Bent chromosome image straightening method based on joint model

Abstract

The invention discloses a curved chromosome image straightening method based on a joint model. The method comprises the following steps: acting a deformation field on a real straight chromosome to realize simulation of a curved chromosome; the method comprises the following steps: extracting respective local and global morphological characteristics of a real straight chromosome and a simulated curved chromosome through convolution operation of a first UNet encoder and self-attention guidance of a Transform layer, and establishing a morphological characteristic mapping relation of the two chromosomes by using decoding regression, namely a morphological straightening deformation field; the length and the bending degree are calculated, the morphological straightening deformation field is further corrected structurally, and a primarily-corrected morphological straightening deformation field is obtained; performing secondary detail correction optimization of morphology and structure on the primarily corrected morphological straightening deformation field again through a second UNet; and finally, sequentially inputting a to-be-predicted actual bending chromosome into the morphological straightening deformation fields subjected to primary correction and secondary correction to obtain a final straightening chromosome. The method is high in universality and high in accuracy.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to a method for straightening images of curved chromosomes based on a joint model. Background technique [0002] Karyotyping is an essential step in the study of genetic disorders such as Turner syndrome, Down syndrome, and Creedue chat syndrome, because chromosomes tend to bend randomly in stained microscopic images because of their non-rigid nature. This bending deformation can increase the difficulty of the analysis of band features, hinder the classification of chromosome types and the identification of abnormalities. Chromosome correction allows cytogeneticists to see and analyze chromosomes more clearly, thereby increasing the efficiency of karyotyping. In the correction of bent chromosomes, morphological features (banding information) and structural features can be used for classification of chromosome types and identification of abnormalities. Therefore, in the corr...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a straightening method for curved chromosomes suitable for different types of curvatures and different types in order to solve the problems that the morphological and structural features of chromosomes are poorly preserved and the straightening algorithm is not strong after straightening.

Images