基于距离估计的细胞核标记法  

A nucleus location method based on distance estimation

作　　者：孙文灏 陆福相[1] 马义德[1] SUN Wenhao;LU Fuxiang;MA Yide(School o fin formation Science and Engineering, Lanzhou University, Lanzhou 730000, P.R.Chin)

机构地区：[1]兰州大学信息科学与工程学院,兰州730000

出　　处：《生物医学工程学杂志》2018年第3期435-442,451,共9页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(61175012;61201421);兰州大学中央高校基本科研业务费用专项资金(lzujbky-2016-139)

摘　　要：为了更加简单、高效并准确地识别定位经苏木精-伊红(HE)染色切片图像中的细胞核,本文提出了一种基于距离的细胞核标记方法,这种方法为在细胞核丛聚图像中提取细胞核单体提供了一种新的处理思路。与目前主流的基于凹度分析的方法不同,本文所述方法避免了对图像中细胞核丛聚和细胞核单体的分类预处理,可以对含有细胞核丛聚的完整图像进行直接处理。该方法使用了一种被称为距离评估矩阵序列(MSDRE)的矩阵集对丛聚细胞核中的点到区域边界的距离进行快速估算,结合凸区域的中心点距边界最远这一客观事实,它可以快速准确地定位、标记出图像中所有的细胞核单体。在实验中,本标记方法获得了95.26%的标记准确率和每1 000个目标物平均耗时1.54 s的标记效率,较目前的主流方法具有更好的识别准确率和执行效率。本文所述方法在保持标记准确率不降低的前提下,大幅提高了识别标记的效率,提升了HE染色切片图像分析系统的实时性,有利于相关成果的实施和应用。To locate the nuclei in hematoxylin-eosin（HE） stained section images more simply, efficiently and accurately, a new method based on distance estimation is proposed in this paper, which shows a new mind on locating the nuclei from a clump image. Different from the mainstream methods, proposed method avoids the operations of searching the combined singles. It can directly locate the nuclei in a full image. Furthermore, when the distance estimation built on the matrix sequence of distance rough estimating（MSDRE） is combined with the fact that a center of a convex region must have the farthest distance to the boundary, it can fix the positions of nuclei quickly and precisely. In addition, a high accuracy and efficiency are achieved by this method in experiments, with the precision of 95.26% and efficiency of 1.54 second per thousand nuclei, which are better than the mainstream methods in recognizing nucleus clump samples.Proposed method increases the efficiency of nuclear location while maintaining the location＇s accuracy. This can be helpful for the automatic analysis system of HE images by improving the real-time performance and promoting the application of related researches.

关 键 词：细胞核标记 医学图像处理 丛聚单体标记 距离估算 边界矩阵 距离评估矩阵序列 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]