基于新疆地方性高发病肝包虫病CT图像灰度直方图特征检索方法的研究  

The Study of the CT Image Retrieval Method about the Xinjiang Local Liver Hydatid Disease which Has a Higher Incidence Based on the Image of Gray-level Histogram Features

作　　者：严传波[1] 木拉提.哈米提 陈建军[1] 胡彦婷[1] 孔德伟[2] 李莉[1] 周晶晶[1] 

机构地区：[1]新疆医科大学医学工程技术学院,乌鲁木齐830011 [2]新疆医科大学一附院影像中心,乌鲁木齐830054

出　　处：《科技通报》2013年第3期76-79,共4页Bulletin of Science and Technology

基　　金：国家自然科学基金项目(30960097);国家自然科学基金项目(81160182)

摘　　要：新疆地方性肝包虫病是新疆牧区发病率较高的传染性寄生虫病,严重影响牧区各族人民生活质量的提高。根据图像特征,选择合适距离算法,实现快速准确地图像检索,对辅助医生早期发现、诊断和治疗肝包虫病有重大意义。本文研究比较了使用肝包虫病CT医学图像灰度直方图特征进行图像检索时,不同距离算法的有效性。实验结果表明:对于肝包虫病医学图像的基于灰度直方图特征的图像检索,马氏距离算法与标准欧氏距离算法比其他距离算法较优。Xinjiang local liver hydatid is infectious parasitic disease in Xinjiang pastoral areas,which has a higher incidence. It is seriously affecting the health of people in pastoral areas.Based on the image features,selecting the appropriate distance algorithms to quickly and accurately retrieve the image,It has great significance that it can assist the doctors to early detect, diagnose and cure the liver hydatid.This paper compared the performance of different distance algorithms to retrieve the image when using the liver hydatid medical CT image＇s gray-level histogram features.The results show that： for the liver hydatid medical CT images retrieval based on gray-level histogram features,the performance of the Mahalanobis distance algorithm and standardized euclidean distance algorithm are superior to other distance algorithms.

关 键 词：肝包虫 图像检索 灰度直方图 距离算法 

分 类 号：R532.32[医药卫生—内科学] TP317.4[医药卫生—临床医学]