基于相似度测量的医学超声图像对比度增强  

Contrast enhancement of medical ultrasonic images based on homogeneity measurement

作　　者：陈文山[1] 汪天富[1] 林江莉[1] 李德玉[1] 饶莉[2] 唐红[2] 

机构地区：[1]四川大学生物医学工程系,四川成都610065 [2]四川大学华西医院心内科,四川成都610041

出　　处：《中国医学影像技术》2006年第9期1432-1434,共3页Chinese Journal of Medical Imaging Technology

基　　金：国家自然科学基金项目(60272060);教育部博士点基金(20030610032);教育部优秀青年教师项目(2003-355-2)。

摘　　要：目的探求一种基于相似度测量的医学超声图像对比度增强方法。方法本文在基于相似度测量的对比度增强方法的基础上,针对医学超声图像的特点,引入了局部模糊分形维数特征,改进了相似度和对比度变换因子的计算方法,同时提出了对比度增强系数的自适应选择方法,通过改变图像局部对比度增强图像。结果大量的实验结果表明处理后的图像对比度得到了明显的提高,同时背景和噪声未出现明显改变,组织细节信息保留完整,图像可读性增强。结论本文算法在增强图像对比度的同时能够有效地保留组织细节信息并抑制噪声过度增强,是一种有效的医学超声图像对比度增强方法。Objective To explore a method about contrast enhancement of medical ultrasonic images based on homogeneity measurement. Methods Contrast enhancement method based on homogeneity measurement was utilized to enhance the contrast of ultrasonic images. The local Fuzzy fraetal dimension was introdueed. The algorithms of homogeneity and the contrast transformation factor were modified. Meanwhile, the adaptive algorithm of the contrast enhance constant was proposed. Results The experimental results showed that the processed image could effectively suppress the background and noises, preserve details and enhance contrast. Conclusion Comparing to traditional methods, the improved algorithm prevails in preserving original image＇s detail without over-enhancing the noise. Thus, the proposed method gains efficiency for medical ultrasonic images.

关 键 词：相似度 对比度增强 医学超声图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]