Intelligent cell identification method based on laser confocal microscopy technology

Abstract

The invention discloses an intelligent cell identification method based on the laser confocal microscopy technology. The method comprises the following steps: (1) carrying out culture and fluorescentstaining treatment on cells; (2) adopting a laser confocal microscope to obtain a layer-cut image of a cell multi-fluorescence channel; (3) sequentially carrying out graying, denoising processing andthreshold segmentation on the layer-cut image, picking out a cell region, and storing gray data of the same fluorescence channel into a three-dimensional matrix; (4) determining each cell region and labeling by adopting a region random growth model; (5) sequentially carrying out interpolation three-dimensional reconstruction on the labeled cells, and calculating three-dimensional morphological parameters of each cell; (6) repeating the processes (1) to (5) by using different cells, and learning the three-dimensional morphological characteristics of the cells by using a machine learning methodto finally realize the identification of various cells. According to the identification method provided by the invention, various cells can be rapidly and effectively identified on the basis of the three-dimensional morphological characteristics of the cells obtained by the laser confocal microscopy technology.

Description

technical field [0001] The invention relates to the fields of image processing and artificial intelligence identification, in particular to an intelligent cell identification method based on laser confocal microscopy technology. Background technique [0002] The principle of confocal microscopy was proposed by American scientist Marvin Minsky in 1957, and Meridian Corporation of the United States realized the commercialization of laser scanning confocal microscopy (LSCM) after 1987. It has the advantages of high resolution, high contrast, non-destructive tomography, etc., and is widely used in the research of biological tissues, cells and other various biological particles. [0003] Unlike traditional optical microscopes, laser confocal microscopes can acquire two-dimensional plane images with extremely small depth of field when taking cell images. When the sample is continuously moved along the direction perpendicular to the two-dimensional plane image, optical slices at d...

AI Technical Summary

Problems solved by technology

This process consumes a lot of time and energy for researchers, so the intelligent segmentation and labeling of cell images is very important, and it is necessary to find an ideal cell labeling and counting method