一种新的描述二维医学图像相似度的方法

首都医科大学学报 ›› 2001, Vol. 22 ›› Issue (4): 318-320.

一种新的描述二维医学图像相似度的方法

许敏, 闫岩, 江久汇, 张建, 郭德成, 刘学宗

首都医科大学生物医学工程学院

收稿日期:2001-07-04 修回日期:1900-01-01 出版日期:2001-10-15 发布日期:2001-10-15

New Method to Analyze the Similarity between Two-dimensional Medical Images

Xu Min, Yan Yan, Jiang Jiuhui, Zhang Jian, Guo Decheng, Liu Xuezong

BME Department, Capital University of Medical Sciences

Received:2001-07-04 Revised:1900-01-01 Online:2001-10-15 Published:2001-10-15

摘要/Abstract

摘要： 通过提取2幅图像中的特征点的位置坐标,并进行标准化,构成2组二维向量,用比较2组向量相关性的方法分析它们的相关性,该相关性就表征了2幅图像间的相似度.同时提出一种基于特征点位置坐标的分析二维医学图像相似度的方法.使用该方法分析了5幅正常颌X线片,得到任意2幅图之间的相似度,并对影响相似度的因素作了分析,说明特征点的数目和选取方式对相似度影响较大,重复定点中的随机误差对相似度的影响很小.该方法能够定量地描述图像的相似度,并可以直接推广到分析3D医学图像的相似度.

关键词: 典型相关, 医学图像, X线片

Abstract: A new method is posed that analyzes the similarity between the 2D images based on the landmark positions. Get the coordinates of the landmarks and standardized them to make up two groups of vectors, and analyzed the correlation between them, which represented the similarity of the two images. Five cephalometric radiographs images were analyzed in this method and factors affecting the similarity were discussed. It indicated that the number of landmarks and the method of selection could influence the results remarkably but random error had little influence. This method can evaluate the similarity between the images quantitatively and can also be applied to the 3D images.

Key words: canonical correlation analysis, medical image, cephalometric radiographs

中图分类号:

许敏;闫岩;江久汇;张建;郭德成;刘学宗. 一种新的描述二维医学图像相似度的方法[J]. 首都医科大学学报, 2001, 22(4): 318-320.

Xu Min;Yan Yan;Jiang Jiuhui;Zhang Jian;Guo Decheng;Liu Xuezong . New Method to Analyze the Similarity between Two-dimensional Medical Images[J]. Journal of Capital Medical University, 2001, 22(4): 318-320.

[1]	冯健;罗述谦. 应用蠕虫模型自动分割医学图像的研究[J]. 首都医科大学学报, 2007, 28(3): 355-358.
[2]	冯连泽;吕凤萍;王卫;鲁厚祯;何滨. 国人成人正常心脏纤维支架微机图像研究[J]. 首都医科大学学报, 2000, 21(2): 97-100.
[3]	马斌荣;魏秉璋. 医学图像三维重构计算机系统及其在医学中的应用[J]. 首都医科大学学报, 1995, 16(2): 109-112.