Profiling oocytes with neural networks from images and mechanical data.

The success rate of assisted reproductive technologies could be greatly improved by selectively choosing egg cells (oocytes) with the greatest chance of fertilization. The goal of mechanical profiling is, thus, to improve predictive oocyte selection by isolating the mechanical properties of oocytes and correlating them to their reproductive potential. The restrictions on experimental platforms, however - including minimal invasiveness and practicality in laboratory implementation - greatly limits the data that can be acquired from a single oocyte. In this study, we perform indentation studies on human oocytes and characterize the mechanical properties of the zona pellucida, the outer layer of the oocyte. We obtain excellent fitting with our physical model when indenting with a flat surface and clearly illustrate localized shear-thinning behavior of the zona pellucida, which has not been previously reported. We conclude by outlining a promising methodology for isolating the mechanical properties of the cytoplasm using neural networks and optical images taken during indentation.

Separating the contributions of zona pellucida and cytoplasm in the viscoelastic response of human oocytes.

The successful characterization of the mechanical properties of human oocytes and young embryos is of crucial relevance to reduce the risk of pregnancy arrest in in-vitro fertilization processes. Unfortunately, current study has been hindered by the lack of accuracy in describing the mechanical contributions of each structure (zona pellucida, cytoplasm) due to its high heterogeneity. In this work, we present a novel approach to model the oocyte response taking into account the effect of both zona and cytoplasm, as well as different loading conditions. The model is then applied to develop an experimental protocol capable of accurately separating the viscoelastic contribution of zona and cytoplasm by simply varying the loading condition. This new protocol has the potential to open the door to improving our understanding the mechanical properties of oocytes at different stages, and provide a quantitative predictive ability to the evaluation of oocyte quality. STATEMENT OF SIGNIFICANCE: Assisted reproductive technologies, such as in vitro fertilization, often rely on identifying high quality oocytes or female egg cells. The viscoelastic properties of these cells, such as stiffness and stress relaxation time, have been identified as potential objective indicators of cell quality. However, their characterization has proven difficult due to the structural heterogeneity of the cell and inconsistent loading conditions. This paper presents a new model that, although simple, addresses the above difficulties to provide accurate estimations of the cell's mechanical properties. Learning from this model, we then propose a novel non-invasive testing protocol to allow oocyte characterization with increased accuracy. We believe this effort would improve consistency in measurements and enhance our knowledge on the mechanics of oocytes.