电子测量与仪器学报

张杰,施露露,史振志,闻路红,庞吉宏.相差细胞图像的光照均衡与分割计数方法研究[J].电子测量与仪器学报,2022,36(5):136-145

相差细胞图像的光照均衡与分割计数方法研究

Study of light equalization and segmentation countingmethod for cell phase contrast images

DOI：

英文关键词:phase contrast microscopic cell images light balance double threshold segmentation image block

基金项目:浙江省博士后科研项目（ZJ2021003）、宁波市“3315计划”创新团队项目（2020A 17 C）资助

作者	单位
张杰	1. 宁波大学高等技术研究院
施露露	2. 中国科学院上海技术物理研究所
史振志	1. 宁波大学高等技术研究院
闻路红	1. 宁波大学高等技术研究院
庞吉宏	1. 宁波大学高等技术研究院

Author	Institution
Zhang Jie	1. The Research Institute of Advanced Technologies, Ningbo University
Shi Lulu	2. Shanghai Institute of Technical Physics Chinese Academy of Sciences
Shi Zhenzhi	1. The Research Institute of Advanced Technologies, Ningbo University
Wen Luhong	1. The Research Institute of Advanced Technologies, Ningbo University
Pang Jihong	1. The Research Institute of Advanced Technologies, Ningbo University

摘要点击次数: 950

全文下载次数: 1146

中文摘要:

为了解决相差显微细胞图像的光照不均匀,实现准确、快速的细胞图像分割与计数,本文提出了一种图像光照均衡,并结合双阈值分割计数的方法。该方法对图像进行分块,依据子块与整幅图像平均灰度的比值进行亮度调节,并采用高斯函数权值优化比值,消除因图像分块而产生的“方块效应”,并通过图像熵与高斯函数标准差关系曲线确定了最优的标准差;使用双阈值方法分割修复后的图像,结合孔洞填充与面积约束优化分割后的细胞形态。利用 C2C12 相差显微细胞图像数据集测试该算法,其中高细胞密度图像的分割精确率、召回率和 F 值分别为 0. 966 2、0. 967 8 和 0. 967 0,明显优于其他对比方法。实验结果表明,该方法在处理不同细胞密度的光照不均匀相差细胞图像时,均能实现光照均衡,且图像信息损失较小,分割计数结果准确。

英文摘要:

In order to solve the uneven illumination of phase contrast microscopic cell images, achieving the goals of accurate and fast cell image segmentation and automatic counting, this paper proposes a method of image illumination equalization combined with double threshold segmentation and counting. The method chunks the image, adjusts the brightness based on the ratio of sub-blocks to the average gray level of the whole image, and optimizes the ratio by using Gaussian function weights to eliminate the “square effect” caused by image chunks, and determines the optimal standard deviation by the relationship curve between image entropy and Gaussian function standard deviation. The images were segmented using a double-threshold method to optimize the morphology of the restored cells by combining cavity filling and area constraints. The algorithm was tested using the C2C12 phase-difference microscopic cell image dataset, in which the segmentation accuracy, recall and F-value of the high cell density images were 0. 966 2, 0. 967 8 and 0. 967 0, respectively, which were significantly better than other comparative methods. The results showed that the method could achieve light equalization when processing the light inhomogeneous phase contrast cell images of different cell densities, with less image information loss, high-accuracy cell-segmentation and counting results.

查看全文查看/发表评论下载PDF阅读器