ectopic expression of miR-483-3p decreased the levels of ECM. In addition, miR-483-3p targeted Smad4 through two binding sites, resulting in a decrease of Smad4 expression. Furthermore, knockdown of Smad4 reduced the levels of ECM in HTMCs. Conclusions: MicroRNA-483-3p has an inhibitory effect on ECM production in HTMCs through downregulating Smad4, which indicates that miR-483-3p may serve as a potential therapeutic target in glaucoma.

Objective: This study aims to develop and evaluate a non-imaging clinical data-based nomogram for predicting the risk of vision-threatening diabetic retinopathy (VTDR) in diabetes mellitus type 2 (T2DM) patients.Methods: Based on the baseline data of the Guangdong Shaoguan Diabetes Cohort Study conducted by the Zhongshan Ophthalmic Center (ZOC) in 2019, 2294 complete data of T2DM patients were randomly divided into a training set (n=1605) and a testing set (n=689). Independent risk factors were selected through univariate and multivariate logistic regression analysis on the training dataset, and a nomogram was constructed for predicting the risk of VTDR in T2DM patients. The model was evaluated using receiver operating characteristic (ROC) curves and area under the curve (AUC) in the training and testing datasets to assess discrimination, and Hosmer-Lemeshow test and calibration curves to assess calibration.Results: The results of the multivariate logistic regression analysis showed that Age (OR = 0.954, 95% CI: 0.940-0.969, p = 0.000), BMI (OR = 0.942, 95% CI: 0.902-0.984, p = 0.007), systolic blood pressure (SBP) (OR =1.014, 95% CI: 1.007-1.022, p = 0.000), diabetes duration (10-15y: OR =3.126, 95% CI: 2.087-4.682, p = 0.000; >15y: OR =3.750, 95% CI: 2.362-5.954, p = 0.000), and glycated hemoglobin (HbA1C) (OR = 1.325, 95% CI: 1.221-1.438, p = 0.000) were independent risk factors for T2DM patients with VTDR. A nomogram was constructed using these variables. The model discrimination results showed an AUC of 0.7193 for the training set and 0.6897 for the testing set. The Hosmer-Lemeshow test results showed a high consistency between the predicted and observed probabilities for both the training set (Chi-square=2.2029, P=0.9742) and the testing set (Chi-square=7.6628, P=0.4671).Conclusion: The introduction of Age, BMI, SBP, Duration, and HbA1C as variables helps to stratify the risk of T2DM patients with VTDR.

Tear meniscus height (TMH) is an important reference parameter in the diagnosis of dry eye disease. However, most traditional methods of measuring TMH are manual or semi-automatic, which causes the measurement of TMH to be prone to the influence of subjective factors, time consuming, and laborious. To solve these problems, a segmentation algorithm based on deep learning and image processing was proposed to realize the automatic measurement of TMH. To accurately segment the tear meniscus region, the segmentation algorithm designed in this study is based on the DeepLabv3 architecture and combines the partial structure of the ResNet50, GoogleNet, and FCN networks for further improvements. A total of 305 ocular surface images were used in this study, which were divided into training and testing sets. The training set was used to train the network model, and the testing set was used to evaluate the model performance. In the experiment, for tear meniscus segmentation, the average intersection over union was 0.896, the dice coefficient was 0.884, and the sensitivity was 0.877. For the central ring of corneal projection ring segmentation, the average intersection over union was 0.932, the dice coefficient was 0.926, and the sensitivity was 0.947. According to the evaluation index comparison, the segmentation model used in this study was superior to the existing model. Finally, the measurement outcome of TMH of the testing set using the proposed method was compared with manual measurement results. All measurement results were directly compared via linear regression; the regression line was y0.98x−0.02, and the overall correlation coefficient was r²0.94. Thus, the proposed method for measuring TMH in this paper is highly consistent with manual measurement and can realize the automatic measurement of TMH and assist clinicians in the diagnosis of dry eye disease.

With the widespread application of Implantable Collamer Lens (ICL) implantation surgery in the field of myopia correction, a comprehensive understanding of its potential complications, especially those related to intraocular pressure (IOP), becomes crucial. This article systematically reviews various complications that may lead to IOP elevation after ICL surgery. Firstly, common complications after ICL surgery, including residual viscoelastic, steroid response, and excessive vault of the ICL, are detailed, emphasizing their potential impact on intraocular pressure. Regarding residual viscoelastic, we delve into its direct relationship with postoperative elevated IOP and possible preventive measures. For steroid response, we stress the importance of timely adjustment of steroid therapy and monitoring intraocular pressure. Additionally, excessive vault of the ICL is considered a significant potential issue, and we elaborate on its mechanism and possible management methods. In further discussion, we focus on relatively rare complications such as Toxic Anterior Segment Syndrome (TASS), Urrets-Zavalia Syndrome (UZS), Pigment Dispersion Syndrome (PDS), and malignant glaucoma. For these relatively rare complications, this review thoroughly explores their potential mechanisms, emphasizes the importance of prevention, and provides guidance for early diagnosis and treatment. This is a comprehensible review that aims to offer eye care professionals a comprehensive understanding and effective management guidance for complications of elevated IOP after ICL surgery, ultimately providing optimal care for patients’ visual health.

Objective: The purpose of this study is to investigate the independent influencing factors of the transition from normal population to prediabetes, and from prediabetes to diabetes, and to further construct clinical prediction models to provide a basis for the prevention and management of prediabetes and diabetes.Materials and methods: The data for this study were based on clinical information of participants from the Health Management Center of Peking University Shenzhen Hospital. Participants were classified into normal group, prediabetes group, and diabetes group according to their functional status of glucose metabolism. Spearman’s correlation coefficients were calculated for the variables, and a matrix diagram was plotted. Further, univariate and multivariate logistic regression analysis were conducted to explore the independent influencing factors. The independent influencing factors were used as predictors to construct the full-variable prediction model (Full.model) and simplified prediction model (Simplified.model).Results: This study included a total of 5310 subjects and 22 variables, among which there were 1593(30%) in the normal group, 3150(59.3%) in the prediabetes group, and 567(10.7%) in the diabetes group. The results of the multivariable logistic regression analysis showed that there were significant differences in 9 variables between the normal group and the prediabetes group, including age(Age), body mass index(BMI), systolic blood pressure(SBP), urinary glucose(U.GLU), urinary protein(PRO), total protein(TP), globulin(GLB), alanine aminotransferase(ALT), and high-density lipoprotein cholesterol(HDL-C). There were significant differences in 7 variables between the prediabetes group and the diabetes group, including Age, BMI, SBP, U.GLU, PRO, triglycerides(TG), and HDL.C. The Full.model and Simplified.model constructed based on the above influencing factors had moderate discriminative power in both the training set and the test set.Conclusion: Age, BMI, SBP, U.GLU, PRO, TP, and ALT are independent risk factors, while GLB and HDL.C are independent protective factors for the development of prediabetes in the normal population. Age, BMI, SBP, U.GLU, PRO, and TG are independent risk factors, while HDL.C is an independent protective factor for the progression from prediabetes to diabetes. The Full.model and Simplified.model developed based on these influencing factors have moderate discriminative power.