期刊文献+

基于支持向量机的高强度聚焦超声束损伤程度分类识别 被引量:2

Support Vector Machine Based High Intensity Focused Ultrasound Beam Lesion Degree Classification and Recognition
原文传递
导出
摘要 基于超声的组织损伤无损检测在高强度聚焦超声(HIFU)的临床推广与应用中具有重要意义。提出一种亚像素级方法将HIFU束损伤所导致的图像变化程度量化为相关距离。采用相关距离作为样本进行基于支持向量机(SVM)的HIFU束损伤程度分类训练,并对方法进行分类识别检验。实验结果表明,超声图像亚像素级相关分析矢量场可反映组织发生凝固性坏死的位置,基于SVM的分类算法可有效识别HIFU束损伤程度。 Ultrasound based tissue thermal lesion non-invasive detection is of great significance in high intensity focused ultrasound(HIFU) clinical application.In this paper,we propose a sub-pixel method to quantify the ultrasound image change caused by HIFU as correlation-distance.The support vector machine(SVM) was trained by using correlation distance as samples,and the recognition effect was tested.Results showed that sub-pixel cross-correlation vector field could reflect the ablation lesions position.SVM based classification method can recognize HIFU beam lesion degree effectively.
出处 《生物医学工程学杂志》 EI CAS CSCD 北大核心 2010年第5期978-983,共6页 Journal of Biomedical Engineering
基金 国家863重点项目资助(2007AA022000)
关键词 高强度聚焦超声 无损检测 支持向量机 High intensity focused ultrasound(HIFU); Non-invasive detection; Support vector machine(SVM);
  • 相关文献

参考文献7

  • 1WENG L, REID J M, SHANKAR O M, et al. Non-uniform ultrasound speckle phase distribution applied to scatterer spacing estimation[C]. Proceedings of the IEEE Ultrasonics Symposium, 1990, 3: 1593-1596.
  • 2WEAR K A, WAGNER R F, INSANA M F, et al. Application of autoregressive spectral analysis to cepstral estimation of mean scatterer spacing[J]. IEEE Trans on UFFC, 1993, 40 (1):50-58.
  • 3SEIP R, VANBAREN P, CAIN C A, et al. Noninvaslve real- time muhipoint temperature control for ultrasound phased array treatments[J]. IEEE Transaetions on Uhrasonies, Ferroelectries, and Frequeney Control, 1996,43 : 1063-1073.
  • 4BURGERS C J C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2:121-167.
  • 5VAPNIK V. The nature of statistical learning theory[M]. New York:Springer-Verlag, 1995.
  • 6KNERR S, PERSONNAZ L, DREYFUS G. Single-layer learning revisited: A stepwise procedure for building and training neural network[M]. Berlin, Neurocomputing: Algorithms, Architectures and Applications, NATO ASI, Springer-Verlag, 1990.
  • 7BOTTOU L, CORTES C, DENKER J S,et al. Comparison of classifier methods, A case study in handwritten digit reeognition[C]. ICPR94,1994, B:77-87.

同被引文献16

引证文献2

二级引证文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部