[关键词]
[摘要]
近年来,人工智能(AI)的蓬勃发展促进了其在医疗保健领域的推广与应用,同时也促进了医疗保健技术的革新与进步,尤其是在图像识别领域发挥出了无可替代的作用。眼科疾病的诊断十分依赖图像识别,AI在眼前段疾病的诊治方面取得了令人瞩目的成果,如感染性角膜炎的分类、圆锥角膜的筛查、晶状体混浊程度的分级、白内障手术视频的自动分期、白内障术后屈光状态的预测、闭角型青光眼的诊断等。AI有望帮助解决目前临床存在的诸多难题,实现对疾病的早期诊治,但也存在着黑箱过程难以解释、缺少公共数据集、算法过于复杂等问题。本文概述了AI在眼前段疾病中的应用现状,分析目前存在的不足以及未来的发展前景。
[Key word]
[Abstract]
In recent years, the application of artificial intelligence(AI)has been greatly promoted in medical care, especially in the field of image recognition which has played an irreplaceable role in the diagnosis of ophthalmic diseases. AI has made remarkable achievements in the diagnosis and treatment of anterior segment diseases such as classification of infectious keratitis, screening of keratoconus, grading of lens opacity, automatic staging of cataract surgery videos, prediction of postoperative refraction status, and the diagnosis of primary angle-closure glaucoma. It is promising that AI could help solve many clinical problems and realize early diagnosis and treatment of diseases. However, there are still some challenges such as the ambiguity of black-box process, the absence of public data sets and the complexity of algorithms. In this paper, the current studies of AI applications in anterior segment diseases have been reviewed in detail. Also, the challenges and future directions of AI in ophthalmology have been proposed.
[中图分类号]
[基金项目]