Deep learning-based chromosome uploidy prediction system and method, terminal and medium

Abstract

The invention belongs to the technical field of biomedicine, and discloses a deep learning-based chromosome uploidy prediction system and method, terminal and medium, and the method comprises the steps: selecting a part of embryo images in the whole process of embryo development, combining the images into a video as a training data set according to the time sequence, building a video sequence feature network model, training the embryo video, extracting morphological characteristics and dynamic characteristics in the embryo development process; and fusing the embryo video features and the clinical data features of the patient, and training a network according to the fused features to obtain a prediction result. According to the method, a video sequence feature network framework is creatively used, the space-time characteristics in the embryo development process are well obtained, and the extraction of the dynamic characteristics and the morphological characteristics of the embryo cells is effectively completed; the prediction model provided by the invention can automatically complete the prediction of the chromosome uploidy, and no manual intervention exists in the prediction process.

Description

technical field [0001] The invention belongs to the technical field of biomedicine, and in particular relates to a deep learning-based chromosome euploidy prediction system, method, terminal and medium. Background technique [0002] At present, chromosomal euploidy is closely related to fetal health. At present, the main technical means for chromosomal euploidy identification is to use the third-generation test-tube baby technology (PGT), which requires professional instruments to detect trace amounts in embryos. Diagnosis with cells is expensive. In the process of diagnosis, the discrimination period is long, which will affect the development of embryos. At the same time, in this process, the artificial error will also be greatly increased. With the help of artificial intelligence technology, combined with the morphological characteristics and kinetic characteristics of embryo images and the basic clinical information of patients during the embryo's own development, a deep...

AI Technical Summary

Problems solved by technology

[0003] According to investigations and studies, no scholars have studied the problem of chromosome euploidy prediction from the perspective of video images. How to construct an effective artificial intelligence prediction model for solving chromosome euploidity prediction; how to design a new prediction network structure can be very Effective feature fusion of embryo morphological features, dynamic features and patient clinical data

[0004] Through the above analysis, the existing problems and defects of the existing technology are: the existing method for chromosomal euploidy identification has a long period of identification, high cost and low penetration rate, and at the same time, the existing technology does not use artificial intelligence prediction models to detect chromosomal euploidy Forecast scenario

Images