Enhancing clinical utility: deep learning-based embryo scoring model for non-invasive aneuploidy prediction

BACKGROUND

The best method for selecting embryos ploidy is preimplantation genetic testing for aneuploidies (PGT-A). However, it takes more labour, money, and experience. As such, more approachable, non- invasive techniques were still needed. Analyses driven by artificial intelligence have been presented recently to automate and objectify picture assessments.

METHODS

In present retrospective study, a total of 3448 biopsied blastocysts from 979 Time-lapse (TL)-PGT cycles were retrospectively analyzed. The "intelligent data analysis (iDA) Score" as a deep learning algorithm was used in TL incubators and assigned each blastocyst with a score between 1.0 and 9.9.

RESULTS

Significant differences were observed in iDAScore among blastocysts with different ploidy. Additionally, multivariate logistic regression analysis showed that higher scores were significantly correlated with euploidy (p < 0.001). The Area Under the Curve (AUC) of iDAScore alone for predicting euploidy embryo is 0.612, but rose to 0.688 by adding clinical and embryonic characteristics.

CONCLUSIONS

This study provided additional information to strengthen the clinical applicability of iDAScore. This may provide a non-invasive and inexpensive alternative for patients who have no available blastocyst for biopsy or who are economically disadvantaged. However, the accuracy of embryo ploidy is still dependent on the results of next-generation sequencing technology (NGS) analysis.

Time-lapse imaging of morula compaction for selecting high-quality blastocysts: a retrospective cohort study

PURPOSE

Before blastocyst development, embryos undergo morphological and metabolic changes crucial for their subsequent growth. This study aimed to investigate the relationship between morula compaction and blastocyst formation and the subsequent chromosomal status of the embryos.

METHODS

This retrospective cohort study evaluated embryo development (n = 371) using time-lapse imaging; 94 blastocysts underwent preimplantation genetic testing for aneuploidy (PGT-A).

RESULTS

The embryos were classified as fully (Group 1, n = 194) or partially (Group 2, n = 177) compacted. Group 1 had significantly higher proportions of good- and average-quality blastocysts than Group 2 (21.6% vs. 3.4%, p = 0.001; 47.9% vs. 26.6%, p = 0.001, respectively). The time from the morula stage to the beginning and completion of compaction and blastocyst formation was significantly shorter in Group 1 than in Group 2 (78.6 vs. 82.4 h, p = 0.001; 87.0 vs. 92.2 h, p = 0.001; 100.2 vs. 103.7 h, p = 0.017, respectively). Group 1 embryos had larger surface areas than Group 2 embryos at various time points following blastocyst formation. Group 1 blastocysts had significantly higher average expansion rates than Group 2 blastocysts (653.6 vs. 499.2 μm2/h, p = 0.001). PGT-A revealed a higher proportion of euploid embryos in Group 1 than in Group 2 (47.2% vs. 36.6%, p = 0.303).

CONCLUSION

Time-lapse microscopy uncovered a positive relationship between compaction and blastocyst quality and its association with embryo ploidy. Hence, compaction evaluation should be prioritized before blastocyst selection for transfer or cryopreservation.

Artificial intelligence in time-lapse system: advances, applications, and future perspectives in reproductive medicine

With the rising demand for in vitro fertilization (IVF) cycles, there is a growing need for innovative techniques to optimize procedure outcomes. One such technique is time-lapse system (TLS) for embryo incubation, which minimizes environmental changes in the embryo culture process. TLS also significantly advances predicting embryo quality, a crucial determinant of IVF cycle success. However, the current subjective nature of embryo assessments is due to inter- and intra-observer subjectivity, resulting in highly variable results. To address this challenge, reproductive medicine has gradually turned to artificial intelligence (AI) to establish a standardized and objective approach, aiming to achieve higher success rates. Extensive research is underway investigating the utilization of AI in TLS to predict multiple outcomes. These studies explore the application of popular AI algorithms, their specific implementations, and the achieved advancements in TLS. This review aims to provide an overview of the advances in AI algorithms and their particular applications within the context of TLS and the potential challenges and opportunities for further advancements in reproductive medicine.

Comparison of two culture media on morphokinetics and ploidy status of sibling embryos

To investigate the effects of culture media with different lactate concentrations on early embryonic development, data collected from our patients undergoing preimplantation genetic testing (PGT) were assessed using the EmbryoScope™ time-lapse culturing system. After intracytoplasmic sperm injection (ICSI), sibling oocytes were cultured in the same EmbryoScope (Vitrolife) slides including two different commercially available media. The patients with fewer than five mature oocytes were not included in the analyses. All embryos were hatched on day 3, and trophectoderm biopsies (n = 212) were performed accordingly. PGT for aneuploidy (PGT-A) on biopsied materials was carried out using next generation sequencing. Morphokinetic parameters, fertilization, irregular division, degeneration, blastulation, euploidy, and pregnancy rates of embryos cultured in LifeGlobal Global Total medium (LGGT) and Continuous Single Culture-NX Complete medium (CSCM-NXC) were compared. There were no differences observed in time to pronuclear fade, or in time spent as 2-cell (cc2) and 3-cell (s2), to 4-cell, 5-cell, morula and blastocyst stages (P > 0.05). Embryos reached the 2-cell (t2) and 3-cell (t3) stages significantly faster in LGGT (P < 0.05), whereas embryos grown in CSCM-NXC with lower lactate reached starting blastulation significantly sooner (P = 0.026). However, there were no statistical differences observed in fertilization, blastulation, degeneration, irregular division euploidy, and pregnancy rates between the two groups (P > 0.05). Even though pregnancy and fertilization rates did not indicate statistical differences, results are significant to provide better insight on potential roles of lactate in embryo development. These finding will advance the fundamental knowledge of human embryo development and assisted reproductive technologies.

Early embryo development anomalies identified by time-lapse system: prevalence and impacting factors

RESEARCH QUESTION

What is the prevalence of embryo abnormal early cleavage (ACL) identified by time lapse and factors related to patients and treatment that explain ACL occurrence?

DESIGN

A single-centre, retrospective cohort study. Data were collected on all IVF cycles for which embryos were observed in the EmbryoScope® between December 2015 and August 2017. Only diploid zygotes cleaved on day 2 were included. The study included 318 cycles (250 couples and 1343 embryos). Embryo videos were retrospectively analysed for ACL. The prevalence of each type of ACL was recorded. The influence of clinical factors (whether they were intrinsic to patients or specific to IVF treatment) on ACL occurrence was analysed in multivariate multilevel mixed-effect logistic regression analysis.

RESULTS

A high prevalence of ACL was observed: 37.6% (505/1343) of embryos presented at least one ACL, 22.8% (306/1343) a trichotomous mitosis, 25.8% (347/1343) a rapid cleavage, 6.7% (90/1343) a cell fusion and two or more ACL (16.1%). Part of the variation (12-25%) in ACL occurrence could be explained by embryo origin. Trichotomous mitosis and two or more ACL phenotypes were less likely to occur in women with endometriosis or tubal pathology and tubal pathology alone, respectively. No factor related to IVF cycles was found to be statistically associated with ACL occurrence.

CONCLUSIONS

Our findings emphasize the importance of considering embryo origin when interpreting studies focusing on embryo characteristics and factors that could affect their quality. The present study is limited by a small sample size of known embryo implantations and monocentric criterion.

Blastomere movement post first cell division correlates with embryonic compaction and subsequent blastocyst formation

BACKGROUND

Blastomere movement (BMov) occurs after the first cell division in human embryos. This movement has been suggested as a prognostic parameter for pregnancy outcome prediction following cleavage-stage embryo transfer. However, the effect of BMov on preimplantation development and pregnancy outcome after blastocyst transfer remains unclear. Therefore, this study aimed to evaluate whether BMov after the first cell division is correlated with blastocyst formation rate and live birth rate after single vitrified-warmed blastocyst transfer (SVBT).

METHODS

Nine hundred and sixty-six embryos cultured in the EmbryoScope+® time-lapse system were retrospectively analyzed. The BMov type was categorized into three groups; namely, bouncing, wobbling, and twist-and-crumble. The BMov duration (dBMov) between the first (t2) and second cell division (t3) was monitored, and the ratio of dBMov to the duration of the 2-cell stage was calculated [dBMov/(t3-t2)]. Developmental rates to the 4-cell, 8-cell, morula, blastocyst, and expanded blastocyst stages were assessed, as well as blastocyst morphological grade. The correlations between dBMov and clinical pregnancy, ongoing pregnancy, and live birth rates were evaluated.

RESULTS

Increased dBMov/(t3-t2) was significantly correlated with decreased developmental rates to the 8-cell, morula, blastocyst, and expanded blastocyst stages, especially from the 4-cell stage to the morula stage. Analysis of different types of BMov revealed that embryos with bouncing movement exhibited significantly higher developmental rates to the 8-cell, morula, blastocyst, and expanded blastocyst stages compared with embryos with twist-and-crumble movement. The morphological quality of blastocyst-stage embryos with twist-and-crumble movement was significantly lower than that of embryos with bouncing and wobbling movements. The rates of clinical pregnancy, ongoing pregnancy, and live birth after SVBT were not correlated with BMov type or duration.

CONCLUSIONS

Embryonic compaction and subsequent blastocyst formation are adversely affected by twist-and-crumble movement and prolonged movement after the first cell division. Our results indicate that the preimplantation developmental competence of human embryos could be predicted by assessing BMov after the first cell division on day 1.

Prolonged blastomere movement induced by the delay of pronuclear fading and first cell division adversely affects pregnancy outcomes after fresh embryo transfer on Day 2: a time-lapse study

RESEARCH QUESTION

What is the incidence, origin and clinical significance of blastomere movement after the first cell division in the human embryo?

DESIGN

A total of 1096 embryos, cultured in the EmbryoScope+ ® time-lapse system and subjected to a single fresh cleaved embryo transfer, were retrospectively analysed. Type and duration of blastomere movement (dBMov) between the first (t2) and second cell division (t3) was monitored, and the ratio of dBMov during the 2-cell stage [dBMov/(t3-t2)] was calculated. Morphological evaluation of embryos was performed by referring to the size of the blastomere and fragmentation after first division in addition to Veeck's criteria on Day 2. The correlation between dBMov and ongoing pregnancy was evaluated and the association of dBMov with patient and embryonic characteristics was determined.

RESULTS

Both movement type and the value of dBMov/(t3-t2) were significantly associated with asymmetrical first division, fragment formation and morphological grade on Day 2. Multivariate logistic regression analysis revealed that a higher value of dBMov/(t3-t2) significantly correlated with a decreased ongoing pregnancy rate, even after adjustment for co-founders (odds ratio 0.399, P = 0.0419). The time intervals of pronuclear (PN) alignment and PN fading were significantly correlated with the dBMov/(t3-t2) value.

CONCLUSIONS

Embryos with extended blastomere movement after the first cell division, which is associated with the delay of PN fading and first cell division, have a lower competence to initiate an ongoing pregnancy after fresh embryo transfer on Day 2. Thus, blastomere movement could be a useful predictive parameter for selecting embryos at the early cleavage stage.

Pregnancy rates of day 4 and day 5 embryos after culture in an integrated time-lapse incubator

BACKGROUND

The aim of this study was to compare pregnancy rates in patients undergoing IVF/ICSI with embryo transfer after 4 and 5 days of culture in a closed incubation system with integrated time-lapse imaging.

METHODS

Out of n = 2207 in vitro fertilization (IVF)/ intracytoplasmic sperm injection (ICSI) cycles performed between January 2011 and April 2016 at a tertiary referral university hospital, a total of n = 599 IVF/ICSI cycles with prolonged embryo culture in an integrated time-lapse system (EmbryoScope^© (Vitrolife)) until day 4 or 5 were retrospectively analyzed with regard to embryo morphology and pregnancy rates.

RESULTS

A transfer on day 5 compared to a transfer on day 4 did not result in higher implantation and clinical pregnancy rates (IR 29.4% on day 4 versus 33.0% on day 5, p = 0.310; CPR 45.2% on day 4 versus 45.7% on day 5, p = 1.0). The percentage of ideal embryos transferred on day 4 was comparable to the rate of ideal embryos transferred on day 5 (41.6% versus 44.1%, p = 0.508). However, on day 4 a significantly higher number of embryos was transferred (1.92 on day 4 versus 1.84 on day 5, p = 0.023), which did not result in higher rates of multiple pregnancies.

CONCLUSIONS

Pregnancy rates in IVF/ICSI cycles with integrated time-lapse incubation and transfer on day 4 and 5 are comparable. This finding provides the clinician, IVF laboratory and patient with more flexibility.

TRIAL REGISTRATION

This study was retrospectively registered by the local ethics committee of the University of Heidelberg on December 19, 2016 (registration number S-649/2016).