一个用于眼底普查的图象处理系统

AUTOMATIC RETINAL IMAGE DIAGNOSIS SYSTEM FOR MASS HEALTH SCREENINGS

建立一个自动的眼底图象分析诊断系统 ,使得眼底改变由定性描述进入定量描述阶段。方法 :系统包括图象采集、图象归档、图象处理、血管网络参数测量以及基于AI与ANN结合的辅助诊断等。本文就该系统的软、硬件设计及功能、特点作了详细介绍。结果 :提出了一系列眼底图象定量分析的新参数及相应的测量新算法。结论 :系统功能齐全 ,精度高及可重复性好。

A computerized system was reported capable of automatically doing quantitative analysis of morphological, structural and optical modifications of retinal vessels. This system included hardware for image acuquisition and display and software for performing image archiving, image analysis, retinal vascular networks recognition and artificial intelligence. By clinical experiment, the effectiveness of this system was proved and some numerical index for classification the degree of retinal arteriosclerosis was put forward. The accuracy and reliability of the results, justified by their low variability, made feasible the standardization of quantitative parameters to be used both in the diagnosis and in the prognosis of systemic diseases, and also allowed prospective studies based upon them.