| 基于边界特征的乳腺肿瘤超声图像识别 |
| |
| 引用本文： | 张科宏,彭玉兰,李德玉,林江莉,罗燕,汪天富,蒋银宝.基于边界特征的乳腺肿瘤超声图像识别[J].生物医学工程学杂志,2006,23(6):1237-1240. |
| |
| 作者姓名： | 张科宏 彭玉兰 李德玉 林江莉 罗燕 汪天富 蒋银宝 |
| |
| 作者单位： | 1. 四川大学373信箱,生物医学工程中心,成都,610065
2. 四川大学,华西医院,超声科,成都,610041 |
| |
| 基金项目： | 四川省青年科技基金;四川省应用基础研究计划 |
| |
| 摘 要： | 通过对乳腺肿瘤边界特征的分析，得到边界的特征量似圆度，面积比率，长宽比组成的特征矢量，最后用反向传播人工神经网络（BP）的算法对经病理证实的119幅乳腺良、恶性肿块超声图像进行分类识别。BP神经网络对良、恶性肿瘤正确识别率分别为89．7％、73．5N。量化后的乳腺超声图像肿瘤轮廓特征结合BP神经网络可以比较有效的用于肿瘤的良、恶性识别。
|
| 关 键 词： | 乳腺肿瘤 超声图像 轮廓特征 BP神经网络 |
| 收稿时间： | 2005-01-27 |
| 修稿时间： | 2005-01-272005-03-17 |
The Recognition of Breast Tumor Based on Ultrasonic Image Contour Features |
| |
| Zhang Kehong,Peng Yulan,Li Deyu,Lin Jiangli,Luo Yan,Wang Tianfu,Jiang Yinbao.The Recognition of Breast Tumor Based on Ultrasonic Image Contour Features[J].Journal of Biomedical Engineering,2006,23(6):1237-1240. |
| |
| Authors: | Zhang Kehong Peng Yulan Li Deyu Lin Jiangli Luo Yan Wang Tianfu Jiang Yinbao |
| |
| Institution: | 1,Biomedical Engineering Center, Sichuan University, box 373, Chengdu 610065, China;2,Department of Ultrasound,West China Hospital,Sichuan University, Chengdu 610041,China |
| |
| Abstract: | The purpose of this article is to evaluate the role of quantitative margin features in the computer-aided diagnosis of malignant and benign solid breast masses using sonographic imaging. The tumour was seperated by the expert .Three contour features circurity(C) ,area ratio(A) and length width ratio(LWR) was caculated from the tumour contour. Then back-propagation(BP) neural network with contour features was used to classify tumors into benign and malignant. Results from 119 ultrasonic images have been applied in this experiment. BP neural network yielded the following results: 89.7% and 73.5% respectively. The methods applied in this paper are helpful to raise the correctance of breast cancer diagnosis. |
| |
| Keywords: | Breast tumor Ultrasonic image Contour feature BP neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
