System for predicting whether embryo can be capsulated or not based on time-delay camera system and deep learning algorithm

Abstract

The invention discloses a system for predicting whether an embryo can be capsulated or not based on a time-delay camera system and a deep learning algorithm. The system comprises a single-cell and multi-cell identification module, a pronucleus identification module, a pronucleus disappearance identification module, a five-classification cell identification module, a time domain prediction module, a space domain prediction module and a time-space domain combination prediction module. According to the system for predicting whether the embryo can be capsulated or not based on the time-delay camera system and the deep learning algorithm, time sequence and form information of a video are separately identified by using a time domain model and a space domain model, and then the time sequence and form information are integrated, so that the prediction accuracy is remarkably improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence learning and analyzing medical images, in particular to a system for predicting whether an embryo can form a cyst based on a time-lapse camera system and a deep learning algorithm. Background technique [0002] At present, the standard of embryo evaluation and screening widely used in clinical practice is still the traditional morphological method, that is, embryologists evaluate the morphology and developmental stages of embryos at several fixed time points after embryo fertilization to determine their developmental ability. Morphological assessment, however, is subject to the subjectivity of the embryologist. More importantly, embryonic development is a process of dynamic changes, and the observation of intermittent time points cannot obtain comprehensive embryonic development information, thereby missing key events in the embryonic development process. In recent years, the time...

AI Technical Summary

Problems solved by technology

However, the accuracy of the EevaTM system for automatic annotation of early embryos needs to be improved: when compared with manual annotation of the same embryo video, EevaTM did not show an advantage in predicting blastocysts and embryo screening

Another study examined the validity of 6 published ESAs and found that they had no diagnostic value for data other than modeling, suggesting that existing ESAs may not be clinically applicable

Images