Cell image segmentation method

Abstract

The invention provides a cell image segmentation method. The cell image segmentation method comprises the following steps: (A1) acquiring an image of a cell in a division period; (A2) preprocessing the image, wherein the preprocessing comprises at least one of denoising and enhancing the contrast ratio of a foreground and a background; (A3) utilizing a segmentation threshold to realize first segmentation of cells and a background in the preprocessed image; (A4) carrying out second segmentation on the image after the first segmentation by utilizing an operator, a connected domain marking methodand the preprocessed image; and (A5) processing the image after the second segmentation, wherein the processing includes the operation of performing hole filling on the binary image and removing isolated points, and outputting a final segmented image. The method has the advantages of high segmentation precision and the like.

Description

technical field [0001] The invention relates to cell analysis, in particular to a cell image segmentation method. Background technique [0002] Stem cells are cells with the potential of self-replication and multi-directional differentiation. They have the ability to form other cells or tissues in the human body. They are called "universal cells" in the medical field. The large medical application value is of great significance to the maintenance of human health and the continuation of life. [0003] The growth of stem cells is a process of continuous division and differentiation, and random movement. Traditional research methods mainly rely on researchers to understand and analyze the growth status of cells through naked eye observation, which has the following disadvantages: [0004] 1. The number of cells is huge and densely distributed, which requires huge human resources; [0005] 2. Due to the microscopic characteristics of cells, it is difficult for researchers to o...

AI Technical Summary

Problems solved by technology

[0004]1. The number of cells is huge and densely distributed, requiring huge human resources;

[0005]2. Due to the microscopic characteristics of cells, it is difficult for researchers to observe for a long time, and the observation process is very subjective, so it is difficult to ensure the correctness of the observation results;

[0006]3. The growth environment of stem cells is an important experimental parameter. The dye labeling method used in traditional cell observation methods will affect the activity of cells, which makes the cells It is more difficult to observe and mark the

At the same time, for the segmentation of adhesive stem cell images with apertures, the traditional threshold method cannot accurately obtain the pixel distribution information of the cells and the background in the image, resulting in the inability to accurately segment the edges of the real cells, and the segmentation effect is not good; and the principle of phase contrast microscopy is used to eliminate the influence of the aperture , requiring a complex modeling process

Images