Department of Electrical and Computer Engineering, Queen’s university, Kingston, ON K7L 3N6, Canada.
IEEE Trans Biomed Eng. 2013 Jun;60(6):1608-18. doi: 10.1109/TBME.2013.2240300. Epub 2013 Jan 15.
This paper presents the results of a feasibility study to demonstrate the application of ultrasound RF time series imaging to accurately differentiate ablated and nonablated tissue. For 12 ex vivo and two in situ tissue samples, RF ultrasound signals are acquired prior to, and following, high-intensity ultrasound ablation. Spatial and temporal features of these signals are used to characterize ablated and nonablated tissue in a supervised-learning framework. In cross-validation evaluation, a subset of four features extracted from RF time series produce a classification accuracy of 84.5%, an area under ROC curve of 0.91 for ex vivo data, and an accuracy of 85% for in situ data. Ultrasound RF time series is a promising approach for characterizing ablated tissue.
本文介绍了一项可行性研究的结果，该研究旨在展示超声射频时间序列成像在准确区分消融和未消融组织方面的应用。对 12 个离体和 2 个原位组织样本进行了高强度超声消融前后的射频超声信号采集。在监督学习框架中，使用这些信号的空间和时间特征来对消融和未消融组织进行特征描述。在交叉验证评估中，从射频时间序列中提取的四个特征子集产生了 84.5%的分类准确率、离体数据的 ROC 曲线下面积为 0.91，以及原位数据的 85%准确率。超声射频时间序列是一种很有前途的用于描述消融组织的方法。
