Exploring the Role of Explainability in AI-Assisted Embryo Selection

Infertility is a common reproductive health problem that affects millions of people worldwide, causing social, psychological, physical and economic distress to the ones seeking to conceive [7]. In the coming years infertility rates are projected to grow due to environmental and lifestyle factors [18, 37]. In vitro fertilization (IVF) technology is used to overcome infertility, it involves the fertilization of an egg with sperm in the laboratory, followed by the transfer of the resulting embryos into the patient's uterus. The main challenge of IVF is the selection of the embryos that will be either selected for implantation, frozen (for later implantation) or discarded (if they exhibit undesirable features). This selection is to be performed during the early hours after embryo insemination, typically between three and five days after. During this time, embryos are monitored in time-lapse imaging incubators (TLI), facilitating uninterrupted embryo growth within stable culture conditions. This technology offers a dynamic perspective on in vitro embryonic development, augmenting the clinical effectiveness of IVF [29]. To assess quality, embryologists evaluate different morphological characteristics depending on the embryo development phase.