|
|||||
|
|
| 基于BP神经网络的全身骨SPECT图像分割 | |
| 引用本文： | 朱春媚,田联房,陈萍,何元烈,王立非,叶广春,毛宗源. 基于BP神经网络的全身骨SPECT图像分割[J]. 生物医学工程学杂志, 2007, 24(5): 1050-1053 |
| 作者姓名： | 朱春媚 田联房 陈萍 何元烈 王立非 叶广春 毛宗源 |
| 作者单位： | 1. 电子科技大学,中山学院,自动化工程系,中山,528403 2. 华南理工大学,自动化科学与工程学院,广州,510640 3. 广州医学院,第一附属医院,核医学科,广州,510120 4. 广州中医药大学,祈福医院,影像中心,广州,511495 |
| 摘 要： | 我们尝试用BP神经网络分割全身骨SPECT图像,实现病变区域的自动识别。由于SPECT图像病变区域的判断要考虑图像的整体信息,其特征具有不确定性,单靠神经网络识别很难达到理想的效果。我们把分割过程分预处理、神经网络分割和后处理三部分,先用最佳阈值法进行预处理,然后用神经网络进行粗分类,最后用模板匹配和去对称程序排除误识别的区域。 |
| 关 键 词： | 全身骨SPECT图像 BP神经网络 分割 自动识别 |
| 修稿时间： | 2005-04-29 |
Segmentation of Whole Body Bone SPECT Image Based on BP Neural Network |
|
| Zhu Chunmei,Tian Lianfang,Chen Ping,He Yuanlie,Wang Lifei,Ye Guangchun,Mao Zongyuan. Segmentation of Whole Body Bone SPECT Image Based on BP Neural Network[J]. Journal of biomedical engineering, 2007, 24(5): 1050-1053 | |
| Authors: | Zhu Chunmei Tian Lianfang Chen Ping He Yuanlie Wang Lifei Ye Guangchun Mao Zongyuan |
| Affiliation: | Department of Automation Engineering, University of Electronic Science Technology of China, Zhongshan Institute, Zhongshan 528403, China. chunmeizhu@126.com |
| Abstract: | In this paper,BP neural network is used to segment whole body bone SPECT image so that the lesion area can be recognized automatically.For the uncertain characteristics of SPECT images,it is hard to achieve good segmentation result if only the BP neural network is employed.Therefore,the segmentation process is divided into three steps: first,the optimal gray threshold segmentation method is employed for preprocessing,then BP neural network is used to roughly identify the lesions,and finally template match method and symmetry-removing program are adopted to delete the wrongly recognized areas. |
| Keywords: | Whole body bone SPECT image BP neural network Segmentation Automatic recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |