Better than the human eye – machine learning models to objectively analyze bovine embryo quality

Abstract

Machine learning (ML) is a type of artificial intelligence that al­lows software applications to become more accurate at predict­ing outcomes without being explicitly programmed. ML models use millions of parameters to detect patterns and generate al­gorithms which can provide image analysis and predictive out­put superior to the human eye. ML models offer value to many biological applications, including the evaluation and selection of bovine embryos in conventional embryo transfer (ET) and in vitro fertilization (IVF). The objective of this study was to train ML models to evaluate bovine embryo viability and test their prediction accuracy against known pregnancy outcomes.