Fetal Images Trophectoderm Score Prediction Using Deep Learning Methodologies

In-vitro fertilization (IVF) is an assisted reproductive technology (ART) and is regarded as one of the most successful. The embryo quality is determined by the Gardner system which quantifies three characteristics of embryo morphology: expansion, inner cell mass (ICM), and trophectoderm quality (TE). However, several complex and expensive procedures are involved. Increasing the success and at the same time simplifying the procedure, requires relying on novel technologies, like computer vision and deep learning (DL). DL can automatically extract valuable features from data, are highly adaptable, and perform efficiently across various problems. This has spurred significant research efforts into creating and evaluating DL-powered tools for embryo selection. This work utilizes DL learning methods for the task of TE score prediction.