Chromosome division phase positioning and sequencing method

Abstract

The invention discloses a chromosome division phase positioning and sequencing method, and belongs to the technical field of chromosome recognition. The chromosome division phase positioning and sequencing method comprises the following steps: 1) establishing an identification model based on a darknet53 basic network; 2) obtaining an independent chromosome image, and inputting the image accordingto a specified size; 3) performing feature extraction on the input chromosome image by using an identification model, setting three downsampling scales for the structure of the identification model, setting three priori boxes for each downsampling scale, and clustering the priori boxes with nine sizes in total; and 4) carrying out frame prediction by using the output of logistic. According to theinvention, an identification model is established based on a darknet53 basic network; characteristic extraction is performed on the input chromosome image by using the recognition model, and frame prediction is performed quickly, so that the chromosome type can be recognized accurately and efficiently, and compared with the existing recognition technology, the analysis efficiency of the chromosomekaryotype can be effectively improved, the recognition sorting time is shortened, and the chromosome sorting is completed with high accuracy.

Description

technical field [0001] The invention belongs to the technical field of chromosome recognition, and in particular relates to a method for positioning and sorting chromosome division phases. Background technique [0002] Human chromosomal disease is a syndrome of a series of clinical symptoms caused by congenital chromosome number or structure abnormalities. Mainly children with mental retardation, developmental delay, congenital deformities. It can also cause miscarriage and stillbirth. These are unbearable for every family. However, the prevalence of this symptom in my country's pregnant population is about 5%-10%, accounting for more than half of aborted embryos. And these data have an increasing trend year by year, and the Chinese government and related institutions have also begun to pay attention to chromosomal diseases. [0003] The method of clinical detection of human chromosomal diseases is to obtain the stained and banded karyotype samples by culturing somatic c...

AI Technical Summary

Problems solved by technology

The current method of analyzing chromosome pictures is basically manual operation and manual identification. The inspection doctor first needs a lot of training time to master the knowledge of identifying each chromosome type, and the workload is heavy.

Even for experienced doctors to analyze and identify the patient's chromosomes, they first need to manually segment the crossed, cohesive and overlapping chromosomes, then use the mouse to separate the cohesive and overlapping chromatids, and then count the segmented chromatids. The whole process generally takes more than two weeks, and the time period is relatively long

Moreover, manual recognition is highly subjective, easily affected by the external environment, and the accuracy rate is not high.

Images