粘连巨噬细胞图像的分割与描述

王平; 张力

doi:null

您当前的位置：

首页 >

文章列表页 >

粘连巨噬细胞图像的分割与描述

更新时间：2020-08-12

- 粘连巨噬细胞图像的分割与描述
- Segmentation and Description to adhesion Macrophage Image
- 液晶与显示 2012年27卷第2期
- 作者机构：
  
  南昌大学信息工程学院电子信息工程系
- 作者简介：
- 基金信息：
- DOI：
  中图分类号： TP391.41
- 收稿日期：2012-07-18，
  
  修回日期：2012-08-12，
  
  网络出版日期：2012-08-27，
  
  纸质出版日期：2012-04-15
- 稿件说明：
移动端阅览
王英涛, 周璇, 张志东. 双轴向列相Fréedericksz转变的Monte Carlo模拟[J]. 液晶与显示, 2012,(2): 144-152

WANG Ying-tao, ZHOU Xuan, ZHANG Zhi-dong. Monte Carlo Simulation of Fréedericksz Transitions in Biaxial Nematic Liquid Crystals[J]. , 2012,(2): 144-152
王英涛, 周璇, 张志东. 双轴向列相Fréedericksz转变的Monte Carlo模拟[J]. 液晶与显示, 2012,(2): 144-152 DOI：

WANG Ying-tao, ZHOU Xuan, ZHANG Zhi-dong. Monte Carlo Simulation of Fréedericksz Transitions in Biaxial Nematic Liquid Crystals[J]. , 2012,(2): 144-152 DOI：

摘要

粘连细胞的分割是医学细胞图像处理中的关键，随着形态学在图像分割中的应用，分水岭分割成为粘连细胞分割中最有效的方法之一。然而，由于巨噬细胞图像中的噪声和形态的不规则性，传统分水岭算法容易产生过分割。若在经距离变换得到的距离图中提取“种子点”，并根据距离图信息得到“种子点”合并的阈值，若两“种子点”之间的距离小于阈值，则将这两“种子点”合并。若在分水岭分割中使用根据新“种子点”重新分布的距离图，实验结果表明：与传统方法相比，该算法虽然要多花费些时间，但可以有效地分割粘连巨噬细胞并抑制过分割现象。分割后，对细胞进行标记并提取细胞的特征参数，如周长、面积、圆度因子、灰度均值等。

Abstract

Segmentation to adhesion cells is critical in image segmentation realm

with the morphology was used in image segmentation

watershed becomes one of the most efficient skills in solving adhesion cells. However

the traditional watershed algorithm is apt to cause over-segmentation for the noise and irregular shape of macrophages.If extracting the "seeding points" from the distance map

and combining some "seeding points" into more reasonable "seeding points" by a certain criterion that the neighbor "seeding points" should be combined to one "seeding point" if the distance between the two points is under threshold which is got from the information the distance map indicates.And redistribute distance map depending on the "seeding points" before watershed

the simulation results show that the algorithm can effectively segment adhesion macrophages as well as restrain the over-segmentation phenomena with a little more time compared with the traditional method.After segmentation

we can mark the numbers to the cells and abstract the characteristic parameters such as circumference、area、roundness factor 、mean gray and so on.

关键词

Keywords

references

吴定允,张利红.改进分水岭算法在医学图像分割中的应用[J].电视技术,2011,35(5):106:108.[2]VINCENT L,SOILLE P.Watersheds in digital spaces:An eficient algorithm based on immersion simulations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598.[3]KIM J B,KIM H J.Multiresolution-based watersheds for efficient image segmentation[J].Pattern Recognition Letters,2003,24(1):473-488.[4]JUNG C R.Multiscale Image Segmentation Using Wavelets and Watersheds[C].Proceedings of the XVI Brazilian Symposium on Computer Graphics and Image Processing.Brazil,273-287.[5]NG H P,ONG S H,FOONG K W C,etc.Masseter segmentation using an improvedwatershed algorithm with unsupervised classification[J].Computers in Biology and Medicine,2008, 38(1):171-184.[6]卢中宁,强赞霞.基于梯度修正和区域合并的分水岭分割算法[J].计算机工程与设计,2009,30(8):2075-2077.[7]OTSU N.A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems,Man and Cybernetics, 1979,9(1):62-66.[8]肖超云,朱伟兴.基于Otsu准则及图像熵的阈值分割算法[J].计算机工程,2007,33(14):188-190.[9]夏国清,鲍苏苏,陈华珍,等.基于数学形态学的CT腹部器官提取[J].计算机应用研究,2009,26(8):3172—3174.[10]MEIJSTER A, WILKINSON M..A comparison of algorithms for connected set openings and closings[J].IEEE Trans. Pattern Anal. Mach. Intell,2002,24 (4) :484-494. [11]GONZALEZ R C,WOODS R E.Digital Image Processing[M].Third Edition.北京:电子工业出版社,2010:688-692.[12]BORGEFORS G.Transformations in arbitrary dimensions[J].Computer Vision, Graphics and Image Processing, 1984, 27:321-345.[13]SMET P D,PIRES R L.Implementation and Analysis of an Optimized Rain Falling Watershed Algorithm[C]//Proc of SPIE’00. San Diego, USA, 2000: 759-766.[14]杨润玲,周军妮,刘利.基于改进FCM聚类的图像分割新方法[J].电视技术,2008,32(6):12:14.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据