Predicting Cell Cleavage Timings from Time-Lapse Videos of Human Embryos

Assisted reproductive technology is used for treating infertility, and its success relies on the quality viability of embryos chosen uterine transfer. Currently, embryologists manually assess embryo development, including time duration between cell cleavages. This paper introduces a machine learning methodology automating computations start cleavage stages, in hours post insemination, time-lapse videos. The detects cells video frames predicts frame with onset stage. Next, reads insemination from using optical character recognition. Unlike traditional detection techniques, our suggested approach eliminates need extra image processing tasks such as locating or removing extracellular material (fragmentation). accurately stages up to five cells. was also able detect morphological structures later morula blastocyst. It takes about one minute annotate times all cleavages video.