Embryo division process analysis and pregnancy rate intelligent prediction method and system

Abstract

The invention discloses an embryo division process analysis and pregnancy rate intelligent prediction method and system. The method comprises the following steps: collecting embryo images within D1 toD6 periods; inputting the embryo image into a prokaryotic number prediction network model, a blastomere number prediction network model, a fragment proportion prediction network model, a blastocyst cavity and inner cell mass grade prediction network model and a trophoblast grade prediction network model; calculating and outputting a predicted prokaryotic number, a predicted blastomere number, a predicted fragment proportion, a predicted blastocyst cavity proportion, a predicted intracellular mass grade and a predicted trophoblast grade of the embryo image; and inputting the same into an embryo pregnancy rate state prediction machine learning model to calculate and output an embryo pregnancy rate prediction result. According to the intelligent prediction method and system, the whole embryodevelopment process is monitored, the embryo pregnancy rate is obtained through calculation by means of the comprehensive scoring function, manual intervention is not needed in the prediction process, and doctors can be helped to quickly and accurately judge embryo scores.

Description

technical field [0001] The invention relates to the technical fields of embryo morphology and artificial intelligence, in particular to a method and system for analyzing embryo division process and intelligently predicting pregnancy rate. Background technique [0002] The quality of embryo development directly affects the result of pregnancy rate. Embryologists rely on embryo morphology and genetics to distinguish the quality of embryos. Among them, the use of genetic methods to determine the quality of embryos requires extremely high experimental conditions. , and using embryo morphological information to complete embryo evaluation is a simple, fast and effective method. At present, most embryologists judge the quality of embryos by obtaining some important morphological feature changes in the embryo development process based on their long-term embryo observation experience, and use it as an important predictor of the success rate of embryo transfer in the later stage. in ...

AI Technical Summary

Problems solved by technology

[0006]The purpose of the present invention is to overcome the traditional image analysis method in the prior art for the acquisition of fragmented regions, the calculation of the proportion of the blastocoel, and the evaluation of the inner cell mass and trophoblast , the accuracy rate is low, and the real-time performance is poor, and a method and system for embryo division process analysis and pregnancy rate intelligent prediction method and system are proposed. By constructing an effective blastomere number prediction AI model, the different High-level feature extraction, model training and prediction of blastomeres during the period, the accuracy and recognition efficiency have been greatly improved

Images