Automatic analysis method for growth fusion degree of adherent cells

Abstract

The invention provides an automatic analysis method for the growth fusion degree of adherent cells and belongs to the technical field of image processing. Based on the application of the image processing technology, the problems of poor accuracy, low efficiency and the like due to the dependence on the subjective judgments of inspectors during the cell culture process in the medical industry can be solved. The implementation process of the method comprises the following steps of (1) judging an input image type and making the corresponding conversion operation; (2) subjecting a to-be-processed image to high and low cap combination transformation in the grey-level morphology; (3) reducing background noise interference factors based on the differential method in combination with the background estimation method; (4) adopting the K-Means clustering algorithm to realize the rough separation for the foreground of a cell image from the background of the cell image; (5) denoising the cell image by adopting the area filtering method; (6) adding up the pixel levels of two cell results based on the area filtering method; (7) conducting the adaptive analysis on a binary morphology processing coefficient by using a fitting function; (8) optimizing the image by adopting the binary morphology method; (9) calculating a final fusion degree. The method of the invention has an important application value in cell biological characteristics identification.

Description

technical field [0001] The invention relates to an automatic analysis method for the growth and fusion degree of adherent cells. The method overcomes the segmentation problems caused by factors such as the weak contrast between the foreground and the background of the cell image, the unbalanced background gray scale distribution, and large fluctuations, and can realize the cell culture process. The invention relates to the automatic analysis and calculation of medium growth fusion degree, which belongs to the technical field of image processing. Background technique [0002] Growth confluency is an important specification parameter in the cell culture process. At present, in the biomedical industry, it usually depends on the subjective and direct judgment of the inspector. Due to the rapid growth of cells, the growth needs to be detected from time to time. This identification method not only consumes a lot of manpower and time, but also different inspectors often make incons...

AI Technical Summary

Problems solved by technology

Due to the weak contrast between the foreground and the background of the image, and the gray value range of the pixels in the cells is large, when the traditional threshold method is used for region detection, the obtained target is incomplete and the mis-segmentation phenomenon is serious; secondly, because the edge detection algorithm actually relies on The gradient information is used as the threshold condition, and the value greater than the threshold is regarded as the boundary, and the value smaller than the threshold is regarded as the background. Although the gray value of the outer edge of the cell is higher in visual characteristics, and the gray value of the inner cell is larger, this characteristic does not Absolutely, not all the outer edges of the target show this characteristic, so the segmentation effect of the edge detection algorithm is not good; when the active contour model is actually applied, the segmentation effect is ideal in the case of low fusion, but as the fusion increase, the segmentation effect gradually becomes worse, so the active contour model is only suitable for use when the cells are relatively independent and the shape is relatively regular, and it is not universal

Images