Longitudinal Surface Measurements of Human Blastocysts Show That The Dynamics of Blastocoel Expansion Are Associated With Fertilization Method And Ongoing Pregnancy

Background: Despite all research efforts during this era of novel time-lapse morphokinetic parameters, a morphological grading system is still routinely being used for embryo selection at the blastocyst stage. The blastocyst expansion grade, as evaluated during morphological assessment, is associated with clinical pregnancy. However, this assessment is performed without taking the dynamics of blastocoel expansion into account. Here, we studied the dynamics of blastocoel expansion by comparing longitudinal blastocoel surface measurements using time-lapse embryo culture. Our aim was to first assess if this is impacted by fertilization method and second, to study if an association exists between these measurement and ongoing pregnancy. Methods: This was a retrospective cohort study including 225 couples undergoing 225 cycles of in vitro fertilization (IVF) treatment with time-lapse embryo culture. The fertilization method was either conventional IVF, intracytoplasmic sperm injection (ICSI) with ejaculated sperm or ICSI with sperm derived from testicular sperm extraction (TESE-ICSI). This resulted in 289 IVF embryos, 218 ICSI embryos and 259 TESE-ICSI embryos that reached at least the full blastocyst stage. Blastocoel surface measurements were performed on time-lapse images every hour, starting from full blastocyst formation (tB). Linear mixed model analysis was performed to study the association between blastocoel expansion, the calculated expansion rate (µm2/hour) and both fertilization method and ongoing pregnancy. Results: The blastocoel of both ICSI embryos and TESE-ICSI embryos was significantly smaller than the blastocoel of IVF embryos (beta -1121.6 µm2; 95% CI: -1606.1 to -637.1, beta -646.8 µm2; 95% CI: -1118.7 to 174.8, respectively). Still, the blastocoel of transferred embryos resulting in an ongoing pregnancy was significantly larger (beta 795.4 µm2; 95% CI: 15.4 to 1575.4) and expanded significantly faster (beta 100.9 µm2/hour; 95% CI: 5.7 to 196.2) than the blastocoel of transferred embryos that did not, regardless of the fertilization method. Conclusion: Longitudinal blastocyst surface measurements and expansion rates are promising non-invasive quantitative markers that can aid embryo selection for transfer and cryopreservation.

Validation on Real Data of an Extended Embryo-Uterine Probabilistic Graphical Model for Embryo Selection

Embryo selection is a critical step in assisted reproduction (ART): a good selection criteria is expected to increase the probability of inducing pregnancy. In the past, machine learning methods have been used to predict implantation and to rank the most promising embryos. Here, we study the use of a probabilistic graphical model that assumes independence between embryos’ individual features and cycles characteristics. It also accounts for a third source of uncertainty attributed to unknown factors. We present an empirical validation and analysis of the behavior of the model within real data. The dataset describes 604 consecutive ART cycles carried out at Hospital Donostia (Spain), where embryo selection was performed following the Spanish Association for Reproduction Biology Studies (ASEBIR) protocol, based on morphological features. The performance of our model is evaluated with different metrics and the predicted probability densities are examined to obtain significant insights about the process. Special attention is given to the relation between the model and the ASEBIR protocol. We validate our model by showing that its predictions show correlation with the ASEBIR score when the score is not provided as a feature. However, once the selection based on this protocol has taken place, our model is unable to separate implanted and failed embryos when only embryo individual features are used. From here, we can conclude that ASEBIR score provides a good summary of morphological features.

Longitudinal Surface Measurements of Human Blastocysts Show That the Dynamics of Blastocoel Expansion Are Associated With Fertilization Method and Ongoing Pregnancy

Background: Despite all research efforts during this era of novel time-lapse morphokinetic parameters, a morphological grading system is still routinely being used for embryo selection at the blastocyst stage. The blastocyst expansion grade, as evaluated during morphological assessment, is associated with clinical pregnancy. However, this assessment is performed without taking the dynamics of blastocoel expansion into account. Here, we studied the dynamics of blastocoel expansion by comparing longitudinal blastocoel surface measurements using time-lapse embryo culture. Our aim was to first assess if this is impacted by fertilization method and second, to study if an association exists between these measurement and ongoing pregnancy. Methods: This was a retrospective cohort study including 225 couples undergoing 225 cycles of in vitro fertilization (IVF) treatment with time-lapse embryo culture. The fertilization method was either conventional IVF, intracytoplasmic sperm injection (ICSI) with ejaculated sperm or ICSI with sperm derived from testicular sperm extraction (TESE-ICSI). This resulted in 289 IVF embryos, 218 ICSI embryos and 259 TESE-ICSI embryos that reached at least the full blastocyst stage. Blastocoel surface measurements were performed on time-lapse images every hour, starting from full blastocyst formation (tB). Linear mixed model analysis was performed to study the association between blastocoel expansion, the calculated expansion rate (µm2/hour) and both fertilization method and ongoing pregnancy. Results: The blastocoel of both TESE-ICSI embryos and ejaculated sperm ICSI embryos was significantly smaller than the blastocoel of IVF embryos (beta -647.7 µm2; 95% confidence interval (CI): -1133.6 to -161.9, beta -1017.0 µm2; 95% CI: -1525.1 to -508.8, respectively). In addition, the blastocoel of embryos resulting in an ongoing pregnancy was significantly larger (beta 795.4 µm2; 95% CI: 15.4 to 1575.4) and expanded significantly faster (beta 100.9 µm2/hour; 95% CI: 5.7 to 196.2) than the blastocoel of embryos that did not result in an ongoing pregnancy. Conclusion: Longitudinal blastocyst surface measurements and expansion rates are promising non-invasive quantitative markers that can aid the embryo selection for transfer and cryopreservation.

Does artificial intelligence have a role in the IVF clinic?

Lay summary The success of IVF has remained stagnant for a decade. The focus of a great deal of research is to improve on the current ~30% success rate of IVF. Artificial intelligence (AI), or machines that mimic human intelligence, has been gaining traction for its potential to improve outcomes in medicine, such as cancer diagnosis from medical images. In this commentary, we discuss whether AI has the potential to improve fertility outcomes in the IVF clinic. Based on existing research, we examine the potential of adopting AI within multiple facets of an IVF cycle, including egg/sperm and embryo selection, as well as formulation of an IVF treatment regimen. We discuss both the potential benefits and concerns of the patient and clinician in adopting AI in the clinic. We outline hurdles that need to be overcome prior to implementation. We conclude that AI has an important future in improving IVF success.