目的：利用超高效液相色谱串联四极杆-静电场轨道阱高分辨质谱(ultra-high per formance liquid chromatography tandem quadrupole-electrostatic field orbitrap high resolution mass spectrometer, UHPLC- HRMS)代谢组学技术结合机器学习识别与糖尿病视网膜病变(diabetic retinopathy, DR)进展过程中的房水代谢差异，以寻找DR进展相关生物标志物。方法：本研究共纳入78例2型糖尿病(type 2 diabetes mellitus, T2DM)患者以及30名年龄性别匹配健康对照人群。使用UHPLC- HRMS检测所有患者及对照人群房水中的代谢物丰度，结合机器学习筛选T2DM和DR进展相关代谢物标志物并建立预测模型。结果：在校正混杂因素后，与健康人群对比1, 5-脱水山梨醇、硫酸十四烷基酯和N,N,N-三甲基-5-氨基戊酸在T2DM患者中表现出显著差异(均P < 0.05)；而N-乙酰色氨酸、亚油酰胺、油酰胺、棕榈酰胺、戊酸(游离脂肪酸(5:0)和琥珀酸与DR进展显著相关(均P < 0.001)。代谢通路分析表明，“缬氨酸、亮氨酸和异亮氨酸的生物合成”“精氨酸的生物合成”和“半胱氨酸及蛋氨酸代谢”是T2DM差异代谢途径。基于生物标志物的随机森林预测模型显示，差异代谢产物对T2DM和DR进展的预测准确率分别为81.3%和74%。结论：代谢组学结合机器学习方法有效揭示了T2DM及与DR进展相关的代谢特征，亚油酰胺和油酰胺有望成为DR进展的生物标志物，为DR的诊断和个体化治疗提供了新的可能性。

Objective: To identify aqueous humor metabolic profiles associated with the progression of type 2 diabetes mellitus (T2DM) and diabetic retinopathy (DR), aiming to discover potential biomarkers for DR progression. Ultra-high performance liquid chromatography tandem quadrupole-electrostatic field orbitrap high-resolution mass spectrometry (UHPLC-HRMS) will be utilized in conjunction with machine learning (ML) for comprehensive analysis. Methods: A total of 78 patients with T2DM and 30 age- and gender-matched healthy controls were included. UHPLC-HRMS was used to identify metabolites in the aqueous humor of all participants. ML was employed to screen for metabolites associated with T2DM and DR progression, and predictive models were established. Results: After adjusting for covariates, 1,5-anhydroglucitol, tetradecyl sulfate, and n,n,n-trimethyl-5-aminovaleric acid identified as significant indicators for T2DM compared to controls (all P < 0.05). N-acetyltryptophan, linoleamide, oleamide, palmitic amide, valeric acid(FFA(5:0), and succinic acid emerged as predictors for DR progression (all P < 0.001). Metabolic pathway analysis revealed that "valine, leucine and isoleucine biosynthesis", "arginine biosynthesis," and "cysteine and methionine metabolism" were the most enriched pathways for T2DM. Predictive models achieved R² values of 81.3%, and 74% for T2DM and DR progression, respectively. Conclusions: Metabolomic combined with ML effectively uncovered metabolic characteristics associated with T2DM and DR progression. Linoleamide and oleamide represent promising potential biomarkers for DR progression, offering new opportunities for diagnosis and personalized treatment of DR.

目的：探讨内镜下泪囊鼻腔吻合(endoscopic dacryocystorhinostomy, En-DCR)联合双管人工泪管植入(bicanalicular silicone tube intubation, BSTI)术治疗小泪囊型慢性泪囊炎的疗效。方法：回顾2020年7月—2023年3月在温州医科大学附属眼视光医院通过CT泪囊造影术(CT dacryocystography, CT-DCG)确诊的单眼小泪囊型慢性泪囊炎并接受手术的患者69例(69眼)，手术采取术中开放泪总管平面的En-DCR并联合BSTI术治疗。术后3个月取出人工泪管，通过术前和术后9个月随访资料，记录和分析了纳入患者的基本资料、手术治疗、治疗效果(包括解剖成功率和功能成功率)和并发症情况。结果：本研究最终纳入61例(61眼)患者，其中男21例、女40例，右眼33眼、左眼28眼。平均年龄为(55.31±12.28)岁(范围为27~75岁)。所有患者均顺利完成术中开放泪总管平面的En-DCR并联合BSTI术治疗。随访9个月，En-DCR的解剖成功率为80.33%(49/61)，功能成功率为75.41%(46/61)，在随访过程中未出现视力下降、眶内出血、感染扩散等并发症。结论：En-DCR联合BSTI术治疗小泪囊型慢性泪囊炎可取得较为满意疗效。

Objective: To evaluate the efficacy of endoscopic dacryocystorhinostomy (En-DCR) Combined with bicanalicular silicone tube intubation (BSTI) for the Management of Chronic dacryocystitis with Small Lacrimal sac. Methods: A total of 69 patients (69 eyes) with chronic dacryocystitis with small lacrimal sac diagnosed by CT dacryocystography (CT-DCG) treated with En-DCR combined with BSTI at the Eye Hospital of Wenzhou Medical University from July 2020 to March 2023 were reviewed. The surgery procedure exposed the plane of common canalicular, and followed by BSTI. The tube was removed 3 months after surgery. The basic data, surgical treatment, therapeutic effect (including anatomical and functional success rates) and complications of the included patients were recorded and analyzed through the follow-up data before and 9 months after surgery. Results: Ultimately, 61 patients (61 eyes) were included in this study—21 males and 40 females—with a distribution of 33 right eyes and 28 left eyes. The mean age was calculated at 55.31±12.28 years (range: 27 to 75 years). All patients underwent a successful En-DCR with exposed the plane of common canalicular and BSTI. At the nine-month follow-up, the anatomical success rate of En-DCR was 80.33%(49/61), the functional success rate was 75.41%(46/61). No complications such as visual impairment, intraorbital hemorrhage, or spread of infection occurred during the follow-up period. Conclusions: The combination of En-DCR and BSTI surgery for chronic dacryocystitis with small lacrimal sac can achieve a satisfactory therapeutic effect.

目的：探索和实践人工智能辅助诊断的闵行区视觉健康管理模式。方法：介绍闵行区人工智能辅助诊断的视觉健康管理模式；分析对比传统视觉健康管理模式和人工智能辅助诊断视觉健康管理模式下，社区视觉健康筛查情况，眼病发现、需转诊、复诊情况等；工作人员配置、眼科门诊接诊情况、居民眼病知识率和视觉健康服务满意情况等。结果：传统视觉健康管理模式和人工智能辅助诊断模式主要眼病（糖尿病视网膜病变、青光眼、年龄相关性黄斑变性、高度近视）发现率比较差异均有统计学意义（c²=954.03，P ＜0.01），需转诊率差异有统计学意义（c²=431.07，P ＜0.01）。人工智能辅助诊断管理模式与传统视觉健康管理模式的居民在青光眼的知晓率比较差异有统计学意义（c²=4.24，P＜0.05）。传统视觉健康管理模式和人工智能辅助诊断模式居民对视觉健康服务中的服务质量和服务时间的满意度比较差异有统计学意义（Z=-2.75，Z=-2.18，P ＜0.05）。结论：人工智能辅助诊断视觉健康管理模式，糖尿病视网膜病变、青光眼等主要眼病发现率高于传统模式，需转诊率降低，居民对青光眼的知晓率提升，在服务质量和服务时间上的居民满意度较高。基于人工智能辅助诊断的视觉健康筛查与管理模式值得本区其他社区的推广和应用。

Objective To explore and practice the visual health management mode of Minhang District . Methods Introduce the visual health management mode of AI-assisted diagnosis in Minhang District; analyze and compare the traditional visual health management mode and AI-assisted visual health management mode, community visual health screening projects and completion conditions, screening files, eye disease discovery , referral, actual referral and return ; analyze and compare the visual health management mode, staff allocation, ophthalmic outpatient reception, and the satisfaction of visual health service. Results The difference in the discovery rate of major eye diseases (Diabetic Retinopathy,Glaucoma,Age-related Macular Degeneration,High Myopia) between the traditional model and artificial intelligence-assisted diagnosis mode in both communities (c²=954.03, P<0.01), the referral rate (c²=431.07, P<0.01). The awareness of AI-assisted diagnosis management improved in glaucoma in the two modes was statistically significant (c²=4.24, P<0.05). Traditional model and artificial intelligence assisted diagnosis model of visual health service quality and service time is statistically significant (Z=-2.75, Z=-2.18, P<0.05). Conclusion The visual health screening and management mode based on AI-assisted diagnosis is worthy of the promotion and application in other communities in the region.

慢性中心性浆液性脉络膜视网膜病变(cCSC)以广泛的脉络膜视网膜异常为特征，包括脉络膜血管扩张及其引发的弥漫性视网膜色素上皮病变和浆液性视网膜脱离，常累及黄斑区，引起视功能损害。传统观点认为其可能由急性CSC演变而来，但近期研究显示两者在临床上存在明显差异。其病情反复、迁延，预后较差。随着光学相干断层扫描血管造影(OCTA)、超广角成像和en face重建成像等新多模式影像(MMI)技术的出现和人工智能及机器学习的发展，更多有意义的cCSC影像学特征不断出现。文章详细介绍了cCSC在眼底成像、眼底自发荧光(FAF)、光学相干断层扫描(OCT)、眼底荧光素血管造影(FFA)、吲哚菁绿血管造影和OCTA等影像技术中的表现，并探讨了人工智能在识别CSC分类及其OCT 生物标志物等方面的应用。不同影像技术在cCSC的诊断和研究中各有优势，如FAF可能是评估疾病进展及变化的有效手段，OCT可更直观地观察视网膜结构的改变，FFA是识别渗漏点的重要检查手段，而OCTA可能是评估脉络膜微循环的的最佳手段等。这些MMI研究进展为深入了解cCSC的病理生理机制及临床特征提供了重要线索，有助于提高诊断的准确性和效率，改善患者的预后和生活质量。

Chronic central serous chorioretinopathy (cCSC) is characterized by extensive retinochoroidal abnormalities. This includes difuse retinal pigment epitheliopathy and serous retinal detachment associated with choroidal vasodilatation, ofen involving the macula and cause visual impairment. It was originally considered that it might evolve from acute CSC, but recent studies have shown significant clinical differences between the two. It tends to recur, be prolonged, and have an unfavorable prognosis. With the advent of new multimodal imaging (MMI) techniques such as optical coherence tomography angiography (OCTA), ultra-wide-feld imaging, and en face reconstruction imaging, along with the advancement of artificial intelligence and machine learning, more significant cCSC imaging characteristics have been constantly emerging. Tis article provides a comprehensive overview of cCSC’s imaging features across various modalities, including fundus photography, fundus autofluorescence (FAF), optical coherence tomography (OCT), fuorescein angiography (FFA), indocyanine green angiography, and OCTA. It also explores the application of artifcial intelligence in identifying CSC classifications and OCT biomarkers. Different imaging techniques have their own advantages in the diagnosis and study of cCSC, such as FAF being an efective means to assess disease progression and changes, OCT providing a more intuitive observation of retinal structural changes, FFA being an important tool for identifying leakage points, and OCTA possibly being the best means to assess choroidal microcirculation. Tese MMI research advancements ofer crucial insights for clinicians, aiding in more accurate diagnosis and efective treatment, thereby potentially improving patient outcomes and quality of life.

目的：评估炎非感染性葡萄膜炎继发炎性脉络膜新生血管(inflammatory choroidal neovascularization, iCNV)的临床特征及眼底多模式影像表现。方法：采用回顾性观察性研究，采用眼底荧光素血管造影(fundus fluorescein angiography, FFA)、吲哚菁绿血管造影(Indocyanine green angiography, ICGA)、谱域相干光断层扫描(spectral domain optical coherence tomography, SD-OCT)联合光学相干断层扫描血管成像(optical coherence tomography angiography, OCTA)等多种眼底影像学方法，对纳入患者的眼底进行检查，分析非感染性iCNV的面积、分型、位置及形态等影像学特征与临床特征的关系。结果：研究共纳入39例患者，对48只患眼中的51处iCNV病灶进行了评估。纳入患者年龄为(35.28±13.62)岁。其中3例患眼出现多灶性CNV。SD-OCT显示92.16%(47/51)的iCNV为2型CNV，17.65%(9/51)的iCNV出现海绵征，13.72%(7/51)的iCNV伴有局灶脉络膜凹陷。ICGA造影期间，74.50%的iCNV病灶(38/51)伴有弱荧光病灶，25.49%的病例(13/51)显示脉络膜高通透性表现。OCTA enface图像显示iCNV形态多样，包括焦点状(15例，29.41%)、盘状/海扇状(16例，31.37%)、枯树状(9例，17.65%)、星状(9例，17.65%)及弥漫网状(2例，3.92%)。其中，枯树状及星状iCNV提示iCNV为非活动性(P＜0.01)。结论：非感染性iCNV与炎性病灶关系密切，在SD-OCT，ICGA上皆具特征性的影像表现。OCTA能直观地观察到iCNV的形态。这些多模式影像特征为临床医生提供了对于非感染性iCNV重要的鉴别诊断依据，有助于制定有效的诊疗方案。

Objective: To evaluate the clinical characteristics and multimodal imaging features of non-infectious inflammatory choroidal neovascularization (iCNV). Methods: In this study retrospective, observational study, multimodal imaging examinations, including fluorescein angiography (FFA), indocyanine green angiography (ICGA), spectral-domain optical coherence tomography (SD-OCT), and optical coherence tomography angiography (OCTA), were used to observe the morphology of non-infectious iCNV in patients diagnosed with uveitis. The area of iCNV, CNV types, CNV morphology and other imaging characteristics were further analyzed. Results: A total of 39 patients were included, with 48 affected eyes and 51 iCNV were identified. The average age of the included patients was 35.28±13.62 years. Among the affected eyes, 3 presented with multifocal CNV, and 92.16% of iCNV were classified as type 2 CNV. iCNV exhibited diverse morphologies, including focal-like pattern (15 cases, 29.41%),sea-fan pattern(16 cases, 31.37%), dead-tree pattern CNV(9 cases, 17.65%), stellar pattern (9 cases, 17.65%), and diffuse reticular (2 cases, 3.92%). Notably, tree-like and stellar pattern iCNV showed a significant correlation with non-active CNV (P < 0.01). Conclusions: Non-infectious iCNV is closely related to inflammatory lesions, exhibiting characteristic imaging features on SD-OCT and ICGA. OCTA allows for direct observation of the morphology of iCNV. These multimodal imaging characteristics provide important diagnostic criteria for clinicians, aiding in the formulation of effective treatment plans.

随着多模式影像技术的应用，年龄相关性黄斑变性(age related macular degeneration, AMD)的一种特殊亚型：表皮玻璃疣(cuticular drusen)被发现，其与AMD尤其是非渗出性AMD又称干性(dry)AMD进展密切相关。但目前聚焦于AMD合并表皮玻璃疣的多模式影像特点等的相关文献较少，因此研究和阐明表皮玻璃疣的多模式影像特点、与其他AMD亚型玻璃疣的鉴别诊断、病理生理机制、治疗方法等具有重要的临床意义。运用多模式影像可以看到表皮玻璃疣呈双眼对称的无数散在的大小均匀的黄色视网膜下结节，典型的“星空状”荧光素钠眼底血管造影(fundus fluorescein angiography, FFA)表现， 以及光学相干断 层成像(optical coherence tomography, OCT)中视网膜色素上皮(retinal pigment epithelium, RPE)和Bruch膜之 间的锯齿状隆起。AMD合并表皮玻璃疣患者的分布特点个体差异很大，容易与AMD其他亚型的玻璃疣混淆，需要与硬性玻璃疣、软性玻璃疣、大胶质玻璃疣、Sorsby眼底营养不良(Sorsby's fundus dystrophy , SFD) 等相鉴别。研究表明表皮玻璃疣具有遗传性的类似动脉粥样硬化的发病机制，与RPE分泌的大型脂蛋白颗粒的堆积密切相关。未来可能会有针对补体系统的药物用于延缓表皮玻璃疣相关病变的进展。文章就表皮玻璃疣的临床表现、多模式影像的典型特点、鉴别诊断、遗传学基础、病理生理学发病机制、 并发症以及临床诊疗策略进行综述。

With the application of multimodal imaging techniques, a specific subtype of age-related macular degeneration (AMD),
known as cuticular drusen, has been identified. This subtype is closely associated with the progression of AMD, particularly non-exudative AMD, also referred to as dry AMD. However, there is a scarcity of literature focusing on the multimodal imaging characteristics of AMD combined with cuticular drusen. Therefore, studying and elucidating the multimodal imaging features of cuticular drusen, its differential diagnosis from other AMD subtypes of drusen, pathophysiological mechanisms, and treatment methods holds significant clinical importance. Multimodal imaging reveals cuticular drusenas numerous, symmetrical, evenly sized, yellow subretinal nodules in both eyes, exhibiting a typical "stars-in-the-sky" appearance on fluorescein angiography (FFA) and zigzag elevations between the retinal pigment epithelium (RPE) and Bruch's membrane on optical coherence tomography (OCT). The distribution characteristics of AMD patients with cuticular drusen vary greatly among individuals and can easily be confused with drusen from other AMD subtypes, so the differentiation from hard drusen, soft drusen, large colloidal drusen, and Sorsby's fundus dystrophy (SFD) is necessary. Studies suggest that cuticular drusen have a genetic, atherosclerosis- like pathogenesis which closely related to the accumulation of large lipoprotein particles secreted by the RPE. Future therapies targeting the complement system maybe employed to delay the progression of cuticulardrusen-related lesions. This article reviews the clinical manifestations, typical multimodal imaging features, differential diagnosis, genetic basis, pathophysiological mechanisms, complications, and clinical management strategies of cuticulardrusen.

糖尿病视网膜病变(diabetic retinopathy, DR)作为糖尿病的一种常见并发症是导致工作年龄人群失明的主要原因。血糖变异性(glycemic variability, GV)指血糖波动的程度。最新研究表明，GV与糖尿病患者的代谢状况和微血管病变密切相关。该文综述了GV对DR的影响及其研究进展。GV是指血糖水平在高点和低点之间波动的不稳定状态，分为长期GV和短期GV。长期GV主要通过空腹血糖(fasting plasma glucose, FPG)、餐后血糖(postprandial plasma glucose, PPG)和糖化血红蛋白(glycated hemoglobin, HbA1c)评估，短期GV则通过血糖标准差(standard deviation, SD)、变异系数(coefficient of variation, CV)、低血糖指数(low blood glucose index, LBGI)等指标量化。研究表明，GV是糖尿病大管和微血管并发症的重要风险预测因子，与冠状动脉综合征、心肌梗死、脑卒中、糖尿病肾病、周围神经病变等密切相关。在DR方面，GV可能是其进展的风险因素，高GV会加剧氧化应激、炎症反应、内皮功能障碍和新生血管生成，从而促进DR的发展。治疗策略包括动态血糖监测系统、药物干预(如基础胰岛素、阿格列汀等)、合理饮食和运动等，这些方法可改善GV，降低并发症风险，提高患者预后和生活质量。

Diabetic retinopathy (DR) is a common complication of diabetes and is a leading cause of blindness in the working-age population. Glycemic variability (GV) refers to the degree of fluctuation in blood glucose levels. Recent studies have shown that GV is closely related to the metabolic status and microvascular complications in patients with diabetes. This article reviews the impact of glycemic variability (GV) on diabetic retinopathy (DR) and the latest research progress.GV is defined as the unstable state of blood glucose levels fluctuating between highs and lows, which is categorized into long-term GV and short-term GV. Long-term GV is mainly assessed through fasting plasma glucose (FPG), postprandial plasma glucose (PPG), and glycated hemoglobin (HbA1c). Short-term GV is quantified by indicators such as the standard deviation of blood glucose (SD), coefficient of variation (CV), and low blood glucose index (LBGI).Studies have shown that GV is an important risk predictor for both macrovascular and microvascular complications in diabetic patients, being closely associated with conditions such as coronary artery syndrome, myocardial infarction, stroke, diabetic nephropathy, and peripheral neuropathy. Regarding DR, GV is likely a risk factor for its progression. High GV can exacerbate oxidative stress, inflammatory responses, endothelial dysfunction, and neovascularization, thereby promoting the development of DR.Treatment strategies include continuous glucose monitoring systems, pharmacological interventions (such as basal insulin, alogliptin, etc.), as well as proper diet and exercise. These approaches can improve GV, reduce the risk of complications, and enhance patients' prognosis and quality of life.

CSNB是一组高度异质的遗传性视网膜疾病(inherited retinal disease, IRD)，主要由视网膜光感受器细胞和双极细胞间的信号传导障碍引发。其主要临床特征为静止性夜盲和暗适应功能障碍，常伴有早发性近视、眼球震颤、斜视和远视等症状，ERG在CSNB的诊断、分型及治疗指导中起着至关重要的作用。尽管CSNB发病率低，属于罕见病，但其真实发病率可能被低估，部分原因在于其症状轻微、眼底表现多不明显，且临床常忽视视网膜功能检查，导致较高的漏诊和误诊率。随着分子遗传学技术的进步，大量研究揭示了CSNB不同基因缺陷的致病机制，特别是与早发近视的关联机制，这些研究同也增加了对视网膜信号传导和近视发病机制的理解。然而，CSNB的基因治疗仍处于早期阶段。本综述旨在全面探讨CSNB的疾病谱，包括不同类型患者的临床表现、影像学和功能学表型特征，以及相关遗传学致病机制，并总结基因型与表型的关联。同时，综述最新研究成果与未来发展方向，旨在提高国内学者对CSNB的认识，为临床诊断和治疗提供参考，并为后续研究提供新思路。

Congenital Stationary Night Blindness (CSNB) represents a group of highly heterogeneous inherited retinal diseases (IRDs) primarily caused by impaired signal transmission between photoreceptor cells and bipolar cells in the retina. The main clinical features include stationary night blindness and dark adaptation dysfunction, often accompanied by early-onset myopia, nystagmus, strabismus, and hyperopia. Electroretinography (ERG) plays a crucial role in the diagnosis, classification, and therapeutic management of CSNB. Although CSNB is classified as a rare disease due to its low incidence, its true prevalence is likely underestimated, partly because of its mild symptoms, inconspicuous fundus manifestations, and frequent oversight of retinal function tests in clinical practice, leading to high rates of underdiagnosis and misdiagnosis. With advances in molecular genetics, extensive research has elucidated the pathogenic mechanisms of various genetic defects in CSNB, particularly those associated with early-onset myopia. These studies have also enhanced our understanding of retinal signal transduction and the pathogenesis of myopia. However, gene therapy for CSNB remains in its early stages. This review aims to comprehensively explore the disease spectrum of CSNB, including clinical manifestations, imaging and functional phenotypic characteristics across different subtypes, and associated genetic pathogenic mechanisms. We also summarize genotype-phenotype correlations, review the latest research advancements, and discuss future directions. By doing so, this review seeks to improve the understanding of CSNB among domestic researchers, provide guidance for clinical diagnosis and treatment, and offer new insights for future research.

“六要素，三个一”是眼底影像基础阅片工作中进行眼底疾病临床创新性研究的模式要点，即在眼底阅片过程中捕捉到1个异常的病例后，通过积累病例、提炼特征、文献检索、寻同查异，进而扩展到1组病例，最后通过思辨创新，提出或完善1种新的疾病或疾病表征。近二十年来，在此模式的指导下，团队在眼底疾病研究工作中取得了一些原创性的成果：比如息肉状脉络膜血管病变的认识及其在国人新生血管性年龄相关性黄斑变性中发病比例第一，提出点状内层脉络膜病变病灶国际分期和命名新亚型，年龄相关的吲哚菁绿血管造影晚期散在弱荧光点揭示潴留性视网膜色素上皮脱离的发病机制，发现急性黄斑神经视网膜病变是登革热患者视力下降的主要原因，在全球最大的持续性鳞状黄斑病变的病例系列中明确病灶层次等创新性成果。“六要素”框架规范眼底影像研究流程，强调研究过程的严谨性与渐进性，且多次循环后衍生发散出更多研究线索和思路，极大拓展研究深度和广度。“三个一”路径体现了研究的层次性，从个体现象(点)到群体规律(线)，最终构建疾病认知的立体网络(面)；指导眼底异常影像征象、罕见病、新病种研究，加速疾病谱系完善。以“六要素”为纲，以“三个一”为略，将继续推动眼底疾病临床研究的创新与突破。

The "6 Elements, 3 Ones" constitutes a methodological framework for conducting innovative clinical research of ocular fundus diseases in foundational fundus imaging interpretation. This model emphasizes: 1) identifying a single abnormal case during routine fundus evaluation; 2) systematically expanding this observation into a case series through case accumulation, feature extraction, literature review, and comparative analysis; and 3) ultimately proposing or refining novel disease entities or manifestations through critical thinking and innovation. Over the past two decades, guided by this paradigm, our research team has achieved several original breakthroughs in fundus imaging studies, including: establishing polypoidal choroidal vasculopathy as the predominant subtype of neovascular age-related macular degeneration in Chinese populations; proposing an international staging system and novel subtypes for punctate inner choroidopathy; elucidating the pathogenesis of retentional retinal pigment epithelial detachment through the sign of age-related scattered hypofluorescent spots on late-phase indocyanine green angiography; identifying acute macular neuroretinopathy as the primary cause of vision loss in dengue fever patients; and precisely localizing lesion in the world's largest case series of persistent placoid maculopathy. The "6 Elements" framework standardizes fundus disease research protocols, emphasizing methodological rigor and progressive investigation while generating multiple research trajectories through iterative cycles, thereby expanding both the depth and breadth of scientific inquiry. The "3 Ones" pathway embodies hierarchical research progression - transitioning from individual phenomena (point observations) to population-level patterns (linear correlations), ultimately constructing a multidimensional disease cognition network (planar integration). This approach guides investigations ranging from signs of common disease to rare disorders and novel disease entities, accelerating the refinement of disease taxonomies. By adhering to the "6 Elements" as the structural framework and implementing the "3 Ones" as the strategic pathway, we will continue to advance innovation and achieve breakthroughs in clinical fundus disease researches.

泪器疾病是一类常见的眼科疾病，其诊疗过程复杂，治疗方法精细，涉及多种临床数据及影像资料。现有研究表明，随着人工智能（artificial intelligence，AI）技术，尤其是机器学习和深度学习的发展，AI在泪器疾病的早期筛查、精确诊断和个性化治疗中展现了巨大的应用潜力。AI能够通过高效的图像分析、多模态数据融合及深度学习算法，提供更加精确的疾病识别和治疗方案，并且能够对患者的病情进行定期监测和动态调整，提升治疗效果。然而，其仍面临诸多挑战，如多模态数据融合的复杂性、模型泛化能力的局限以及实时预测和动态调整的需求等，需要通过持续的技术创新、算法优化和跨学科合作来实现。文章对当前AI在泪器疾病诊疗中的应用现状进行了全面梳理和总结，深入分析了AI技术在诊断与治疗中的优势与局限，特别强调了AI与新兴技术的结合在优化临床决策支持系统方面的重要性。通过分析现有的挑战与技术融合策略，文章提出了AI在泪器疾病诊疗中的发展方向，旨在为未来的研究者提供创新性的思路，为眼科领域的临床实践提供有价值的参考，助力泪器疾病的精准医疗和个性化治疗的发展。

Lacrimal disorders are common ophthalmic conditions characterized by complex diagnostic and treatment processes, involving intricate therapeutic approaches and diverse clinical and imaging data. Recent studies have indicated that with the advancements in artificial intelligence (AI) technologies, particularly in machine learning and deep learning, AI demonstrates significant potential in the early screening, accurate diagnosis, and personalized treatment of lacrimal disorders. AI has the ability to provide more precise disease identification and treatment strategies through efficient image analysis, multimodal data fusion, and deep learning algorithms. Additionally, it enables regular monitoring and dynamic adjustment of patients' conditions, improving treatment outcomes. However, several challenges persist, such as the complexity of multimodal data integration, limitations in model generalization capabilities, and the need for real-time prediction and dynamic adjustments, all of which necessitate continuous technological innovations, algorithm optimization, and interdisciplinary collaborations. This paper provides a comprehensive review of the current status of AI applications in the diagnosis and treatment of lacrimal disorders, analyzing the advantages and limitations of AI in clinical practice. It especially emphasizes the importance of integrating AI with emerging technologies to optimize clinical decision support systems. By addressing the existing challenges and exploring strategies for technological integration, this paper proposes future directions for the development of AI in lacrimal disorder diagnosis and treatment, aiming to offer innovative perspectives for future researchers and valuable references for clinical practice in the field of ophthalmology, ultimately contributing to the advancement of precision medicine and personalized treatment for lacrimal disorders.