基于CT图像的肺部肿瘤自动定位系统  

Automated positioning system for pulmonary tumors in CT images

作　　者：朱建峰[1] 张建州[1] 蒋平[1] 周林[1] 

机构地区：[1]四川大学计算机学院,四川成都610065

出　　处：《计算机工程与设计》2006年第21期3970-3972,共3页Computer Engineering and Design

基　　金：国家自然科学基金项目(60371024)

摘　　要：系统自动检测出CT图像中的肺癌区域,并精确地勾画出肺癌的轮廓。应用核心的分割算法分割肺区,针对检测肺癌这个特定的临床任务所做的肺区轮廓修补操作也是必需的。根据周长,面积,直径,形状参数,平均CT值等特征,构造分类器来判别提取出的结节的性质,将最终定性为肺癌的区域的轮廓精确地勾画出来作为系统的输出结果。The system detects pulmonary tumors automatically in CT images, and draws the outline of the contour of pulmonary tumors precisely. A core segmentation method is developed for segmenting lung; however, modification is required for specific clinical task such as pulmonary tumor detection. Then, a classifier is constructed for determining the segmented pulmonary nodules using some features such as perimeter, area, diameter, and form factor, average CT value. The output of the system is the delineated-precisely contour of the area which is determined as tumor by the classifier.

关 键 词：CT 阈值分割 区域生长 特征提取 分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]