颜佩,丁亚军,钱盛友,胡强,盛祎,邹孝.基于K均值聚类的组织损伤等级判定研究[J].电子测量与仪器学报,2017,31(3):468-473 |
基于K均值聚类的组织损伤等级判定研究 |
Research on biological tissue lesion level judgment based on K means clustering |
|
DOI:10.13382/j.jemi.2017.03.021 |
中文关键词: 高强度聚焦超声 灰度均值 小波系数均值 K均值聚类 组织损伤等级 |
英文关键词:high intensity focused ultrasound (HIFU) gray average the mean of the wavelet transform coefficient K means clustering biological tissue lesion level |
基金项目:国家自然科学基金(11474090,11174077)、湖南师范大学博士基金(130645)资助项目 |
|
Author | Institution |
Yan Pei | College of Physics and Information Science, Hunan Normal University, Changsha 410081, China |
Ding Yajun | 1. College of Physics and Information Science, Hunan Normal University, Changsha 410081, China;
2. Institute of Image Recognition & Computer Vision, Hunan Normal University, Changsha 410081, China |
Qian Shengyou | College of Physics and Information Science, Hunan Normal University, Changsha 410081, China |
Hu Qiang | College of Physics and Information Science, Hunan Normal University, Changsha 410081, China |
Sheng Yi | College of Physics and Information Science, Hunan Normal University, Changsha 410081, China |
Zou Xiao | College of Physics and Information Science, Hunan Normal University, Changsha 410081, China |
|
摘要点击次数: 2846 |
全文下载次数: 16879 |
中文摘要: |
利用高强度聚焦超声(HIFU)对新鲜离体猪肉组织进行辐照,可对猪肉组织造成3个等级程度的损伤。从B超图像处理方向出发,提出一种基于K均值聚类并结合双参数的组织损伤等级判定方法。通过B超仪器实时获取HIFU辐照前后的134例猪肉组织图像,并做预处理获得焦斑区域的减影图像。再提取减影图像的灰度均值和小波系数均值,利用K均值聚类的方法对猪肉样本组织的损伤等级进行分类处理。实验结果表明,灰度均值参数能较好地区分第2、3等级程度的损伤,小波系数均值能较好地区分第1、2等级程度的损伤,而基于K均值聚类并结合双参数的分类方法结合了前两者的优点,在组织损伤等级的总辨识率上分别提高了5.23%和3.43%,更能准确地判定组织的损伤等级,便于临床医生客观地监控HIFU治疗过程,对提高HIFU疗效有实际意义。 |
英文摘要: |
High intensity focused ultrasound (HIFU) can irradiate fresh pork in vitro, which causes 3 degrees of lesion of pork tissue. From the aspects of B mode ultrasound image processing, the research on biological tissue lesion level judgment based on K means clustering and combined with double parameters is proposed in this paper. Real time B mode ultrasound images of 134 pork tissues before and after HIFU irradiation can be obtained by B ultrasonic instrument, and they are preprocessed to get digital subtraction images of the focal spot area. Then the gray average and the mean of the wavelet transform coefficient of these digital subtraction images can be extracted. Meanwhile, the pork tissue samples can be classified by K means clustering. The results show that gray average can distinguish the second and the third level of tissue lesion more effectively, and the mean of the wavelet transform coefficient can distinguish the first and the second level of tissue lesion more effectively. However, the method based on K means clustering and combined with double parameters is equipped with the advantages of the two former. And compared the two formers, this method improves the recognition rate of tissue lesion level by 5.23% and 3.43% respectively. And it can judge the lesion level of the pork tissue more accurately. The method can help clinicians to monitor the HIFU treatment process objectively, and it has practical significance to improve the HIFU therapeutic effect. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|