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.