摘要
彩色多普勒超声是肾动脉狭窄的首选筛查工具,目前临床上主要依靠人工判别来诊断肾动脉狭窄,对操作者具有很强的依赖性。在肾动脉多普勒超声图像的基础上,通过提取肾动脉血流信号曲线、提取曲线特征,继而基于SVM构建分类器,对肾动脉血流信号曲线进行分类,取得了较高的分类精度,并与最大似然分类器进行了分类实验比较,在肾动脉狭窄的计算机辅助诊断方向进行了有意义的探索。
CDS（Color Doppler Sonography）is the first choice to screen RAS（Renal Artery Stenosis）.Currently,to diagnose RAS clinically mainly relies on manual evaluation,which has a great dependency on operators.Blood signal curves of the renal artery and features of classification are extracted from CDS images,and then classifier is created based on SVM to classify blood signal curves of the renal artery with a high accuracy of classification.Besides,the result of SVM classifier is compared with that of maximum likelihood classifier.It has positive effect for diagnosing RAS with computer-aided diagnosis.
出处
《计算机工程与应用》
CSCD
2013年第18期125-129,共5页
Computer Engineering and Applications
基金
国家自然科学基金(No.60971050)
关键词
多普勒超声
肾动脉血流信号曲线
支持向量机（SVM）
分类
Color Doppler Sonography（CDS）
blood signal curve of renal artery
Support Vector Machine（SVM）
classification
