【作者】 陈洪斌；

【导师】 王超；

【作者基本信息】 天津大学 ， 检测技术与自动化装置， 2009， 硕士

【摘要】 近年来,乳腺癌已经成为“女性健康的第一杀手”,对女性生命构成了巨大威胁,保乳手术是当前乳腺癌的主要治疗方式,决定保乳手术是否成功的关键因素之一,就是术中乳腺癌灶边缘界定的效果,即能否实时、准确地评价手术切缘,帮助施术医师在手术中合理选择组织切除范围,确保在手术结束前清除残留病灶。将生物电阻抗测量技术应用到术中乳腺癌灶边缘界定中,是本课题的重要研究内容。生物电阻抗测量技术(BIMT)是利用生物组织与器官的电特性及其变化,提取与人体生理、病理相关信息的一种无损伤检测技术。相对于病理切片而言,生物阻抗测量技术基本可以实现实时测量,大大缩短了等待时间。本课题重点研究乳腺癌组织与正常组织(腺体和脂肪组织)电特性差异,从组织频阻特性曲线中寻找特征参数,对乳腺组织进行识别。搭建组织阻抗的测量系统,测量得到组织的阻抗实部虚部值,绘制成频阻特性曲线。通过对组织特性曲线的分析,确定了特性曲线的分段一次拟合斜率和分段平均阻抗作为特征参数;实现训练集测试集的循环选取,因而实验的平均准确率可以正确反映样本特性;按照逐步接近术中乳腺癌灶边缘界定的实际情况的思想,设计了四种分类方式;利用支持向量机和主成分分析等数学方法实现了组织辨识。实验结果表明,40Hz~1.1MHz频段内的组织频阻特性具有最好的区分效果,对其进行29均分并提取连续的一次拟合斜率和平均阻抗作为特征参数,提供给支持向量机和主成分分析进行组织辨识,得到了较好的分类准确率。更多还原

【Abstract】 In recent years, breast cancer has become the first most commonly diagnosed types of cancer among women. The breast conservative operation is the major treatment. Its successful execution depends on several key points, one of which is the intraoperative margin assessment of breast cancer. It can help the surgeon judge the margin instantly and then choose the excising area reasonably. So that the remained focus could be cleaned in time. It can also shorten the waiting time and lighten patients’pain in partial mastectomy.It is the main purpose of this paper to apply Bio-Impedance Measuring Technology (BIMT) to intraoperative margin assessment of breast cancer. BIMT is a noninvasive measuring technology, the purpose of which is to extract physiological and pathological information by detecting the electrical properties of tissues and organs. BIMT is able to attain measurement result more quickly as opposed to pathological section, So it is been paid special attention by the researchers in clinical medicine areas.This paper focuses on researching the differences of electrical properties between breast cancer and normal breast tissues (mammary gland and adipose). The characteristic parameters searched from the frequency-resistance curve are studied to distinguish different tissues. The measurement system for breast tissues impedance is designed to get the real and imaginary part of tissues impedance values, and the frequency-resistance curves are drawn based on these impedance datum.Frequency-resistance slopes and resistance averages are found good enough to be used in the distinction of breast tissues. Train set and test set are cycle picking to make the average accuracies of the experiments can accurately reflect the sample characteristics. In order to get closer to the practical situation of intraoperative margin assessment of breast cancer, 4 different distinction modes are designed. Support Vector Machine (SVM) and Principal Component Analysis (PCA) are used in differentiate, which have a better performance.It is well shown that tissues impedance in the frequency range of 40Hz~1.1MHz has the best expression in distinguishment. The frequency range is split into 29 sections to attain the slopes and impedances averages, which are provided to SVM and PCA to differentiate tissues as characteristic parameters. The classification precision shows that this distinction method a worthwhile research of topic.更多还原