基于多分辨率分形布朗运动模型及遗传算法的脂肪肝定量分析新方法

A Novel Method to Quantitatively Analyze the Fatty Liver Ultrasonic Images Based on Multiresolution Fractal Brownian Motion Model and Genetic Algorithm

医学超声图像是脂肪肝诊断的常用工具,为了使医生能够更准确地评价脂肪肝,需要建立一种指标体系对脂肪肝超声图像进行定量评价。本研究采用多分辨率分形布朗运动(Fractal brownian motion,FBM)模型及遗传算法(Genetic algorithm,GA)构造了一个定量评价方法,并获得脂肪肝医学超声图像定量评价体系。该体系对于辅助医生更加准确地诊断评价脂肪肝病变程度具有潜在的应用价值。

Medical ultrasonic imaging is frequently used for diagnosing the fatty liver disease. In order to help doctors diagnose fatty liver disease more precisely, we need to construct a quantitative assessment system, and in this paper, we propose a method to construct such system with the use of multiresolution fractal Brownian motion model and the genetic algorithm. In such a way, a set of standards can help doctors diagnose the degree of the fatty liver disease more precisely.