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

Abstract

The invention discloses a method and system for automatic analysis of chromosomes based on deep learning, which can adopt multi-level processing to process the independent and overlapping forms of chromosomes hierarchically, and perform cluster analysis on chromosome position coordinates, classification labels and classification confidence Output the karyotype map. Through the above method, the chromosome segmentation method based on deep learning can be adopted, which does not depend on specific chromosome morphological patterns, and has high generalization ability. Accuracy, multi-scale processing can be used, the image to be detected can be fully utilized, and the segmentation effect in the case of chromosome overlap and adhesion can be effectively improved.

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