Automatic chromosome segmentation and classification method based on deep learning

Abstract

The invention discloses an automatic chromosome segmentation and classification method based on deep learning. The method comprises the following steps: obtaining a chromosome image and filtering cell impurities by using an Attention U-Net model; segmenting chromosomes and cutting out each chromosome region image; extracting features from the obtained chromosome region, training a support vector machine, a random forest and a logistic regression classifier, and carrying out model integration by adopting a voting method so as to identify overlapped adhesion chromosomes or single chromosomes; respectively designing independent segmentation modules for the overlapped adhesion chromosomes, segmenting the overlapped chromosomes by utilizing a method of separating and then splicing, and segmenting the adhesion chromosomes by utilizing a convex defect point detection method; and respectively inputting the chromosome training data with marked types into 24 classification models ResNet20, ResNet32 and ResNet44 for training, then carrying out model integration by using a stacking method, and outputting a final chromosome classification result and a chromosome karyotype analysis chart so as to carry out chromosome anomaly identification.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an automatic chromosome segmentation and classification method based on deep learning. Background technique [0002] Chromosome analysis (karyotype analysis) is a very important and difficult task in the field of biological research. The purpose of chromosome analysis is to determine the chromosomal composition of cells or individuals, especially to compare the differences between it and the normal structure with physiological or clinical diseases are linked. Observing the karyotype of metaphase chromosomes during cell division is a difficult and burdensome process. First, the cells of the sample tissue are cultured, and the culture is used for sectioning and staining; then the cells suitable for observation are found on the prepared microsections, and captured in digital form by a camera, and the cytogenetics personnel manually press their morphology and ba...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to address the deficiencies in the above-mentioned prior art, that is, the current karyotype analysis method is time-consuming, low in efficiency, and insufficient in accuracy and cannot meet the needs of clinical work. Therefore, the present invention provides a method based on depth Learned chromosome automatic segmentation and classification method to solve the difficulties of manual segmentation and classification processing

Images