摘要
严重急性呼吸道综合症(SARS),又称“非典型肺炎”,是目前人类面临的一种严重危害生命和健康的新发传染病。利用PACS系统中的胸部数字X光(DX)正位图像,采用图像数据挖掘技术,设计并实现了SARS计算机辅助诊断系统。经过数据清理定位DX肺部图像的感兴趣区域,分割出双肺区域,提取特征参数,构造决策树,实现对SARS患者和一般肺炎胸部DX正位图像的分类。实验结果表明,检测SARS图像正确率达到70%以上。
Severe acute respiratory syndrome （SARS）, called ＂typical Pneumonia＂ in China, is a newly occurred fast transmittable infectious disease which badly endangers human＇s life and health, This paper designs and realizes a computer aided diagnosis SARS based on image data mining techniques for digital X-Ray images in picture archiving and communication system （PACS）. First, lung region of interest is located after data cleaning. Then lung region segmentation and feature parameters extraction are performed. The decision tree is constructed for discrimination of SARS and ＂typical Pneumonia＂. The experiment result shows that more than 70% SARS cases can be detected.
出处
《计算机工程》
EI
CAS
CSCD
北大核心
2006年第21期209-211,共3页
Computer Engineering
基金
广州医学院第二附属医院资助项目"医院信息综合管理系统"
关键词
图像数据挖掘
计算机辅助诊断
SARS
图像分割
决策树
hnage data mining
Computer aided diagnosis（CAD）
Severe acute respiratory syndrome（SARS）
Image segmentation
Decision tree
