OBJECTIVE: This study aimed to quantitatively evaluate optic nerve head and retinal vascular parameters in children with hyperopia in relation to age and spherical equivalent refraction (SER) using artificial intelligence (AI)-based analysis of colour fundus photographs (CFP).
METHODS: This cross-sectional study included 324 children with hyperopia aged 3-12 years. Participants were divided into low hyperopia (SER+0.5 D to+2.0 D) and moderate-to-high hyperopia (SER≥+2.0 D) groups. Fundus parameters, such as optic disc area and mean vessel diameter, were automatically and quantitatively detected using AI. Significant variables (p<0.05) in the univariate analysis were included in a stepwise multiple linear regression.
RESULTS: Overall, 324 children were included, 172 with low and 152 with moderate-to-high hyperopia. The median optic disc area and vessel diameter were 1.42 mm2 and 65.09 µm, respectively. Children with high hyperopia had larger superior neuroretinal rim (NRR) width and larger vessel diameter than those with low and moderate hyperopia. In the univariate analysis, axial length was significantly associated with smaller superior NRR width (β=-3.030, p<0.001), smaller temporal NRR width (β=-1.469, p=0.020) and smaller vessel diameter (β=-0.076, p<0.001). A mild inverse correlation was observed between the optic disc area and vertical disc diameter with age.
CONCLUSIONS: AI-based CFP analysis showed that children with high hyperopia had larger mean vessel diameter but smaller vertical cup-to-disc ratio than those with low hyperopia. This suggests that AI can provide quantitative data on fundus parameters in children with hyperopia.

Fundus imaging plays a pivotal role in diagnosing retinal and choroidal diseases. Optical coherence tomography angiography (OCTA), by capturing signals to reconstruct vascular structures, offers a clear depiction of retinal vasculature with notable advantages such as rapid scanning and non-invasiveness. Although OCTA, due to its underlying principles, cannot dynamically assess vascular function, exploring its future applications and potential to eventually replace traditional fundus angiography remains a key focus in the medical community. OCTA provides multiple parameters that conventional fundus angiography cannot obtain. With the expanding coverage area of OCTA scans and improvements in artifact elimination, the detection rate of various retinal and choroidal diseases has significantly increased, making the widespread clinical application of OCTA an inevitable trend. Although ultra-widefield OCTA cannot yet fully replace angiography in clinical practice, with continued clinical practice, expanded clinical research, and ongoing technological innovation, OCTA is expected to gradually replace fundus angiography in the future.
眼底影像学在视网膜和脉络膜疾病的诊断中发挥着关键作用。相干光层析血管成像术（OCTA）通过采集信号重建血管结构，能够清晰地展示视网膜血管情况，具备扫描速度快和无创性等显著优势。尽管由于检测原理限制，OCTA无法动态评估血管功能，但探讨OCTA未来应用的发展趋势及其是否能最终替代眼底血管造影术，仍是当前医学界关注的焦点。OCTA因其能够提供传统眼底血管造影术无法获取的多种参数，且随着OCTA检查结果眼底覆盖面积的扩大及伪影消除能力的提升，其在多种视网膜和脉络膜疾病的识别率已显著提高，OCTA在临床上的广泛应用已是大势所趋。尽管目前超广角OCTA在临床应用中还不能全面替代血管造影术，但随着临床实践的深入、临床研究的扩展以及技术的持续创新，OCTA在未来有望逐步替代眼底血管造影术。.

Artificial intelligence (AI) has demonstrated revolutionary potential and wide-ranging applications in the comprehensive management of fundus diseases, yet it faces challenges in clinical translation, data quality, algorithm interpretability, and cross-cultural adaptability. AI has proven effective in the efficient screening, accurate diagnosis, personalized treatment recommendations, and prognosis prediction for conditions such as diabetic retinopathy, age-related macular degeneration, and other fundus diseases. However, there is a significant gap between the need for large-scale, high-quality, and diverse datasets and the limitations of current research data. Additionally, the black-box nature of AI algorithms, the acceptance by clinicians and patients, and the generalizability of these algorithms pose barriers to their widespread clinical adoption. Researchers are addressing these challenges through approaches such as federated learning, standardized data collection, and prospective trials to enhance the robustness, interpretability, and practicality of AI systems. Despite these obstacles, the benefits of AI in fundus disease management are substantial. These include improved screening efficiency, support for personalized treatment, the discovery of novel disease characteristics, and the development of precise treatment strategies. Moreover, AI facilitates the advancement of telemedicine through 5G and the Internet of Things. Future research should continue to tackle existing issues, fully leverage the potential of AI in the prevention and treatment of fundus diseases, and advance intelligent, precise, and remote ophthalmic services to meet global eye health needs.
人工智能（AI）在眼底病全程管理中展现出革新价值与广泛应用潜力，但也面临临床转化、数据质量、算法解释性、跨文化适应性等挑战。AI在糖尿病视网膜病变、年龄相关性黄斑变性等眼底病中，实现高效筛查、精确诊断、个性化治疗建议及预后预测。然而，AI对大规模、高质量、多样化的数据集需求与现有研究数据局限性之间的矛盾，以及黑箱模型的可解释性问题、医生与患者接受度、算法普适性等挑战，阻碍了其在眼科临床的广泛普及。为应对这些挑战，研究者们正探索采用联邦学习、标准化数据收集、前瞻性试验等方法，提升AI系统的稳健性、可解释性和实用性。尽管存在挑战，AI在眼底病管理中的优势显著，包括提升筛查效率、辅助个性化治疗、揭示疾病新特征及制定精准治疗策略，并通过5G、物联网等技术推动远程医疗发展。未来研究应继续解决现存问题，充分发挥AI在眼底病防治中的潜力，推动眼科服务迈向智能化、精准化、远程化，以满足全球眼健康需求。.

BACKGROUND: Glaucoma is a worldwide eye disease that can cause irreversible vision loss. Early detection of glaucoma is important to reduce vision loss, and retinal fundus image examination is one of the most commonly used solutions for glaucoma diagnosis due to its low cost. Clinically, the cup-disc ratio of fundus images is an important indicator for glaucoma diagnosis. In recent years, there have been an increasing number of algorithms for segmentation and recognition of the optic disc (OD) and optic cup (OC), but these algorithms generally have poor universality, segmentation performance, and segmentation accuracy.
METHODS: By improving the YOLOv8 algorithm for segmentation of OD and OC. Firstly, a set of algorithms was designed to adapt the REFUGE dataset\'s result images to the input format of the YOLOv8 algorithm. Secondly, in order to improve segmentation performance, the network structure of YOLOv8 was improved, including adding a ROI (Region of Interest) module, modifying the bounding box regression loss function from CIOU to Focal-EIoU. Finally, by training and testing the REFUGE dataset, the improved YOLOv8 algorithm was evaluated.
RESULTS: The experimental results show that the improved YOLOv8 algorithm achieves good segmentation performance on the REFUGE dataset. In the OD and OC segmentation tests, the F1 score is 0.999.
CONCLUSIONS: We improved the YOLOv8 algorithm and applied the improved model to the segmentation task of OD and OC in fundus images. The results show that our improved model is far superior to the mainstream U-Net model in terms of training speed, segmentation performance, and segmentation accuracy.

UNASSIGNED: This study investigated the distribution of fundus tessellation density (FTD) in a Chinese pediatric population and its potential in reflecting early myopic maculopathy (tessellated fundus).
UNASSIGNED: Participants were enrolled from kindergartens, primary schools, and middle schools, with cluster sampling in Shanghai, China. A series of ophthalmic examinations was conducted. Based on fundus photograph, FTD was quantitatively assessed using an artificial intelligence algorithm, and tessellated fundus was diagnosed by well-trained ophthalmologists.
UNASSIGNED: A total of 14,234 participants aged four to 18 years were included, with 7421 boys (52.1%). Tessellated fundus was observed in 2200 (15.5%) participants. The median of FTD was 0.86% (range 0.0-42.1%). FTD increased with age and axial length. In the logistics regression, larger FTD was independently associated with tessellated fundus (P < 0.001). The area under curves of receiver operating characteristic curve for categorizing tessellated fundus using FTD was 0.774, and the cutoff point of FTD was 2.22%.
UNASSIGNED: The density of fundus tessellation was consistent with the severity of myopia. FTD could help diagnose the early stage of myopic maculopathy, tessellated fundus, providing a new pattern for myopia screening and detection of early myopic fundus changes.
UNASSIGNED: Quantification of fundus tessellation with artificial intelligence could help detect early myopic maculopathy.

Degenerative fundus disease encompasses a spectrum of ocular diseases, including diabetic retinopathy (DR) and age-related macular degeneration (AMD), which are major contributors to visual impairment and blindness worldwide. The development and implementation of effective strategies for managing and preventing the onset and progression of these diseases are crucial for preserving patients\' visual acuity. Melatonin, a neurohormone primarily produced by the pineal gland, exhibits properties such as circadian rhythm modulation, antioxidant activity, anti-inflammatory effects, and neuroprotection within the ocular environment. Furthermore, melatonin has been shown to suppress neovascularization and reduce vascular leakage, both of which are critical in the pathogenesis of degenerative fundus lesions. Consequently, melatonin emerges as a promising therapeutic candidate for degenerative ocular diseases. This review provides a comprehensive overview of melatonin synthesis, its localization within ocular tissues, and its mechanisms of action, particularly in regulating melatonin production, thereby underscoring its potential as a therapeutic agent for degenerative fundus diseases.

OBJECTIVE: In this study we investigated the efficacy of short-term intravitreal injections of anti-vascular endothelial growth factors (anti-VEGF) in treating traumatic submacular hemorrhage.
METHODS: A total of 115 patients were diagnosed with submacular hemorrhage between 2018 and 2022 at Shenzhen Eye Hospital. In a retrospective analysis, we examined 13 of these patients who presented with submacular hemorrhage and choroidal rupture due to ocular trauma. Eight patients were treated with intravitreal anti-VEGF injection and 5 with oral drugs. We systematically analyzed changes in their ocular conditions pre and post-treatment. The evaluations encompassed best-corrected visual acuity (BCVA), optical coherence tomography, fundus fluorescein angiography, and retinal imaging.
RESULTS: The 13 patients diagnosed with submacular hemorrhage comprised of 10 males and 3 female, with their age ranging between 27 and 64 years, with an average age of 38.1 years (standard deviation [SD]: 11.27). A statistically significant reduction in central foveal thickness (CFT) was observed following intravitreal injections of anti-VEGF drugs (P = 0.03). In control group, the CFT was reduced without statistical significance (P = 0.10). The BCVA of the patients in treatment group improved significantly from 1.15 (SD: 0.62. Range: 0.4-2) to 0.63 (SD: 0.59. Range: 0.1-1.6), indicating an average increase of 4.13 lines (SD: 3.36. Range: 0-9) as measured by the visual acuity test using an eye chart (P = 0.01). The difference between baseline visual acuity and final visual acuity was not statistically significant in control group (P = 0.51).
CONCLUSIONS: Short-term administration of anti-VEGF drugs exhibited significant efficacy in reducing submacular hemorrhage following ocular trauma and enhancing visual acuity.

To define the characteristics of fundus manifestations in patients after SARS-CoV-2 infection with multimodal imaging techniques. This is a retrospective multicenter and multimodal imaging study including 90 patients. All patients with a visual complaint occurring immediately after SARS-CoV-2 infection were referred to six clinics between December 2022 and February 2023. Demographic information and the temporal relationship between SARS-CoV-2 infection and visual symptoms were documented. The characteristics of the fundus lesions were evaluated using multimodal imaging. Ninety patients from six hospitals were included in this study, including 24 males (26.67%) and 66 (73.33%) females. Seventy-eight patients (86.66%) (146 eyes) were diagnosed with Acute Macular Neuroretinopathy (AMN). The AMN patients were primarily young women (67.95%). Sixty-eight patients (87.18%) had AMN in both eyes. Thirty-eight eyes (24.36%) included Purtscher or Purtscher-like lesions. optical coherence tomography and infrared retinal photographs can show AMN lesions well. Eleven cases were diagnosed with simple Purtscher or Purtscher-like retinopathy (2 cases, 2.22%), Vogt‒Koyanagi‒Harada (VKH) syndrome or VKH-like uveitis (3 cases, 3.33%), multiple evanescent white-dot syndrome (MEWDS) (2 cases, 2.22%), and rhino-orbital-cerebral mucormycosis (ROCM) (5 cases, 5.56%). After SARS-CoV-2 infection, diversified fundus lesions were evident in patients with visual complaints. In this report, AMN was the dominant manifestation, followed by Purtscher or Purtscher-like retinopathy, MEWDS, VKH-like uveitis, and ROCM.

OBJECTIVE: To identify risk factors influencing visual outcomes in patients with pathological myopia-associated choroidal neovascularization (PM-CNV) following intravitreal injections of conbercept.
METHODS: A total of 86 eyes from 86 patients received intravitreal conbercept in a 1 + PRN regimen. After the initial injection, patients were followed for 12 months. They were categorized into two groups based on their 12-month visual acuity change: those who achieved greater than a one-line improvement in BCVA (improved group; n = 65) and those who experienced a one-line or lesser improvement or a decrease in BCVA (non-improved group; n = 21).
RESULTS: Over the 12-month period, the mean BCVA in the improved group significantly improved from 0.82 to 0.41 LogMAR. In the non-improved group, BCVA changed from 1.24 to 1.09 LogMAR. Similarly, the mean CRT decreased from 426.21 μm at baseline to 251.56 μm at 12 months in the improved group, and from 452.47 to 382.45 μm in the non-improved group. Multivariable logistic regression analyses revealed that older age (OR 1.287; 95% CI 1.019-1.625; P = 0.034), poorer baseline BCVA (OR 6.422; 95% CI 1.625-25.384; P = 0.008), the presence of subfoveal CNV (OR 4.817; 95% CI 1.242-18.681; P = 0.023), and organized interlacing patterns of CNV morphology (OR 5.593; 95% CI 1.397-22.392; P = 0.015) emerged as independent risk factors correlated with worsened visual prognosis following intravitreal conbercept injections.
CONCLUSIONS: Conbercept demonstrates significant efficacy and safety in treating PM-CNV. Key factors influencing visual recovery post-treatment include older age, poorer baseline BCVA, the presence of subfoveal CNV, and organized interlacing patterns of CNV morphology.

Fundus neovascularization diseases are a series of blinding eye diseases that seriously impair vision worldwide. Currently, the means of treating these diseases in clinical practice are continuously evolving and have rapidly revolutionized treatment opinions. However, key issues such as inadequate treatment effectiveness, high rates of recurrence, and poor patient compliance still need to be urgently addressed. Multifunctional nanomedicine can specifically respond to both endogenous and exogenous microenvironments, effectively deliver drugs to specific targets and participate in activities such as biological imaging and the detection of small molecules. Nano-in-micro (NIM) delivery systems such as metal, metal oxide and up-conversion nanoparticles (NPs), quantum dots, and carbon materials, have shown certain advantages in overcoming the presence of physiological barriers within the eyeball and are widely used in the treatment of ophthalmic diseases. Few studies, however, have evaluated the efficacy of NIM delivery systems in treating fundus neovascular diseases (FNDs). The present study describes the main clinical treatment strategies and the adverse events associated with the treatment of FNDs with NIM delivery systems and summarizes the anatomical obstacles that must be overcome. In this review, we wish to highlight the principle of intraocular microenvironment normalization, aiming to provide a more rational approach for designing new NIM delivery systems to treat specific FNDs.