乳腺肿瘤超声图像纹理特征分析.pdfVIP

陈秋霞等：乳腺肿瘤超声图像纹理特征分析 《激光杂志》2014 年第35 卷第3 期 LASERNAL(Vol.35.No.3.2014) 65 乳腺肿瘤超声图像纹理特征分析 1 1 2 1 陈秋霞 ，向军，刘奇 ，刘剑 ( 1.重庆医科大学附属第一医院设备处，重庆 400016； ) 2.四川大学电气信息学院医学信息工程系，成都 610065 提要：提取乳腺肿瘤超声图像的肿瘤区域，计算乳腺肿瘤图像的纹理特征参数，研究纹理特征与肿瘤良恶性的关 系。基于综合空间灰度共生矩阵计算11 个乳腺肿瘤超声图像的纹理特征参数，然后分别利用模糊C 均值和K-medoid 聚类算法对乳腺肿瘤进行良恶性判别，同时，通过重复实验找到判别肿瘤良恶性的最佳特征参数组合。实验结果表 明相关性、和方差、相关信息度量1 和相关信息度量2 四个特征参数组合的判别结果最好，达到了72.64% 。因此，纹理 特征在一定程度上能够反映良恶性乳腺肿瘤的区别，其对于鉴别乳腺肿瘤的良恶性是有效的。 关键词：乳腺肿瘤；纹理特征；聚类算法 中图分类号：TN244.8 文献标识码：A 文章编号：0253-2743 （2014 ）03-065-02 Textural Feature Analysis for Ultrasound Breast Tumor Images 1 1 2 1 CHEN Qiu-xia , XIANG Jun , LIU Qi , Liu Jian (1. Department of Equipment, the First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China; ) 2. Medical Information Engineering, College of Electrical Engineering and Information, Sichuan University, Chengdu 610065, China Abstract:To extract the tumor area of the breast tumors in ultrasonography, upon which calculate the textural features and study the relationship between textural features and pathological nature of the tumors. Eleven textural features are calculated based on the in- tegrated spatial gray level co-occurrence matrix, and the Fuzzy C-means and K-medoid algorithms are applied to differentiate the be- nign and the malignant breast tumors respectively. Meanwhile, the best combination of textural features is determined through repeat- ed experiment. It shows that the combination of feature correlation, sum variance, information me