Automated Cell Division Detection and Classification in Early Mouse and Human Embryos
Infertility affects millions of couples every year. The most effective treatment for infertility is in-vitro fertilization (IVF). Embryo selection, which has become a critical part of IVF treatments, is the process of selecting the most viable embryos to transfer and maximize the chance of pregnancy while minimizing the risks resulting from multiple births. Advancements in time-lapse microscopy have provided a stepping stone for better assessments of embryo quality but have also placed a greater burden on embryologists having to review a steadily growing number of images. Recent developments in artificial intelligence and convolutional neural networks (CNN) have shown great potential in computer-aided analysis of images. In this work, we explore ways to use CNNs to automate the embryo selection. In particular, we focus on predicting the timings of cell divisions in early human embryos, which have been shown to correlate well with pregnancy outcomes. In conclusion, we present a method to aid embryologists with annotating embryos and in a future version we think our method will be a part of a fully automated system for selecting the most viable embryos.
Computer science|Cellular biology|Artificial intelligence
Malmsten, Jonas Erik, "Automated Cell Division Detection and Classification in Early Mouse and Human Embryos" (2019). ETD Collection for Pace University. AAI13896245.
Remote User: Click Here to Login (must have Pace University remote login ID and password. Once logged in, click on the View More link above)