English

应用科学学报 ›› 2010, Vol. 28 ›› Issue (6): 609-615.doi: 10.3969/j.issn.0255-8297.2010.06.009

• 信号与信息处理 • 上一篇    下一篇

基于三维脉冲耦合神经网络模型的医学图像分割

施俊， 常谦， 钟瑾   

  1. 上海大学通信与信息工程学院，上海200072
  • 收稿日期:2010-06-09 修回日期:2010-09-27 出版日期:2010-11-26 发布日期:2010-11-27
  • 作者简介:施俊，博士，副教授，研究方向：医学图像处理、医学信号处理，E-mail: junshi@staff.shu.edu.cn
  • 基金资助:

    国家自然科学基金(No.60701021)；上海市教育委员会科研创新项目基金(No.09YZ15)；上海市教委重点学科建设项目基金(No.J50104)资助

Segmentation of Medical Images Based on Three Dimensional Pulse Coupled Neural Network Model

SHI Jun, CHANG Qian, ZHONG Jin   

  1. School of Communication and Information Engineering, Shanghai University, Shanghai 200072, China
  • Received:2010-06-09 Revised:2010-09-27 Online:2010-11-26 Published:2010-11-27

PDF

1776

被引次数

4

摘要：

该文将脉冲耦合神经网络模型从二维平面扩展到三维空间，同时提出一种新的乘积型互信息算法，将其作为脉冲耦合神经网络分割算法的最优分割准则，并将两者结合实现三维医学图像的整体自动分割. 利用该文提出的算法对三维CT肺部图像进行分割实验，结果表明，该算法在保证分割精度的基础上显著地减少了分割运行时间，提高了分割效率，具有应用于医学图像分割的潜在价值.

关键词: 脉冲耦合神经网络, 图像分割, 乘积型互信息, 三维图像, 运算量

Abstract:

 In this study, the 2D pulse coupled neural network (PCNN) model is extended to the 3D space, and a new rule for optimal image segmentation, named product mutual information (PMI), is proposed. Based on the 3D PCNN and PMI, an automatic segmentation algorithm is developed for 3D medical image segmentation. Three-dimensional CT lung images are segmented with the proposed method, showing reduced execution time and improved computation efficiency with high segmentation accuracy. The method is potentially useful for
medical image segmentation.

Key words: pulse coupled neural network, image segmentation, product mutual information, three dimensional, image, computation complexity

中图分类号: