Selection of competent oocytes by morphological features. Can an artificial intelligence - based model predict oocyte quality?

Infertility is a significant problem of humanity. Despite the many advances in the field of assisted reproductive techniques (ART), accurately predicting the outcome of an in vitro fertilization cycle (IVF) has yet to be achieved. The focus of a great deal of research Is to improve on the current 30% success rate of IVF. Assessment of oocyte quality is probably the most important and difficult task in the ART. Oocyte quality has a direct impact on the fertilization and oocyte competence; the identification of oocyte quality markers is particularly important to select embryos with higher developmental potential and thus increase the success rates of IVF cycles. Nevertheless, the assessment of the oocyte morphology is still performed more arbitrarily. Over the past years, the ARTs have been accompanied by constant innovations; the use of artificial intelligence (AI) techniques has become increasingly popular in the medical field and is being leveraged in the embryology laboratory to help improve IVF outcomes. The aims of this study are to evaluate the influence of specific morphological characteristics of oocytes on the outcome of intracytoplasmic sperm injection (ICSI) and to develop an AI-based model that predicts oocyte quality and fertilization outcome.