A method and system for automatic chromosome analysis based on depth learning

Abstract

The invention discloses a chromosome automatic analysis method and a chromosome automatic analysis system based on depth learning, which can adopt multi-level processing, stratify the independent formand overlapping form of chromosomes, and perform cluster analysis on chromosome position coordinates, classification labels and classification confidence to output a karyotype map. In this manner, the method of chromosome segmentation based on depth learning can be adopted, independent of specific chromosomal morphological patterns, The method has high generalization ability, can adopt chromosomeclassification method based on depth learning, take into account the global morphology and banding characteristics of chromosomes, improve classification accuracy, can adopt multi-scale processing, more fully utilize the detected images, and effectively improve the segmentation effect in the case of chromosome overlap and adhesion.

Description

technical field [0001] The invention relates to the technical field of chromosome analysis, in particular to an automatic chromosome analysis method and system based on deep learning. Background technique [0002] Human chromosome identification is an important research topic in medical genetics. It has a wide range of applications in the fields of medical clinical diagnosis, auxiliary teaching and scientific research. It is an important basis for judging human genetic diseases. Traditional chromosome identification is done manually, not only the identification process is cumbersome, but also the identification work is prone to errors. In order to reduce the workload of medical staff and medical teaching staff and improve the identification efficiency, the automatic identification of chromosomes using computer image processing technology has been used. [0003] Chromosome automatic recognition technology mainly includes three processes: image preprocessing, image segmentati...

AI Technical Summary

Problems solved by technology

Restricted by the depth of striped feature extraction and feature set selection, the chromosome recognition rate of the current scheme is low, especially for overlapping chromosomes with missing striped information, the classification accuracy will drop significantly

Moreover, the above scheme does not make full use of the morphological information of chromosomes, and it is not stable when the stripes are not obvious or there is noise.

Images