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

作　　者：邱天爽[1] 高嵩[1] 康伟[1] 刘颖[2] 

机构地区：[1]大连理工大学电子与信息工程学院,大连116024 [2]大连医科大学附属第二医院,大连116023

出　　处：《生物医学工程学杂志》2009年第3期647-652,共6页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(30570475);教育部博士点基金资助项目(20050141025)

摘　　要：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.

关 键 词：脂肪肝超声图像 图像纹理分析 多分辨率分形布朗运动模型 遗传算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]