人工智能是对人类智能的模拟和拓展。基于深度学习的人工智能可以很好地利用图像的内在特征，如轮廓、框架等，来分析图像。研究人员通常利用图像来诊断眼底病，因此将人工智能应用于眼底检查是有意义的。在眼科领域，人工智能通过分析光学相干断层扫描图像、眼底照片和超宽视野图像，已经在检测多种眼底疾病上取得了类似医生的性能。它也已经被广泛应用于疾病进展预测。然而，人工智能在眼科的应用也存在一些潜在的挑战，黑盒问题是其中之一。研究人员致力于开发更多的可解释的深度学习系统，并确认其临床可行性。人工智能在最流行的眼底病中的最新应用、可能遇到的挑战以及未来的道路将一一阐述。

Artificial intelligence (AI) is about simulating and expanding human intelligence. AI based on deep learning (DL) can analyze images well by using their inherent features, such as outlines, frames and so on. As researchers generally diagnoses ocular fundus diseases by images, it makes sense to apply AI to fundus examination. In ophthalmology, AI has achieved doctor-like performance in detecting multiple ocular fundus diseases through optical coherence tomography (OCT) images, fundus photographs, and ultra-wide-field (UWF) images. It has also been widely used in disease progression prediction. Nonetheless, there are also some potential challenges with AI application in ophthalmology, one of which is the black-box problem. Researchers are devoted to developing more interpretable deep learning systems (DLS) and confirming their clinical feasibility. This review describes a summary of the state-of-the-art AI application in the most popular ocular fundus diseases, potential challenges and the path forward.

巨噬细胞样细胞(macrophage-like cells, MLC)指起源、功能与巨噬细胞类似的免疫细胞，包括小胶质细胞、玻璃体细胞及巨噬细胞。将en face OCT显示层面设置在视网膜表明即可观测到视网膜表明的 MLC(epiretinal MLC, eMLC)，随后利用ImageJ软件即可对细胞进行提取和量化。研究表明，eMLC在炎症情况下均可出现细胞募集及活化现象，但在不同眼底病中各具特点。在糖尿病视网膜病变、视网膜静脉阻塞等视网膜缺血缺氧性疾病中，eMLC密度越高，黄斑水肿可能越严重。此外，eMLC密度更高的视网膜静脉阻塞患者抗VEGF疗效更差，视力预后不佳，提示基于en face OCT的eMLC不仅可用于评估视网膜炎情况，而且还能充当提示疾病疗效及预后的标志物。在葡萄膜炎等免疫炎症性疾病中，en face OCT亦可观测到eMLC密度、形态等改变。白塞病葡萄膜炎患者视网膜血管渗漏程度与eMLC密度相关性强，故eMLC密度可充当无创评估视网膜血管渗漏程度的新指标。然而，目前提取和量化eMLC的方法及标准不统一，降低了各研究间的可比性。因此，亟需制定统一的操作规范和评估标准。此外eMLC 所代表的具体细胞类型及功能仍需进一步探究。未来，研究者可以利用en face OCT对眼底炎症地进行无创评估。基于en face OCT的eMLC还能作为基础研究与临床研究之间的桥梁，为揭示疾病的致病机制提供重要参考。

Macrophage-like cells (MLC) refer to immune cells that originate from and function similarly to macrophages, including microglia, hyalocytes, and macrophages themselves. By setting the display level of en face OCT to the retinal surface, epiretinal MLC (eMLC) can be observed and subsequently extracted and quantified using ImageJ software. Studies indicate that eMLC can exhibit cell recruitment and activation in inflammatory conditions, each displaying distinct characteristics in different retinal diseases. In ischemic and hypoxic retinal conditions such as diabetic retinopathy and retinal vein occlusion, higher densities of eMLC are associated with more severe macularedema. Moreover, patients with retinal vein occlusion showing higher eMLC densities tend to have poorer responses to anti-VEGF treatments and worse visual prognoses, suggesting that eMLC identified via en face OCT can be used not only to assess retinal inflammation but also as biomarkers for disease efficacy and prognosis. In immune-inflammatory diseases like uveitis, changes in eMLC density and morphology can also be observed through en face OCT. Inpatients with Beh?et's disease, a strong correlation exists between the degree of retinal vascular leakage and eMLC density, making eMLC density a potential non-invasive marker for assessing retinal vascular leakage. However, the current methods and standards for extracting and quantifying eMLC are not unified, significantly reducing comparability between studies. Therefore, there is an urgent need to establish uniform operational protocols and assessment standards. Furthermore, the specific cell types and functions represented by eMLC observed via en face OCT require further investigation. In the future, en face OCT could be utilized for non-invasive assessment of retinal inflammation. eMLC based onen face OCT could also serve as a bridge between basic research and clinical studies, providing valuable insights into the pathogenic mechanisms of diseases.