人工智能(artificial intelligence，AI)在眼科领域的应用不断深入、拓展，目前在糖尿病性视网膜病变、白内障、青光眼以及早产儿视网膜病变在内的多种常见眼病的诊疗中逐渐成为研究热点。AI使医疗资源短缺、诊断标准缺乏、诊疗技术水平低下的现状得到改善，为白内障的诊疗开辟了一条“新赛道”。本文旨在综述AI在白内障诊疗中的应用现状、进展及局限性，为AI在白内障领域的进一步开发、应用及推广提供更多信息。
Artificial intelligence (AI) has been widely applied and promoted in ophthalmology, and has gradually become a research hotspot in the diagnosis and treatment of many common ophthalmopathies, including diabetic retinopathy, cataract, glaucoma, and retinopathy of prematurity. AI improves the shortage of medical care, the lack of diagnostic criteria and the low level of diagnosis and treatment technology, and explores a “new race track” for cataract diagnosis and treatment. The purpose of this article is to review the application status, progress and limitations of AI in the diagnosis and treatment of cataract, aiming to provide more information for further development, application and promotion of AI in the field of cataract.
白内障是世界范围内致盲的主要原因之一，占中低收入国家致盲病例的50%。随着人口老龄化程度的加深，到2050年中国白内障致盲病例预计达到2 000万。卫生支出占比低、医疗设备及眼科医生紧缺、筛查费用昂贵仍是中低收入国家无法开展大规模白内障筛查的主要原因。人工智能(artificial intelligence，AI)协助白内障诊断具有便捷、低成本、可远程进行等优点，有望减少甚至避免白内障致盲的发生。文章将对AI通过结合裂隙灯眼前节图像、眼底照片及扫频源光学相干层析图像进行白内障自动诊断等研究进行简要综述。
Cataract is a primary cause of blindness globally, particularly accounting for 50% of blindness cases in low- and middle- income countries. As the population ages, it is predicated that cataract blindness cases in China will rise to 20 million by 2050. However, low health expenditures, scarcity of medical equipment and ophthalmologists, and high screening costs continue to hinder mass cataract screening in these countries. Artificial intelligence(AI)-assisted cataract diagnosis offers significant advantages, including convenience, cost-effectiveness, and remote accessibility, potentially reducing or even eliminating cataract blindness. This review aims to concisely summarize the research on automatic cataract diagnosis utilizing AI, incorporating slit lamp images of anterior eye segment, fundus photographs, and swept source optical coherence tomography images.
近视防控已经上升到我国国家战略层面，高度近视引起的视神经病变会损害视功能，但在临床上常常被忽视。OCT可以非侵入、高分辨率、快速以及可重复地定量视网膜各层厚度，是评估高度近视相关视神经病变的有力工具。由于高度近视常合并视盘和盘周的改变，视神经纤维层厚度的定量常出现误差。近年来，学者开始聚焦于黄斑区神经节细胞复合体(ganglion cell complex,GCC)厚度的研究，但其在高度近视眼中的变化规律尚不统一。该文针对近年来高度近视眼黄斑区GCC的测量规范、诊断价值、变化规律等进行综述，以期提高眼科医师对高度近视视神经病变的重视和研究水平。
Myopia prevention and control has risen to the national strategic level in China. Optic neuropathy caused by high myopia can damage visual function, but it is often ignored in clinical practice Optical coherence tomography (OCT) characterized by non-invasiveness, high resolution, rapid, and repeatable quantifying the thickness of each layer in the retina has emerged as a powerful tool for evaluating high myopia related optic neuropathy. Due to the changes in and near the optic disc in high myopia, errors often occur in the quantification of the thickness of the optic nerve fiber layer. In recent years, researchers have gradually focused on the study of the thickness of ganglion cell complex (GCC), but the regularity of its changes in high myopia is not yet unified. This article reviews the measurement specifications, diagnostic values, and change rules of GCC in the macular region of high myopia in recent years, in order to improve the attention and research level of ophthalmologists on high myopia optic neuropathy.
眼睛由屈光系统和视觉神经系统两大部分构成，是人体最重要的感觉器官之一。眼部各组织的发育或功能异常都可能造成不同程度的视力损害。目前主要通过动物实验或体外细胞培养的方法探究眼病的病理生理机制和治疗手段，但上述两种方法都存在一定的局限性。体外细胞培养不能完全反映器官的形态、结构和生化特征，而动物模型的物种和遗传背景具有异质性。近年来，随着原代组织、胚胎干细胞、诱导多能干细胞衍生的体外三维结构类器官和器官微流控芯片技术的不断发展，构建出了与在体器官的结构、功能更为相似的器官克隆模型，能够提供更敏感、定量、规模化的表型分析，更好地应用于眼的发育、生理结构、疾病机制、个性化医学诊断和治疗方法等方面的研究。目前，眼科的微流控器官芯片与类器官技术在角膜、晶状体、泪腺、视网膜结构发育和疾病模型均展现出巨大的应用潜力。
The eye is composed of refractive system and visual nervous system. It is one of the most important sensory organs of the human body. The abnormal development or function of eye tissues may cause various degrees of visual impairment. At present, the pathophysiological mechanism and treatment of eye diseases are mainly explored through animal experiments and in-vitro cell culture. However, they are of certain limitations. The in-vitro cell culture cannot fully reflect the morphological, structural and biochemical characteristics of organs, whereas the animal models are heterogeneous of species and genetic background. In recent years, with the continuous development of in-vitro three-dimensional structure organoids and organ microfluidic organ-on-a-chip technology derived from primary tissues, embryonic stem cells and induced pluripotent stem cells, organ cloning models more similar to in vivo organs in terms of the structure and function have been constructed. These models can provide more sensitive, quantitative and large-scale phenotypic analysis, and can be better applied to the research of eye development, physiological structure, disease mechanism, personalized medical diagnosis and treatment. At present, microfluidic organ-on-a-chip and organoids technologies have shown great application potential in the structural development and disease models’ construction of cornea, lens, lacrimal gland and retina.
近年来，使用人工智能(artificial intelligence，AI)技术对临床大数据及图像进行分析，对疾病做出智能诊断、预测并提出诊疗决策，AI正逐步成为辅助临床及科研的先进技术。生物样本库作为收集临床信息和样本供科研使用的平台，是临床与科研的桥梁，也是临床信息与科研数据的集成平台。影响生物样本库使用效率及合理共享的因素有信息化建设水平不均衡、获取的临床及检验信息不完全、各库之间信息不对称等。本文对AI和区块链技术在生物样本库建设中的具体应用场景进行探讨，展望大数据时代智能生物样本库信息化建设的核心方向。
In recent years, artificial intelligence (AI) technology has been applied to analyze clinical big data and images and then make intelligent diagnosis, prediction and treatment decisions. It is gradually becoming an advanced technology to assist clinical and scientific research. Biobank is a platform for collecting clinical information and samples for scientific research, serving as a bridge between clinical and scientific research. It is also an integrated platform of clinical information and scientific research data. However, there are some challenges. First, clinical and laboratory information obtained is incomplete. Additionally, the information among different databases is asymmetric, which seriously impedes the information sharing among different Biobanks. In this article, the specific application scenarios of AI technology and blockchain in the construction of a Biobank were discussed, aiming to pinpoint the core direction of the information construction of an intelligent Biobank in the era of big data.
当下，我国眼科的发展存在失衡现象，大城市与农村及偏远地区在眼科相关诊疗设施水平、诊疗技术等方面存在巨大差异，仍需探寻新的智能诊疗模式以解决失衡问题。由于眼球是唯一可以直接观察人体血管和神经的器官，眼部可反映其他脏器的健康状态，部分眼科检查的医学图像可对眼部疾病做出诊断等特点，眼科开展人工智能(artificial intelligence，AI)具有独到的优势。此外，人工智能可在一定程度上提高跨时间空间传递信息的精准度及效率。人工智能在眼科及远程信息传递的优势为解决眼科发展失衡状况提供了助力。本文从眼科人工智能在眼科远程医疗相关应用的角度，主要分析并总结当下我国人工智能在眼科相关疾病远程医疗中的发展程度、所具优势以及存在问题，并讨论眼科人工智能在远程医疗的应用展望。
At present, there is an imbalance in the development of ophthalmology in China. There are huge differences in the level of ophthalmology related facilities, diagnosis and treatment technologies between big cities and rural, remote areas. New intelligent diagnosis and treatment models are still needed to solve the imbalance. Since the eye is the only organ that can directly observe the blood vessels and nerves of the human body, the eye can reflect the health status of other organs and diagnosis of eye diseases based on medical images of some ophthalmic examinations can be made as well as other characteristics. Therefore, the development of artificial intelligence in ophthalmology has unique advantages. In addition, artificial intelligence can improve the accuracy and efficiency of information transmission across time and space to a certain extent. The advantages of artificial intelligence in ophthalmology and telematics are helping to solve the imbalance in ophthalmology development. From the perspective of the application of ophthalmic artificial intelligence in telemedicine, this paper mainly analyzes and summarizes the development degree, advantages and existing problems of artificial intelligence in the telemedicine of ophthalmic diseases in China, and discusses the prospect of the application of ophthalmic artificial intelligence in telemedicine.
目的：评价欧堡Daytona 200度超广角激光扫描检眼镜检查近视患者眼底周边部视网膜病变的应用价值。方法：本研究为前瞻性病例研究，收集爱尔眼科医院要求行屈光手术的近视患者1 000例(2 000只眼)，分别进行小瞳下欧堡Daytona 200度超广角激光扫描检眼镜眼底检查和散瞳后三面镜检查，记录检查结果并进行比较分析。结果：通过欧堡Daytona 200度超广角激光扫描检眼镜检查发现有周边视网膜病变共230例(310只眼)，检出阳性率为15.50%；三面镜检查发现周边部视网膜病变共242例(322只眼)，检出阳性率为16.10%。两种检查方法对近视患者周边部视网膜病变检出阳性率具有很好的一致性(Kappa值0.8~1.0)。结论：欧堡Daytona 200度超广角成像系统为检查周边部视网膜病变提供了更省时高效的方法，在屈光手术前筛查视网膜周边部病变，具有广阔的临床应用前景。
Objectives: To evaluate the clinical value of peripheral retinal diseases in myopic patients examined by 200-degree ultra-wide field laser ophthalmoscope (Daytona). Methods: This was a prospective case-control study. We collected 1 000 myopic patients (2 000 eyes) who were scheduled to undergo refractive surgery in Aier Eye Hospital. They were examined by 200-degree ultra-wide field laser ophthalmoscope (Daytona) with non-mydriasis and three-mirror contact lens with mydriasis. The examination results were recorded and statistically analyzed. Results: A total of 230 cases (310 eyes) with peripheral retinopathy were found by 200-degree ultra-wide field laser ophthalmoscope (Daytona). The positive rate was 15.50%; 242 cases (322 eyes) with peripheral retinopathy were found by three- mirror contact lens, and the positive rate was 16.10%. The two methods were consistent in the detection of peripheral Retinopathy in myopic patients (the Kappa value is between 0.8 and 1.0). Conclusion: 200-degree ultra-wide field laser ophthalmoscope (Daytona) is an effective and rapid method for detecting peripheral retinopathy. It provides a broad clinical application prospects for peripheral retinopathy screening before refractive surgery.
目的：利用信息化手段，优化眼遗传病患者的随访途径，降低病历资料缺失率，助力临床检验科室高效运营。方法：通过态势分析法搜集需求，基于微信公众号平台“中山大学眼科医院小儿遗传”，搭建眼遗传病信息管理系统。根据是否使用眼遗传病信息管理系统、是否受到人员流动限制，将2017年7月1日—2023年11月30日来院进行基因检测的患者分为四组：传统组、传统+人流限制组、微信组和微信+人流限制组，通过χ2检验对眼遗传病信息管理系统进行性能评价。结果：源软件架设在阿里云电子政务平台的眼遗传病信息管理系统，通过加密通讯与医院网络交互。系统主要分为基因检测业务、数据管理和系统管理三大模块。使用该系统的患者或亲属可以在任意时间和地点，自主上传病历资料、签署知情同意书、查询基因检测报告，如有需要还能进行一对一的沟通实现长期随访。在此过程中，患者的临床信息实现数字化。研究共纳入10 662例患者对该系统进行性能评价，使用眼遗传病信息管理系统后，患者病历资料缺失率显著降低，由12.2%(传统+人流限制组)降至2.7%(微信+人流限制组)；患者二次来访率由最高的70%(传统组)降至最低的11.7%(微信组)；两类比较差异有统计学意义(P<0.001)。结论：眼遗传病信息管理系统的使用显著降低患者病历资料缺失率和眼遗传病患者的二次来访率。
Objective: To optimize the follow-up approach for patients with ophthalmic genetic diseases through informational technology, reduce the loss rate of cases, and facilitate the efficient operation of the clinical laboratory. Methods: Using the SWOT analysis method to collect requirements, ‘Pediatric Genetics of Zhongshan Ophthalmic Center’, an ophthalmic genetics information management system for ophthalmic genetic diseases was established on the Wechat public platform. Based on whether the ophthalmic genetic disease information management system was used and there were personnel mobility restrictions, patients who underwent genetic testing in the hospital for genetic testing from July 1, 2017, to November 30, 2023, were divided into four groups: traditional group, traditional+ lockdown group, Wechat+ lockdown group, and Wechat group. Te chi-square test was used to evaluate the performance of the ophthalmic genetic information management system. Results:The ophthalmic genetic disease information management system, which is based on open-source sofware and hosted on the Alibaba Cloud e-government platform, interacts with the hospital network through encrypted communication. Te system was divided into three modules: gene detection business, data management, and system management. By the system, patients or relatives can upload medical records, sign informed consent, inquire about genetic test reports at any time and anywhere, and conduct one-on-one communication to achieve long-term follow-up if necessary. In this process, the patient's clinical information was digitized. A total of 10,662 patients were included in the study to evaluate the performance of the system. The loss rate of cases was decreased from 12.2%to 2.7%, and the rate of second visits was reduced from 70% to 11.7%, which were statistically different, respectively (P< 0.001). Conclusion: Te application of the ophthalmic genetic information management system has signifcantly reduced the loss rate of cases and the rate of second visits in patients with ophthalmic genetic diseases.
因不同的眼部和神经性疾病，导致视觉功能严重受损，为低视力患者日常活动(如阅读及驾驶)及生活质量、心理健康带来严重的影响。人们对外界信息的感知主要来源于视觉，除威胁生命的重大疾病外，对人感官影响最大的损害当属视觉损伤。且随着人口日益老龄化，该问题日趋加重，低视力已成为目前全球范围内一个严重的公共卫生问题。目前，低视力康复发展面临着临床和科研的巨大挑战，要研发出一种能有效改善视觉功能，同时能兼顾多种功能的视障辅助技术，这需要医学、生物学、工程学、微电子学、计算机学等多学科的共同发展和相互合作。低视力康复通过为患者提供适宜的视障辅助技术，最大化利用患者的残余视力及视觉功能，改善与低视力相关的功能限制，有效改善其独立性和整体生活质量，使其独立生活、工作并融入社会成为可能。该文对经典的助视器、人工视觉(视觉假体/视觉感官替代设备)、经颅刺激及视觉生物反馈训练等视障辅助技术在低视力康复中的应用进展进行综述。
Patients with low vision are severely impaired in visual function due to different ocular and neurological disorders,which have a serious impact on their daily activities (such as reading and driving), quality of life and mental health.People's perception of external information mainly comes from vision. Expect for the life-threatening major diseases,visual damage has the greatest impact on people's senses. With the ageing of the population, the problem is getting worse, and low vision has become a serious public health problem in the world. Currently the development of low vision rehabilitation is facing a huge challenge in clinical and scientific research, to develop a visual impairment assistance technology that can effectively improve visual function while balancing multiple functions. It requires the joint development and cooperation of multiple disciplines such as medicine, biology, engineering, microelectronics, and computer science. Low vision rehabilitation provides patients with appropriate visual impairment assistance technology,maximizing the use of residual vision and visual function of patients, improving the functional limitations associated with low vision, effectively improving their independence and overall quality of life, and makes it possible for them to live, work and integrate into the society independently. This article reviews the progress in the application on visual impaired assistive technologies such as classic visual aids, artificial vision (visual prostheses/visual sensory replacement devices), transcranial stimulation and visual biofeedback training in low vision rehabilitation.
目的：比较轻、中、重度近视患儿之间的视觉功能的差异，探索虚拟现实下的短期可塑训练对近视视觉功能的改善效果。方法：选择2022年6月—2022年9月就诊于苏州大学附属儿童医院的6~16岁儿童102例，按照屈光度分为正常对照组、轻度近视组和中重度近视组，进行眼科常规检查和视知觉功能检查，并进行视觉短期可塑训练。结果：近视患儿存在立体视功能缺损，近视程度与精细立体视功能损害呈正相关，各组之间比较差异具有统计学意义(P<0.05)，部分患儿存在中心凹抑制。训练后，轻度近视组的中距离精细立体视功能得到改善，比较差异具有统计学意义(P<0.05)。结论：近视患儿存在立体视功能异常和中心凹抑制，且立体视功能的损害随着近视程度的增加而加重。轻度近视患儿部分精细立体视功能经过虚拟现实短期可塑训练可得到改善，而中重度近视患儿精细立体视功能改善不明显。
Objective: To compare the difference of visual function among children with myopia in different diopter, and explore the effect of short-term plastic training of virtual reality on visual function improvement. Methods: The 102 children aged 6-16 years who admitted to Children's Hospital of SoochowUniversity from June 2022 to September 2022 were recruited and divided into control group, mild myopia group and middle and high myopia group according to diopter. Routine ophthalmologic examination and visual perception function examination were carried out, and short-term plastic training was implemented. After the training, visual perception function examination was completed again. Results: There were significant differences in stereoscopic function defect at different distances among myopic children, a negative correlation between myopia and stereoscopic function was found. while there were several cases have foveal suppression. After training, the fine stereopsis at medium distance of the mild myopia group was significantly improved with significance statistical difference. Conclusions: Myopia can lead to the abnormality of stereopsis and foveal suppression in children. The defect of binocular visual function increases with the increase of myopia. Short term plastic training of virtual reality can partially improve the fine stereoscopic function of mild myopia children whileshowsnosigni ficanceimprovementof the fine stereoscopic function in middle and high myopia group.
