Chromosome karyotype image cutting method

Abstract

The invention discloses a chromosome karyotype image cutting method, and belongs to the technical field of chromosome image processing. An existing image segmentation method is used for segmenting a chromosome image, due to the fact that the chromosome image has a lot of noise, the phenomenon of wrong segmentation can occur, and errors are caused to bring interference to subsequent analysis. According to the method, chromosome image segmentation is mainly carried out based on connected domain segmentation and skeleton extraction modes, after independent single chromosomes are extracted throughconnected domain analysis, skeleton extraction and skeleton analysis are carried out on remaining cross chromosomes to find possible segmentation points, and segmentation of the cross chromosomes isrealized through the segmentation points; compared with the prior art, direct segmentation of the preprocessed image is changed, the segmentation effect is clear, errors caused by segmentation are reduced to the maximum extent, the process is simple and reasonable, large-scale popularization and application can be conducted outwards, and deployment is simple.

Description

technical field [0001] The invention relates to a method for cutting a chromosome karyotype image, belonging to the technical field of chromosome image processing. Background technique [0002] At present, chromosome analysis systems generally rely on human-computer interaction to segment chromosomes. Since the quality of chromosome images is related to the dyeing quality of samples, and is seriously affected by light, there are many impurities in the image, the contrast is poor, and the chromosomes are bright and dark. Banding makes the gray level distribution inside the target uneven. Directly use the existing image segmentation method to segment the chromosome image, because the chromosome image itself has a lot of noise, there will be mis-segmentation, and the resulting error will interfere with the subsequent analysis. Contents of the invention [0003] Aiming at the defects of the prior art, the purpose of the present invention is to provide a method of segmentation...

AI Technical Summary

Problems solved by technology

[0002] At present, chromosome analysis systems generally rely on human-computer interaction to segment chromosomes. Since the quality of chromosome images is related to the dyeing quality of samples, and is seriously affected by light, there are many impurities in the image, the contrast is poor, and the chromosomes are bright and dark. Ribbon makes the gray level distribution inside the target uneven

Directly use the existing image segmentation method to segment the chromosome image. Since the chromosome image itself has a lot of noise, there will be mis-segmentation, and the resulting error will interfere with the subsequent analysis.

Images