High-throughput screening using cell images is an efficient method for
screening new candidates for pharmaceutical drugs. To complete the screening
process, it is essential to have an efficient process for analyzing cell
images. This paper presents a new method for efficiently tracking cells and
quantitatively detecting the signal ratio between cytoplasm and nuclei.
Existing methods include those that use image processing techniques and those
that utilize artificial intelligence (AI). However, these methods do not
consider the correspondence of cells between images, or require a significant
amount of new learning data to train AI. Therefore, our method uses automatic
thresholding and labeling algorithms to compare the position of each cell
between images, and continuously measure and analyze the signal ratio of cells.
This paper describes the algorithm of our method. Using the method, we
experimented to investigate the effect of the number of opening and closing
operations during the binarization process on the tracking of the cells.
Through the experiment, we determined the appropriate number of opening and
closing processes.

高通量筛选利用细胞图像是筛选新药候选物的有效方法，本文介绍了一种高效追踪细胞并定量检测胞浆与细胞核信号比率的新方法，通过自动阈值与标签算法比较不同图像中细胞的位置，进行连续测量与分析细胞信号比率，进一步研究开闭运算次数对细胞追踪的影响，确定了合适的开闭运算过程次数。

自动阈值和标记法追踪和分析荧光标记细胞的方法

Method of Tracking and Analysis of Fluorescent-Labeled Cells Using  Automatic Thresholding and Labeling

In this work, we describe a method for large-scale 3D cell-tracking through a
segmentation selection approach. The proposed method is effective at tracking
cells across large microscopy datasets on two fronts: (i) It can solve problems
containing millions of segmentation instances in terabyte-scale 3D+t datasets;
(ii) It achieves competitive results with or without deep learning, which
requires 3D annotated data, that is scarce in the fluorescence microscopy
field. The proposed method computes cell tracks and segments using a hierarchy
of segmentation hypotheses and selects disjoint segments by maximizing the
overlap between adjacent frames. We show that this method achieves
state-of-the-art results in 3D images from the cell tracking challenge and has
a faster integer linear programming formulation. Moreover, our framework is
flexible and supports segmentations from off-the-shelf cell segmentation models
and can combine them into an ensemble that improves tracking. The code is
available this https URL

通过分割选择方法实现大规模三维细胞追踪，该方法在两个方面对大规模显微数据集中的细胞追踪问题具有有效性：（i）能够解决拥有数百万分割实例的 TB 级三维时间数据集的问题；（ii）能够在不依赖稀缺的三维标注数据的情况下与使用深度学习的方法达到竞争水平。该方法通过分割假设的层次结构计算细胞轨迹和分割，并通过最大化相邻帧之间的重叠来选择不相交的分割。证明该方法在细胞追踪挑战中实现了最先进的结果，并且拥有更快的整数线性规划公式。此外，我们的框架灵活性强，支持来自现成细胞分割模型的分割，并能够将它们组合成一个提高追踪效果的整体。代码可以在此链接中找到：https:// 此链接网址