机器学习在角膜屈光手术术前圆锥角膜筛查中的应用进展

Advance of screening keratoconus before refractive surgery with machine learning

近年来人工智能在图像识别、预测疾病预后等方面取得了重要进展。随着计算机技术的发展,人工智能在眼科领域的应用范围不断扩大。圆锥角膜筛查是确定屈光手术适应证、避免术后角膜扩张的重要手段,而传统诊断方法准确率较低,亚临床期圆锥角膜更加难以发现。机器学习作为一种实现人工智能的重要方法,为较为准确地识别圆锥角膜带来可能,成为近几年屈光领域的研究热点。本综述从机器学习在角膜屈光手术术前圆锥角膜筛查中常用的算法、角膜特征参数提取、模型预测效率等方面进行阐述。

Artificial intelligence(AI)has made important progress in image recognition and disease prognosis prediction in recent years.Along with the development of computer technology,the application scope of AI in the field of ophthalmology is expanding.Keratoconus screening is an important means to determine the indication of refractive surgery and avoid postoperative corneal ectasia,but the accuracy of traditional diagnostic methods is low,especially for subclinical keratoconus.Machine learning,a method to realize artificial intelligence,makes it possible to improve the accuracy of keratoconus screening,and has become a hotspot in the field of refractive surgery recently.The review has clarified the algorithms commonly used in keratoconus screening for refractive surgery,the extraction of corneal features,and the accuracy of model prediction.