Chromosome scatter image automatic segmentation method

Abstract

The invention provides an automatic segmentation method for a chromosome scatter image. The automatic segmentation method comprises the following steps: S1, acquiring a connected domain binary image of the chromosome scatter image; S2, segmenting the connected domain binary image to obtain a connected domain image of the chromosome scatter image; S3, carrying out binary classification on the connected domain image, and separating an adherent chromosome image and a single chromosome image; S4, inputting the separated cohesive chromosome image into a deep learning segmentation network pre-training model for secondary segmentation to obtain a chromosome karyotype image. Compared with an existing chromosome scatter image segmentation method, the method has the advantages that the segmentation of most chromosomes is realized by using a traditional algorithm, and then the classification result, namely adherent chromosomes, is further segmented again by using image dichotomy, so the multi-level fine operation of chromosome segmentation is realized, and the segmentation process is more stable; meanwhile, the segmentation method only needs to label adhered chromosomes and does not need to label a large amount of data, so that the manual labeling cost is saved.

Description

technical field [0001] The invention belongs to the technical field of chromosome analysis, and in particular relates to an automatic segmentation method for chromosome scattered pattern images. Background technique [0002] With the development of computer vision, medical image processing based on computer vision will help doctors perform rapid medical diagnosis. Karyotype image ( Figure 6 ) is very important for doctors to judge the condition. However, only chromosome scattered images ( Figure 5 ), the chromosomes of these images are scattered randomly, randomly, and overlapped. Chromosomal images cannot intuitively provide doctors with problems such as whether there is abnormal structure or number of chromosomes in patients. Therefore, it is necessary to obtain a karyotype chromosome image through secondary processing of the acquired chromosome scattered image. This process is cumbersome and requires careful observation by professional medical staff, which is time-co...

AI Technical Summary

Problems solved by technology

However, only chromosome scattered images ( Figure 5 ), the chromosomes of these images are scattered, randomly, and overlapped

Chromosomal images cannot intuitively provide doctors with problems such as whether the structure or number of chromosomes in patients is abnormal

Therefore, it is necessary to obtain the karyotype chromosome image through secondary processing of the obtained chromosome scattered image. This process is cumbersome and requires professional medical staff to carefully observe the operation, which is time-consuming and labor-intensive. At the same time, there is also the problem of low classification accuracy.

Images