Real-time computer assisted measurement of oocyte and embryo volume for assessment of transport parameters.

Cryopreservation of gametes has revolutionized both animal agriculture and human reproductive medicine. Although many new technologies have tremendously improved the cryopreservation of oocytes and embryos, osmotic stress encountered during the equilibration process can cause their loss of function. Rational cryoprotective agent (CPA) equilibration strategies can be used to minimize this stress but require trained personnel to monitor the process in individual oocytes or embryos or require the use of suboptimal average transport parameter values in mathematically guided protocols. To enable individually optimized equilibration of CPAs in individual cells, here we establish experimental and computational techniques to track the osmotic behavior of individual bovine oocytes and embryos during CPA equilibration in real time. We designed a microfluidic device to provide a controlled flow of CPA and modified standard image analysis techniques to estimate real-time cell volume changes. In particular, we used a level-set method to define a boundary within a contour plot which could automate the image analysis process. A colour based level set algorithm coupled with contour smoothing not only provided the best fit but also reduced the segmentation time to well under a second per image. The accuracy of the automated method was comparable to human segmented images for both oocytes and embryos. This technology should enable both rapid evaluation of key biophysical parameters in oocytes and embryos undergoing CPA equilibration and the development of real-time feedback-control of CPA equilibration, enabling individual oocyte- and embryo-specific optimal protocols.

Machine learning and hypothesis driven optimization of bull semen cryopreservation media.

Cryopreservation provides a critical tool for dairy herd genetics management. Due to widely varying inter- and within-bull post thaw fertility, recent research on cryoprotectant extender medium has not dramatically improved suboptimal post-thaw recovery in industry. This progress is stymied by the interactions between samples and the many components of extender media and is often compounded by industry irrelevant sample sizes. To address these challenges, here we demonstrate blank-slate optimization of bull sperm cryopreservation media by supervised machine learning. We considered two supervised learning models: artificial neural networks and Gaussian process regression (GPR). Eleven media components and initial concentrations were identified from publications in bull semen cryopreservation, and an initial 200 extender-post-thaw motility pairs were used to train and 32 extender-post-thaw motility pairs to test the machine learning algorithms. The median post-thaw motility after coupling differential evolution with GPR the increased from 52.6 ± 6.9% to 68.3 ± 6.0% at generations 7 and 17 respectively, with several media performing dramatically better than control media counterparts. This is the first study in which machine learning was used to determine the best combination of constituents to optimize bull sperm cryopreservation media, and provides a template for optimization in other cell types.