计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (10): 215-217.DOI: 10.3778/j.issn.1002-8331.2009.10.065

• 工程与应用 • 上一篇    下一篇

基于B超图像处理监测生物组织变性的方法

邹 孝1,钱盛友1,刘 畅1,孙福成2,张 激3   

  1. 1.湖南师范大学 物理与信息科学学院,长沙 410081
    2.上海交通大学 生物医学工程系,上海 200030
    3.深圳普罗惠仁医学科技有限公司,广东 深圳 518067
  • 收稿日期:2008-02-26 修回日期:2008-05-08 出版日期:2009-04-01 发布日期:2009-04-01
  • 通讯作者: 邹 孝

Method to check biological tissue denaturation based on mode B ultrasonic image processing

ZOU Xiao1,QIAN Sheng-you1,LIU Chang1,SUN Fu-cheng2,ZHANG Ji3   

  1. 1.College of Physics and Information Science,Hunan Normal University,Changsha 410081,China
    2.Department of Biomedical Engineering,Shanghai Jiaotong University,Shanghai 200030,China
    3.Shenzhen Pro-hifu Medical Technology Co Ltd,Shenzhen,Guangdong 518067,China
  • Received:2008-02-26 Revised:2008-05-08 Online:2009-04-01 Published:2009-04-01
  • Contact: ZOU Xiao

摘要: 提出基于B超图像的灰度和分形截距特征并结合支持向量机监测生物组织变性的方法。通过对高强度聚焦超声打击新鲜离体猪肉和猪肝组织前后获得的B超图像做数字减影,并提取图像特征和分类,找出生物组织变性凝固点。在此基础上,对大量实验数据处理后的统计特性和误差进行了分析,比较了不同特征参数的辨识效果。结果表明:综合图像的分形截距和灰度平均值特征并建立支持向量机,能够更好地监测HIFU治疗中生物组织是否变性。

关键词: 高强度聚焦超声, 组织变性, 分形截距, 支持向量机

Abstract: A method using Support Vector Machine(SVM) is presented to check biological tissue denaturation based on grey value and fractal intercept feature of mode B ultrasonic image.The digital subtraction is executed for mode B ultrasonic images obtained from fresh vitro pork or porcine liver before and after HIFU radiation,and then its image features are extracted and classified to find the concreting point of biological tissue.Through analyzing the statistical properties and errors of plentiful experimental data,the distinguishing effects of different characteristic parameters are compared.The results show that combining the fractal intercept with the average grey to construct SVM,the denaturation of biological tissue can be monitored better during HIFU therapy.

Key words: High Intensity Focused Ultrasound(HIFU), tissue denaturation, fractal intercept, Support Vector Machine(SVM)