基于图像降阶的纹理特征挖掘方法在医学上的应用  

Medical application of texture feature mining based on image degradation

作　　者：于超[1] 王璐[2] 程道文[3] YU Chao;WANG Lu;CHENG Dao-wen(College of Humanities ＆ Information,Changchun University of Technology,Changchun 130122,China;School of Applied Technology,Changchun University of Technology,Changchun 130012,China;School of Basic Sciences,Changchun University of Technology,Changchun 130012,China)

机构地区：[1]长春工业大学人文信息学院,吉林长春130122 [2]长春工业大学应用技术学院,吉林长春130012 [3]长春工业大学基础科学学院,吉林长春130012

出　　处：《东北师大学报（自然科学版）》2018年第3期53-57,共5页Journal of Northeast Normal University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(11305019);吉林省高等教育学会高教科研项目(JGJX2016D208);吉林省教育科学规划项目(GH16560);吉林省科学技术研究项目(吉教科合字[2014]第642号)

摘　　要：借助数据挖掘方法在图像中的应用,提出一种利用图像降阶结合Apriori算法对医学图像纹理特征进行挖掘的模型.将医院信息系统(HIS)中病患特征与病患的医学图像纹理特征相融合,通过剪枝技术建立关联规则库,采用规则库中的规则对医学图像进行信息挖掘.实验结果表明,依靠该方法挖掘的关联规则能够很好地表达纹理,并对医疗辅助诊断起到一定的帮助.According to the method of data mining using in the image,this paper presents a model of medical image texture feature mining using image reduction combined with Apriori algorithm.The characteristics of patient information in hospital information system（HIS）are combined with the texture features of medical images of patients.The association rule database is built by pruning technology,and information mining is done by using rules in rule base.The experimental results show that the association rules based on this method can express the texture well and help the medical assistant diagnosis.

关 键 词：图像降阶 纹理特征 数据挖掘 关联规则 医学图像 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]