[1]吴明珠,陈瑛,李兴民.利用Stein-Weiss解析函数结合反向传播神经网络进行血管分割[J].中国医学物理学杂志,2020,37(6):708-713.[doi:DOI:10.3969/j.issn.1005-202X.2020.06.010]
　WU Mingzhu,CHEN Ying,LI Xingmin,et al.Stein-Weiss analytic function combined with back-propagation neural network for blood vessel segmentation[J].Chinese Journal of Medical Physics,2020,37(6):708-713.[doi:DOI:10.3969/j.issn.1005-202X.2020.06.010]
点击复制

利用Stein-Weiss解析函数结合反向传播神经网络进行血管分割()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
37
期数:
2020年第6期
页码:
708-713
栏目:
医学影像物理
出版日期:
2020-06-25

文章信息/Info

Title:
Stein-Weiss analytic function combined with back-propagation neural network for blood vessel segmentation
文章编号:
1005-202X（2020）06-0708-06
作者:
吴明珠1; 陈瑛1; 李兴民2; 3
1.广州工程技术职业学院信息工程学院， 广东 广州 510075； 2.华南师范大学计算机学院， 广东 广州 510631； 3.南方医科大学珠江医院， 广东 广州 510280
Author(s):
WU Mingzhu1;  CHEN Ying1;  LI Xingmin2;  3
1. School of Information Engineering, Guangzhou Institute of Technology, Guangzhou 510075, China 2. School of Computer, South China Normal University, Guangzhou 510631, China 3. Zhujiang Hospital of Southern Medical University, Guangzhou 510280, China
关键词:
血管分割; Stein-Weiss解析函数; 反向传播神经网络
Keywords:
Keywords: blood vessel segmentation Stein-Weiss analytic function back-propagation neural network
分类号:
R318；TP391
DOI:
DOI:10.3969/j.issn.1005-202X.2020.06.010
文献标志码:
A
摘要:
针对传统反向传播（BP）神经网络对血管进行分割存在耗时长且识别率不高的问题，本研究提出一种新的基于Stein-Weiss解析函数的BP神经网络算法用于血管分割。首先为每个体素构建一个Stein-Weiss函数，然后根据Stein-Weiss解析函数的解析性，计算出相应体素的16个特征值，将这些特征值输入到BP神经网络的输入层，采用BP神经网络的自学习能力对这些数据进行分类学习，最后通过BP神经网络的泛化能力来获取血管边缘。对肝脏血管分割的实验结果表明，相对于传统的BP神经网络分割算法，该算法提取的函数血管边缘识别率高、细节丰富，分割效率也明显提高。
Abstract:
Abstract: For solving the problem of traditional back-propagation (BP) neural network for blood vessel segmentation, such as time consuming and low recognition rate, a BP neural network based on Stein-Weiss analytic function is proposed for blood vessel segmentation. After Stein-Weiss function is constructed for each voxel, 16 eigenvalues of the corresponding voxel are calculated according to the analytic properties of Stein-Weiss analytic function. The calculated eigenvalues are taken as the input data of BP neural network, and then the data are classified and learned through the self-learning ability of BP neural network. Finally, the edge of blood vessel is obtained by the generalization ability of BP neural network. The experimental results of hepatic vessel segmentation show that compared with traditional BP neural network algorithms, the proposed algorithm can be used to not only obtain the edge of blood vessel with high recognition rate and rich details, but also improve the efficiency of segmentation.

相似文献/References:

[1]张梦璐,杨孝平.基于改进活动窄带模型的冠状动脉CT血管造影图像分割[J].中国医学物理学杂志,2017,34(2):170.[doi:10.3969/j.issn.1005-202X.2017.02.012]
　Segmentation of CT angiographic images of the coronary artery based on an improved active narrow band model[J].Chinese Journal of Medical Physics,2017,34(6):170.[doi:10.3969/j.issn.1005-202X.2017.02.012]
[2]孙国栋,石蕴玉,刘翔,等.超声图像血管分割的研究进展[J].中国医学物理学杂志,2022,39(4):453.[doi:DOI:10.3969/j.issn.1005-202X.2022.04.011]
　SUN Guodong,SHI Yunyu,LIU Xiang,et al.Advances in blood vessel segmentation in ultrasound image[J].Chinese Journal of Medical Physics,2022,39(6):453.[doi:DOI:10.3969/j.issn.1005-202X.2022.04.011]
[3]蒋先刚,张红斌.基于三维图像的大脑病灶显示和分析[J].中国医学物理学杂志,2023,40(1):61.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.010]
　JIANG Xiangang,ZHANG Hongbin.Brain lesion display and analysis based on 3D rendering[J].Chinese Journal of Medical Physics,2023,40(6):61.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.010]

备注/Memo

备注/Memo:
【收稿日期】2020-01-20 【基金项目】广东省重点平台及科研项目特色创新类项目（2017GKTS- CX049，2017GKTSCX050）；2019年度校级应用技术协同创新中心项目 【作者简介】吴明珠，硕士，副教授，研究方向：医学图像处理，E-mail: wmz419@126.com
更新日期/Last Update: 2020-07-03