Time-lapse deselection model for human day 3 in vitro fertilization embryos: the combination of qualitative and quantitative measures of embryo growth

Abnormal cleavage up to Day 3 does not compromise live birth and neonatal outcomes of embryos that have achieved full blastulation: a retrospective cohort study

STUDY QUESTION

Do embryos displaying abnormal cleavage (ABNCL) up to Day 3 have compromised live birth rates and neonatal outcomes if full blastulation has been achieved prior to transfer?

SUMMARY ANSWER

ABNCL is associated with reduced full blastulation rates but does not impact live birth rates and neonatal outcomes once full blastulation has been achieved.

WHAT IS KNOWN ALREADY?

It is widely accepted that ABNCL is associated with reduced implantation rates of embryos when transferred at the cleavage stage. However, evidence is scarce in the literature reporting birth outcomes from blastocysts arising from ABNCL embryos, likely because they are ranked low priority for transfer.

STUDY DESIGN, SIZE, DURATION

This retrospective cohort study included 1562 consecutive autologous in vitro fertilization cycles (maternal age 35.1 ± 4.7 years) performed at Fertility North, Australia between January 2017 and June 2022. Fresh transfers were performed on Day 3 or 5, with remaining embryos cultured up to Day 6 before vitrification. A total of 6019 embryos were subject to blastocyst culture, and a subset of 664 resulting frozen blastocysts was included for live birth and neonatal outcome analyses following single transfers.

PARTICIPANTS/MATERIALS, SETTING, METHODS

ABNCL events were annotated from the first mitotic division up to Day 3, including direct cleavage (DC), reverse cleavage (RC) and <6 intercellular contact points at the 4-cell stage (<6ICCP). For DC and RC in combination, the ratios of affected blastomeres over the total number of all blastomeres up to Day 3 were also recorded. All pregnancies were followed up until birth with gestational age, birthweight, and sex of the baby being recorded.

MAIN RESULTS AND THE ROLE OF CHANCE

Full blastulation rates for embryos showing DC (19.5%), RC (41.7%), <6ICCP (58.8%), and mixed (≥2) ABNCL types (26.4%) were lower than the rates for those without ABNCL (67.2%, P < 0.01 respectively). Subgroup analysis showed declining full blastulation rates with increasing ratios of combined DC/RC affected blastomeres over all blastomeres up to the 8-cell stage (66.2% when 0 affected, 47.0% when 0.25 affected, 27.4% when 0.5 affected, 14.5% when 0.75 affected, and 7.7% when all affected, P < 0.01). However, once full blastulation had been achieved, no difference was detected between DC, RC, <6ICCP, and no ABNCL blastocysts following single frozen transfers in subsequent live birth rates (25.9%, 33.0%, 36.0% versus 30.8%, P > 0.05, respectively), gestational age (38.7 ± 1.6, 38.5 ± 1.2, 38.3 ± 3.5 versus 38.5 ± 1.8 weeks, P > 0.05, respectively) and birthweight (3343.0 ± 649.1, 3378.2 ± 538.4, 3352.6 ± 841.3 versus 3313.9 ± 509.6 g, P > 0.05, respectively). Multiple regression (logistic or linear as appropriate) confirmed no differences in all of the above measures after accounting for potential confounders.

LIMITATIONS, REASONS FOR CAUTION

Our study is limited by its retrospective nature, making it impossible to control every known or unknown confounder. Embryos in our dataset, being surplus after selection for fresh transfer, may not represent the general embryo population.

WIDER IMPLICATIONS OF THE FINDINGS

Our findings highlight the incremental impact of ABNCL, depending on the ratio of affected blastomeres up to Day 3, on subsequent full blastulation. The reassuring live birth and neonatal outcomes of ABNCL blastocysts imply a potential self-correction mechanism among those embryos reaching the blastocyst stage, which provides valuable guidance for clinical practice and patient counseling.

STUDY FUNDING/COMPETTING INTEREST(S)

This research is supported by an Australian Government Research Training Program (RTP) Scholarship. All authors report no conflict of interest.

TRIAL REGISTRATION NUMBER

N/A.

A brief history of artificial intelligence embryo selection: from black-box to glass-box

With the exponential growth of computing power and accumulation of embryo image data in recent years, artificial intelligence (AI) is starting to be utilized in embryo selection in IVF. Amongst different AI technologies, machine learning (ML) has the potential to reduce operator-related subjectivity in embryo selection while saving labor time on this task. However, as modern deep learning (DL) techniques, a subcategory of ML, are increasingly used, its integrated black-box attracts growing concern owing to the well-recognized issues regarding lack of interpretability. Currently, there is a lack of randomized controlled trials to confirm the effectiveness of such black-box models. Recently, emerging evidence has shown underperformance of black-box models compared to the more interpretable traditional ML models in embryo selection. Meanwhile, glass-box AI, such as interpretable ML, is being increasingly promoted across a wide range of fields and is supported by its ethical advantages and technical feasibility. In this review, we propose a novel classification system for traditional and AI-driven systems from an embryology standpoint, defining different morphology-based selection approaches with an emphasis on subjectivity, explainability, and interpretability.

Sperm Selection Using Zona Pellucida-Binding Enhanced Embryo Morphokinetic and Clinical Outcomes in ICSI: A Sibling Oocytes Study

The objective was to investigate the embryo morphokinitics using a time-lapse monitoring (TLM) system and assessment of clinical outcomes following intracytoplasmic sperm injection (ICSI) with zona pellucida (ZP)-bound sperm selection and conventional methods. A total of 371 metaphase II (MII) oocytes from 50 ICSI cycles were studied. Sibling oocytes were randomly divided into control (n = 199) and ZP-bound group (n = 172). All resulting zygotes were cultured and monitored in the TLM system up to Day 3 after ICSI. Fertilization rate, early embryo development, and clinical outcomes were evaluated. No significant differences were found in fertilization rate, time-lapse qualitative and quantitative measures, pronuclear fading time (PNF) t2, t3, t4, t5, t6, and t7 (times of cleavage to 2, 3, 4, 5, 6, and 7 cells), respectively. However, the t8 (time of cleavage to eight cells) and cc3 (duration of third cell cycle) revealed a significant difference between control and ZP-bound groups (p < .05). A significant difference between the two groups (p < .05) in the rates of Grade A embryos (according to Basile algorithm), chemical pregnancy, clinical pregnancy, and implantation was observed. Sperm selection using biological materials, such as ZP, improved both embryo quality and pregnancy outcomes, despite not affecting the early embryo development and morphokinetic parameters up to t8. This prospective randomized sibling oocyte trial was registered in October 2020 to January 2022 (IRCT20200705048021N1).

Spontaneous collapse as a prognostic marker for human blastocysts: a systematic review and meta-analysis

STUDY QUESTION

Is spontaneous collapse (SC) by human blastocysts a prognostic factor in IVF treatment?

SUMMARY ANSWER

SC in human blastocyst is associated with reduced euploid embryo and pregnancy rates.

WHAT IS KNOWN ALREADY

SC of the human blastocyst is a phenomenon that was revealed relatively recently following the clinical application of time-lapse monitoring in IVF laboratories. The ploidy and clinical prognosis of affected blastocysts are still poorly understood, with inconsistent reports. Systematic reviews and meta-analyses on this topic are currently absent in the literature but its potential as a marker of embryo viability holds great clinical value. In this study, we aimed to comprehensively evaluate the potential of SC as a prognostic factor in regard to ploidy status, and pregnancy, live birth and miscarriage rates.

STUDY DESIGN, SIZE, DURATION

A systematic review and meta-analysis were performed according to PRISMA guidelines, with a protocol registered with PROSPERO (CRD42022373749). A search of MEDLINE, EMBASE, and the Cochrane Library for relevant studies was carried out on 10 October 2022, using key words relevant to 'blastocyst collapse' and 'time-lapse imaging'.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Two independent reviewers systematically screened and evaluated each study in terms of participants, exposure, comparator, and outcomes (PECO). The Quality In Prognosis Studies tool was used for quality assessment. Data were extracted according to Cochrane methods. Pregnancy, live birth, ploidy, or miscarriage data were summarized by risk ratios (RRs) or odds ratios and their 95% CIs. All meta-analyses were performed with random-effects models.

MAIN RESULTS AND THE ROLE OF CHANCE

Following removal of duplicates, a total of 196 records were identified by the initial search. After screening according to PECO, 19 articles were included for further eligibility assessment. For meta-analysis, seven retrospective cohort studies were eventually included. After data pooling, the incidence of blastocyst SC was 37.0% (2516/6801) among seven studies (ranging from 17.4% to 56.2%). SC was associated with significantly lower clinical pregnancy rates (two studies, n = 736; RR = 0.77, 95% CI = 0.62-0.95; I2 = 30%), ongoing pregnancy rates (five studies, n = 2503; RR = 0.66, 95% CI = 0.53-0.83; I2 = 60%), and reduced euploidy rates (three studies, n = 3569; RR = 0.70, 95% CI = 0.59-0.83; I2 = 69%). Nevertheless, live birth rates (two studies, n = 816; RR = 0.76, 95% CI = 0.55-1.04; I2 = 56%) and miscarriage rate (four studies, n = 1358; RR = 1.31, 95% CI = 0.95-1.80; I2 = 0%) did not differ between blastocysts with or without SC. There was, however, significant heterogeneity between the studies included for evaluation of ongoing pregnancy rates (I2 = 60%, P = 0.04), live birth rates (I2 = 56%, P = 0.13), and ploidy rates (I2 = 69%, P = 0.04). Subgroup analyses were conducted according to different definitions of SC, number of collapse events, and whether the transferred blastocyst had undergone preimplantation genetic testing for aneuploidy; with inconclusive findings across subgroups.

LIMITATIONS, REASONS FOR CAUTION

All studies in the meta-analysis were retrospective with varying levels of heterogeneity for different outcomes. Not all studies had accounted for potential confounding factors, therefore only unadjusted data could be used in the main meta-analysis. Studies employed slightly different strategies when defining blastocyst SC. Standardization in the definition for SC is needed to improve comparability between future studies.

WIDER IMPLICATIONS OF THE FINDINGS

Our results indicate that blastocyst SC has negative implications for a pregnancy. Such blastocysts should be given a low ranking when selecting from a cohort for intrauterine transfer. Blastocyst SC should be considered as a contributing variable when building blastocyst algorithms to predict pregnancy or live birth.

STUDY FUNDING/COMPETING INTEREST(S)

There is no external funding to report. All authors report no conflict of interest.

REGISTRATION NUMBER

PROSPERO 2022 CRD42022373749.

External validation of a model for selecting day 3 embryos for transfer based upon deep learning and time-lapse imaging

RESEARCH QUESTION

Could objective embryo assessment using iDAScore Version 2.0 perform as well as conventional morphological assessment?

DESIGN

A retrospective cohort study of fresh day 3 embryo transfer cycles was conducted at a large reproductive medicine centre. In total, 7786 embryos from 4328 cycles with known implantation data were cultured in a time-lapse incubator and included in the study. Fetal heartbeat (FHB) rate was analysed retrospectively using iDAScore Version 2.0 and conventional morphological assessment associated with the transferred embryos. The pregnancy-prediction performance of the two assessment methods was compared using area under the curve (AUC) values for predicting FHB.

RESULTS

AUC values were significantly higher for iDAScore compared with morphological assessment for all cycles (0.62 versus 0.60; P = 0.005), single-embryo transfer cycles (0.63 versus 0.60; P = 0.043) and double-embryo transfer cycles (0.61 versus 0.59; P = 0.012). For the age subgroups, AUC values were significantly higher for iDAScore compared with morphological assessment in the <35 years subgroup (0.62 versus 0.60; P = 0.009); however, no significant difference was found in the ≥35 years subgroup. In terms of the number of blastomeres, AUC values were significantly higher for iDAScore compared with morphological assessment for both the <8c subgroup (0.67 versus 0.56; P < 0.001) and the ≥8c subgroup (0.58 versus 0.55; P = 0.012).

CONCLUSIONS

iDAScore Version 2.0 performed as well as, or better than, conventional morphological assessment in fresh day 3 embryo transfer cycles. iDAScore Version 2.0 may therefore constitute a promising tool for selecting embryos with the highest likelihood of implantation.

Using the embryo-uterus statistical model to predict pregnancy chances by using cleavage stage morphokinetics and female age: two centre-specific prediction models and mutual validation

BACKGROUND

The predictive capability of time-lapse monitoring (TLM) selection algorithms is influenced by patient characteristics, type and quality of data included in the analysis and the used statistical methods. Previous studies excluded DET cycles of which only one embryo implanted, introducing bias into the data. Therefore, we wanted to develop a TLM prediction model that is able to predict pregnancy chances after both single- and double embryo transfer (SET and DET).

METHODS

This is a retrospective study of couples (n = 1770) undergoing an in vitro fertilization cycle at the Erasmus MC, University Medical Centre Rotterdam (clinic A) or the Reinier de Graaf Hospital (clinic B). This resulted in 2058 transferred embryos with time-lapse and pregnancy outcome information. For each dataset a prediction model was established by using the Embryo-Uterus statistical model with the number of gestational sacs as the outcome variable. This process was followed by cross-validation.

RESULTS

Prediction model A (based on data of clinic A) included female age, t3-t2 and t5-t4, and model B (clinic B) included female age, t2, t3-t2 and t5-t4. Internal validation showed overfitting of model A (calibration slope 0.765 and area under the curve (AUC) 0.60), and minor overfitting of model B (slope 0.915 and AUC 0.65). External validation showed that model A was capable of predicting pregnancy in the dataset of clinic B with an AUC of 0.65 (95% CI: 0.61-0.69; slope 1.223, 95% CI: 0.903-1.561). Model B was less accurate in predicting pregnancy in the dataset of clinic A (AUC 0.60, 95% CI: 0.56-0.65; slope 0.671, 95% CI: 0.422-0.939).

CONCLUSION

Our study demonstrates a novel approach to the development of a TLM prediction model by applying the EU statistical model. With further development and validation in clinical practice, our prediction model approach can aid in embryo selection and decision making for SET or DET.

Associations between morphokinetic parameters of temporary-arrest embryos and the clinical prognosis in FET cycles

Infertility is a major health concern worldwide. This retrospective study aimed to assess the predictive value of the morphokinetic parameters of temporary-arrest embryos for the pregnancy outcomes of women undergoing frozen embryo transfer (FET) cycles. In this study, we evaluated 244 FET cycles with 431 day-4 temporary-arrest embryos. They were categorized into two groups (pregnancy and non-pregnancy) according to the pregnancy outcomes of the women after embryo transfer on day 5, and their fundamental characteristics were compared. The morphokinetic parameters from the time-lapse monitoring system were assessed according to different pregnancy outcomes. The mean number of embryo blastomeres thawed on day 3 in the pregnancy group was 7.47, which was significantly higher than the number in the non-pregnancy group (p < 0.01). Besides, embryos in the non-pregnancy group contained more embryo fragments and lower grades than those in the pregnancy group (p < 0.001). Furthermore, morphokinetic parameters: tPNa, t2, t5, and t5_tPNf showed a statistical difference between the pregnancy and non-pregnancy groups (p < 0.05). Receiver-operating characteristic analysis revealed that the time from pronuclear fading to the 5-cell stage (t5_PNF) predicted the clinical prognosis outcomes (area under the curve = 0.64; 95% confidence interval [CI], 0.58–0.70; p < 0.001). The morphokinetic parameter t5_PNF could be regarded as a potential implantation predictor in our study.

Morphology of inner cell mass: a better predictive biomarker of blastocyst viability

Background

Transfer of embryos at the blastocyst stage is one of the best approaches for achieving a higher success rate in In vitro fertilization (IVF) treatment as it demonstrates an improved uterine and embryonic synchrony at implantation. Despite novel biochemical and genetic markers proposed for the prediction of embryo viability in recent years, the conventional morphological grading of blastocysts remains the classical way of selection in routine practice. This study aims to investigate the association between the morphological features of blastocysts and pregnancy outcomes.

Methods

This prospective study included women undergoing single or double frozen blastocyst transfers following their autologous cycles in a period between October 2020 and September 2021. The morphological grades (A-good, B-average, and C-poor) of inner cell mass (ICM) and trophectoderm (TE) of blastocysts with known implantation were compared to assess their predictive potential of pregnancy outcome. It was further explored by measuring the relationship between the two variables using logistic regression and receiver operating characteristic (ROC) analysis.

Results

A total of 1,972 women underwent frozen embryo transfer (FET) cycles with a total of 3,786 blastocysts. Known implantation data (KID) from 2,060 blastocysts of 1,153 patients were subjected to statistical analysis, the rest were excluded. Implantation rates (IR) from transfer of ICM/TE grades AA, AB, BA, BB were observed as 48.5%, 39.4%, 23.4% and 25% respectively. There was a significantly higher IR observed in blastocysts with ICM grade A (p < 0.001) than those with B irrespective of their TE scores. The analysis of the interaction between the two characteristics confirmed the superiority of ICM over TE as a predictor of the outcome. The rank biserial correlation value for ICM was also greater compared to that of TE (0.11 vs 0.05).

Conclusion

This study confirms that the morphology of ICM of the blastocyst is a stronger predictor of implantation and clinical pregnancy than that of TE and can be utilized as a biomarker of viability.

Isolation of cfDNA from spent culture media and its association with implantation rate and maternal immunomodulation

OBJECTIVES

This investigation aims to evaluate the association between the concentration of cell-free DNA (cfDNA) in the spent culture medium (SCM) with implantation rate and the maternal immune system in the invitro fertilization (IVF). In this study, 30 embryos were cultured and scored according to Gardner's criteria. SCM was gathered on day five from every embryo to analyze the quantity of cfDNA. The real-time PCR technique evaluated the expression level of transcription factors, including Foxp3, RORγt, GATA3, and T-bet. The percentage of Th1, Th2, Th17, Treg, NK cells, and NK cells cytotoxicity was evaluated by flow cytometry.

RESULTS

The concentration of cfDNA in the β-HCG (-), β-HCG ( +), and ongoing pregnancy groups were 20.70 ± 9.224 ng/µL, 27.97 ± 7.990 ng/µL, and 28.91 ± 8.566 ng/µL, respectively. The ratio of Th1/Th2 and Th17/Treg reduced significantly in pregnant women, as well as the level of NK cells and NK cytotoxicity cells fell dramatically in the ongoing pregnancy group. The expression level of RORγt and T-bet declined while the expression level of Foxp3 and GATA3 increased considerably in pregnant mothers. Our investigation revealed that the concentration level of cfDNA in SCM could not be associated with implantation rate, prediction of ongoing pregnancy, and maternal immune system.

Asynchronous division at 4-8-cell stage of preimplantation embryos affects live birth through ICM/TE differentiation

To improve the performance of assisted reproductive technology, it is necessary to find an indicator that can identify and select embryos that will be born or be aborted. We searched for indicators of embryo selection by comparing born/abort mouse embryos. We found that asynchronous embryos during the 4-8-cell stage were predisposed to be aborted. In asynchronous mouse embryos, the nuclear translocation of YAP1 in some blastomeres and compaction were delayed, and the number of ICMs was reduced. Hence, it is possible that asynchronous embryos have abnormal differentiation. When the synchrony of human embryos was observed, it was confirmed that embryos that did not reach clinical pregnancy had asynchrony as in mice. This could make synchrony a universal indicator common to all animal species.

Development of a dynamic machine learning algorithm to predict clinical pregnancy and live birth rate with embryo morphokinetics

Objective

Design

Setting

Patient(s)

Intervention(s)

Main Outcome Measure(s)

Result(s)

Conclusion(s)

The KIDScore™ D3 scoring system contributes to the prediction of embryonic development potential: A promising tool for screening high-quality embryos

Using the KIDScoreTM D3 (KID3) scoring system, day 3 embryos observed by time-lapse imaging (TLI) were scored to explore the predictive value of the KID scoring system on the developmental potential of embryos. The kinetic parameters of 477 normal fertilized embryos from 77 patients who underwent TLI in our hospital from January 2019 to June 2020 were evaluated by KID3, and the embryos were divided into five groups according to the scores for retrospective analysis of blastocyst formation. Additionally, the high-quality blastocyst formation rate, pregnancy rate and early abortion rate were analyzed via KID3 and traditional morphological assessments, and comparisons of differences among different ages were also performed. In the KID3 estimate, the blastocyst or high-quality blastocyst formation rate in the score 5 group was markedly higher than that in the score 1–4 groups. Blastocyst or high-quality blastocyst formation rates in the A group (the results of two evaluation tools indicated they were excellent embryos) and the B group (KID3: excellent embryos, traditional evaluation: not excellent embryos) were evidently increased in comparison with the C or D group (KID3: not excellent embryos, traditional evaluation: excellent embryo or not, respectively). Furthermore, the percentages of score 5 embryos, blastocyst and high-quality blastocyst formation rates for patients ≥ 35 years old were markedly decreased compared with those for patients < 34 years old, while the trends of nondiploid cleavage, multinucleation and asymmetric division were the opposite. Collectively, the KID3 scoring system may be a promising predictive tool for screening embryos with better developmental potential.

Prediction of embryo implantation rate using a sole parameter of timing of starting blastulation

A time-lapse monitoring system provides a complete picture of the dynamic embryonic development process and simultaneously supplies extensive morphokinetic data. The objective of this study was to investigate whether the use of the morphokinetic parameter of time of starting blastulation (tSB) can improve the implantation rate of day-5 transferred blastocyst selected based on morphological parameters. In this retrospective study we analyzed the morphokinetics of 196 day-5 transferred blastocysts, selected solely based on morphological parameters. The interval time from intracytoplasmic sperm injection (ICSI) to time of starting blastocyst formation (tSB) was calculated for each embryo. The overall implantation rate of transferred blastocyst, selected based only on morphological parameters, was 49.2%. Implantation rate, determined retrospectively, was significantly higher (58.8% versus 42.6%, P = 0.02) for embryos with a short interval time to tSB (78-95.9 h) compared with embryos with a longer timeframe (96-114 h). Time of expanded blastocyst (tEB) post-ICSI was also significantly associated with implantation; however, this parameter was not available for all the embryos at time of transfer. When we tested only high ranked KIDScore day-3 sub-group embryos, the implantation rate was significantly higher in short interval time embryos compared with longer interval time embryos (62.2% vs. 45.5%, respectively, P = 0.02).These observations emphasize the importance of the timing of starting blastulation over blastocyst morphological parameters and may provide a preferable criterion for good morphology day-5 blastocyst selection.

Pseudo contrastive labeling for predicting IVF embryo developmental potential

In vitro fertilization is typically associated with high failure rates per transfer, leading to an acute need for the identification of embryos with high developmental potential. Current methods are tailored to specific times after fertilization, often require expert inspection, and have low predictive power. Automatic methods are challenged by ambiguous labels, clinical heterogeneity, and the inability to utilize multiple developmental points. In this work, we propose a novel method that trains a classifier conditioned on the time since fertilization. This classifier is then integrated over time and its output is used to assign soft labels to pairs of samples. The classifier obtained by training on these soft labels presents a significant improvement in accuracy, even as early as 30 h post-fertilization. By integrating the classification scores, the predictive power is further improved. Our results are superior to previously reported methods, including the commercial KIDScore-D3 system, and a group of eight senior professionals, in classifying multiple groups of favorable embryos into groups defined as less favorable based on implantation outcomes, expert decisions based on developmental trajectories, and/or genetic tests.

Time-Lapse Systems: A Comprehensive Analysis on Effectiveness

Time-lapse systems have quickly become a common feature of in vitro fertilization laboratories all over the world. Since being introduced over a decade ago, the alleged benefits of time-lapse technology have continued to grow, from undisturbed culture conditions and round the clock, noninvasive observations to more recent computer-assisted selection of embryos through the development of algorithms. Despite the global uptake of time-lapse technology, its real impact on clinical outcomes is still controversial. This review aims to explore the different features offered by time-lapse technology, discussing incubation, algorithms, artificial intelligence and the regulation of nonessential treatment interventions, while assessing evidence on whether any benefit is offered over conventional technology.

Morphometric and morphokinetic differences in the sperm- and oocyte-originated pronuclei of male and female human zygotes: a time-lapse study

PURPOSE

To study the morphometric and morphokinetic profiles of pronuclei (PN) between male and female human zygotes.

METHOD(S)

This retrospective cohort study included 94 consecutive autologous single day 5 transfer cycles leading to a singleton live birth. All oocytes were placed in the EmbryoScope + incubator post-sperm injection with all annotations performed retrospectively by one embryologist (L-SO). Timing parameters included 2nd polar body extrusion (tPB2), sperm-originated PN (tSPNa) or oocyte-originated PN (tOPNa) appearance, and PN fading (tPNF). Morphometrics were evaluated at 8 (stage 1), 4 (stage 2), and 0 h before PNF (stage 3), measuring PN area (um²), PN juxtaposition, and nucleolar precursor bodies (NPB) arrangement.

RESULTS

Male zygotes had longer time intervals of tPB2_tSPNa than female zygotes (4.8 ± 0.2 vs 4.2 ± 0.1 h, OR = 1.442, 95% CI 1.009-2.061, p = 0.044). SPN increased in size from stage 1 through 2 to 3 (435.3 ± 7.2, 506.7 ± 8.0, and 556.3 ± 8.9 um², p = 0.000) and OPN did similarly (399.0 ± 6.1, 464.3 ± 6.7, and 513.8 ± 6.5 um², p = 0.000), with SPN being significantly larger than OPN at each stage (p < 0.05 respectively). More male than female zygotes reached central PN juxtaposition at stage 1 (76.7% vs 51.0%, p = 0.010), stage 2 (97.7% vs 86.3%, p = 0.048), and stage 3 (97.7% vs 86.3%, p = 0.048). More OPN showed aligned NPBs than in SPN at stage 1 only (44.7% vs 28.7%, p = 0.023).

CONCLUSION(S)

Embryos with different sexes display different morphokinetic and morphometric features at the zygotic stage. Embryo selection using such parameters may lead to unbalanced sex ratio in resulting offspring.

Interpretable, not black-box, artificial intelligence should be used for embryo selection

Artificial intelligence (AI) techniques are starting to be used in IVF, in particular for selecting which embryos to transfer to the woman. AI has the potential to process complex data sets, to be better at identifying subtle but important patterns, and to be more objective than humans when evaluating embryos. However, a current review of the literature shows much work is still needed before AI can be ethically implemented for this purpose. No randomized controlled trials (RCTs) have been published, and the efficacy studies which exist demonstrate that algorithms can broadly differentiate well between 'good-' and 'poor-' quality embryos but not necessarily between embryos of similar quality, which is the actual clinical need. Almost universally, the AI models were opaque ('black-box') in that at least some part of the process was uninterpretable. This gives rise to a number of epistemic and ethical concerns, including problems with trust, the possibility of using algorithms that generalize poorly to different populations, adverse economic implications for IVF clinics, potential misrepresentation of patient values, broader societal implications, a responsibility gap in the case of poor selection choices and introduction of a more paternalistic decision-making process. Use of interpretable models, which are constrained so that a human can easily understand and explain them, could overcome these concerns. The contribution of AI to IVF is potentially significant, but we recommend that AI models used in this field should be interpretable, and rigorously evaluated with RCTs before implementation. We also recommend long-term follow-up of children born after AI for embryo selection, regulatory oversight for implementation, and public availability of data and code to enable research teams to independently reproduce and validate existing models.

Change in the Strategy of Embryo Selection with Time-Lapse System Implementation-Impact on Clinical Pregnancy Rates

Time-lapse systems (TLS) and associated algorithms are interesting tools to improve embryo selection. This study aimed to evaluate how TLS and KIDScore™ algorithm changed our practices of embryo selection, as compared to a conventional morphological evaluation, and improved clinical pregnancy rates (CPR). In the study group (year 2020, n = 303 transfers), embryos were cultured in an EmbryoScope+ time-lapse incubator. A first team observed embryos conventionally once a day, while a second team selected the embryos for transfer based on time-lapse recordings. In the control group (year 2019, n = 279 transfers), embryos were selected using the conventional method, and CPR were recorded. In 2020, disagreement between TLS and the conventional method occurred in 32.1% of transfers, more often for early embryos (34.7%) than for blastocysts (20.5%). Irregular morphokinetic events (direct or reverse cleavage, multinucleation, abnormal pronuclei) were detected in 54.9% of the discordant embryos. When it was available, KIDScore™ was decreased for 73.2% of the deselected embryos. Discordant blastocysts mainly corresponded with a decrease in KIDScore™ (90.9%), whereas discordant Day 3 embryos resulted from a decreased KIDScore™ and/or an irregular morphokinetic event. CPR was significantly improved in the TLS group (2020), as compared to the conventional group (2019) (32.3% vs. 21.9%, p = 0.005), even after multivariate analysis. In conclusion, TLS is useful to highlight some embryo development abnormalities and identify embryos with the highest potential for pregnancy.

Sperm DNA fragmentation measured by sperm chromatin dispersion impacts morphokinetic parameters, fertilization rate and blastocyst quality in ICSI treatments

To determine the effects of sperm DNA fragmentation (SDF) on embryo morphokinetic parameters, cleavage patterns and embryo quality, this retrospective study analyzed 151 intracytoplasmic sperm injection (ICSI) cycles (1152 embryos collected) between November 2016 and June 2019. SDF was assessed using sperm chromatin dispersion. The cycles were divided into two groups based on the SDF rate: SDF < 15% (n = 114) and SDF ≥ 15% (n = 37). The embryo morphokinetic parameters, cleavage patterns, and embryo quality were compared between the two groups. The morphokinetic parameters tPNf, t2, t3, t4, t5, t6, and t8 were achieved significantly earlier in the SDF < 15% group compared with in the SDF ≥ 15% group. The fertilization and 2PN rates seemed to be significantly higher in the SDF < 15% group compared with in the SDF ≥ 15% group, while the abnormal cleavage rates were similar. However, a significantly higher rate of chaotic cleavage (CC) was observed in the SDF ≥ 15% group. The D3 high-quality embryo and available embryo rates were similar between the two groups. The blastocyst formation, high-quality blastocyst, and available blastocyst rates in the SDF < 15% group were significantly higher than those in the SDF ≥ 15% group. With an increase in SDF level, the chemical pregnancy, clinical pregnancy and implantation rates tended to decrease, while the miscarriage rate increased. This study demonstrated that SDF ≥ 15% reduces the fertilization rate of ICSI cycles and affects certain morphokinetic parameters. A higher SDF level can also induce a higher rate of CC, with subsequent decreases in the blastocyst formation rate and blastocyst quality.

Improving embryo selection by the development of a laboratory-adapted time-lapse model

OBJECTIVE

To study whether a powerful, in-house, embryo-selection model can be developed for a specific in vitro fertilization (IVF) laboratory where embryos were already selected for transfer using general models.

DESIGN

In total, 12,944 fertilized oocytes were incubated in an EmbryoScope (Vitrolife, Göteborg, Sweden) at our laboratory. Embryos were selected for transfer or freezing using general models. There were 1,879 embryos with known implantation data (KID), of which 425 had positive KIDs. For the outcome, we set 3 endpoints for KID's definition: gestational sac, clinical pregnancy, and live birth. Results of a comparison between KID-positive and -negative embryos for cell division timings were analyzed separately for intracytoplasmic sperm injection (ICSI) and IVF embryos in patients aged 18-41 years.

SETTING

IVF center.

PATIENTS

The study included 1,075 women undergoing IVF or ICSI treatment between June 2013 and February 2019.

INTERVENTION(S)

None.

MAIN OUTCOME MEASURE(S)

The KID-positive and -negative embryos were analyzed for statistical differences in cell division timing and cell cycle intervals. We used the EmbryoScope Stats software (Unisense FertiliTech, Aarhus, Denmark) for model development. The statistically different timing parameters were tested for their contribution to scoring in the model. The algorithms were tested for area under the receiver operating characteristic curve (AUC) in the KID embryos for developing day-2, -3, and -5 embryo-selection models. The validation of these algorithms was performed using calibration/validation procedures.

RESULTS

Because significant differences in morphokinetics were found between the KID-positive and KID-negative embryos in our laboratory, it was possible to use our specific KID data to develop an in-house model. The algorithms were developed for embryo selection on days 2, 3, and 5 in the ICSI embryos. In most cases, AUC was >0.65, which indicated that these models were valid in our laboratory. In addition, these AUC values were obtained from all gestational sac, clinical pregnancy, and live birth KID embryo databases tested. An increase in the predictability of the models was observed from days 2-3 to day 5 models. The AUC test results ranged between 0.657 and 0.673 for day 2 and day 3, respectively, and 0.803 for the day 5 model.

CONCLUSION

A model based on laboratory-specific morphokinetics was found to be complementary to general models and an important additive tool for improving single embryo selection. Developing an in-house laboratory-specific model requires many stages of sorting and characterization. Many insights were drawn about the model developing process. These may facilitate and improve the process in other laboratories.

Metabolic activity of human blastocysts correlates with their morphokinetics, morphological grade, KIDScore and artificial intelligence ranking

STUDY QUESTION

Is there a relationship between blastocyst metabolism and biomarkers of embryo viability?

SUMMARY ANSWER

Blastocysts with higher developmental potential and a higher probability of resulting in a viable pregnancy consume higher levels of glucose and exhibit distinct amino acid profiles.

WHAT IS KNOWN ALREADY

Morphological and morphokinetic analyses utilized in embryo selection provide insight into developmental potential, but alone are unable to provide a direct measure of embryo physiology and inherent health. Glucose uptake is a physiological biomarker of viability and amino acid utilization is different between embryos of varying qualities.

STUDY DESIGN, SIZE, DURATION

Two hundred and nine human preimplantation embryos from 50 patients were cultured in a time-lapse incubator system in both freeze all and fresh transfer cycles. A retrospective analysis of morphokinetics, morphology (Gardner grade), KIDScore, artificial intelligence grade (EmbryoScore), glucose and amino acid metabolism, and clinical pregnancies was conducted.

PARTICIPANTS/MATERIALS, SETTING, METHODS

ICSI was conducted in all patients, who were aged ≤37 years and previously had no more than two IVF cycles. Embryos were individually cultured in a time-lapse incubator system, and those reaching the blastocyst stage had their morphokinetics annotated and were each assigned a Gardner grade, KIDScore and EmbryoScore. Glucose and amino acid metabolism were measured. Clinical pregnancies were confirmed by the presence of a fetal heartbeat at 6 weeks of gestation.

MAIN RESULTS AND THE ROLE OF CHANCE

Glucose consumption was at least 40% higher in blastocysts deemed of high developmental potential using either the Gardner grade (P < 0.01, n = 209), KIDScore (P < 0.05, n = 207) or EmbryoScore (P < 0.05, n = 184), compared to less viable blastocysts and in blastocysts that resulted in a clinical pregnancy compared to those that failed to implant (P < 0.05, n = 37). Additionally, duration of cavitation was inversely related to glucose consumption (P < 0.05, n = 200). Total amino acid consumption was significantly higher in blastocysts with an EmbryoScore higher than the cohort median score (P < 0.01, n = 185). Furthermore, the production of amino acids was significantly lower in blastocysts with a high Gardner grade (P < 0.05, n = 209), KIDScore (P < 0.05, n = 207) and EmbryoScore (P < 0.01, n = 184).

LIMITATIONS, REASONS FOR CAUTION

Samples were collected from patients who had ICSI treatment and from only one clinic.

WIDER IMPLICATIONS OF THE FINDINGS

These results confirm that metabolites, such as glucose and amino acids, are valid biomarkers of embryo viability and could therefore be used in conjunction with other systems to aid in the selection of a healthy embryo.

STUDY FUNDING/COMPETING INTEREST(S)

Work was supported by Virtus Health. D.K.G is contracted with Virtus Health. The other authors have no conflict of interest to declare.

TRIAL REGISTRATION NUMBER

N/A.

Time-lapse technology improves total cumulative live birth rate and shortens time to live birth as compared to conventional incubation system in couples undergoing ICSI

PURPOSE

The improvement of clinical outcome provided by time-lapse technology (TLT) in IVF over conventional incubation (CI) still remains controversial. This study aimed at evaluating whether the exclusive use of time-lapse technology (TLT) during whole IVF care improves total cumulative live birth rate (TCLBR) and shortens time to live birth (TTLB) as compared to the use of CI in couples undergoing ICSI.

METHODS

This retrospective cohort study was conducted in couples with male infertility undergoing their first ICSI cycle in 2014-2015 and for whom embryo culture system remained the same during their whole IVF care, i.e., TLT or CI. Couples were followed up up to 2020, including all following frozen-embryo transfers and ICSI cycles (if any). Survival analysis was used to compare clinical outcome and time-related endpoints between both groups.

RESULTS

A total of 151 and 250 couples underwent their whole IVF care with the exclusive use of TLT and CI, respectively. Survival analysis showed that TCLBR after whole IVF care was significantly higher in TLT than in CI group (66.9 vs 56.4%, p=0.02, log-rank test). Median live birth time was significantly shorter in TLT than CI group (464 vs 596 days, p=0.01).

CONCLUSIONS

We found that TCLBR and TTLB were significantly improved with TLT over CI in couples undergoing ICSI for male factor. This study fuels the debate on the clinical benefit of using TLT. The use of time-related endpoints adds important information for both patients and practitioners.

Development of deep learning algorithms for predicting blastocyst formation and quality by time-lapse monitoring

Approaches to reliably predict the developmental potential of embryos and select suitable embryos for blastocyst culture are needed. The development of time-lapse monitoring (TLM) and artificial intelligence (AI) may help solve this problem. Here, we report deep learning models that can accurately predict blastocyst formation and usable blastocysts using TLM videos of the embryo’s first three days. The DenseNet201 network, focal loss, long short-term memory (LSTM) network and gradient boosting classifier were mainly employed, and video preparation algorithms, spatial stream and temporal stream models were developed into ensemble prediction models called STEM and STEM⁺. STEM exhibited 78.2% accuracy and 0.82 AUC in predicting blastocyst formation, and STEM⁺ achieved 71.9% accuracy and 0.79 AUC in predicting usable blastocysts. We believe the models are beneficial for blastocyst formation prediction and embryo selection in clinical practice, and our modeling methods will provide valuable information for analyzing medical videos with continuous appearance variation.

Liao et al. propose a deep learning model to predict blastocyst formation using TLM videos following the first three days of embryogenesis. The authors develop an ensemble prediction model, STEM and STEM⁺, which were found to exhibit 78.2% and 71.9% accuracy at predicting blastocyst formation and useable blastocysts respectively.

A machine learning system with reinforcement capacity for predicting the fate of an ART embryo

The aim of this work was to construct a score issued from a machine learning system with self-improvement capacity able to predict the fate of an ART embryo incubated in a time lapse monitoring (TLM) system. A retrospective study was performed. For the training data group, 110 couples were included and, 891 embryos were cultured. For the global setting data group, 201 couples were included, and 1186 embryos were cultured. No image analysis was used; morphokinetic parameters from the first three days of embryo culture were used to perform a logistic regression between the cell number and time. A score named DynScore was constructed, the prediction power of the DynScore on blastocyst formation and the baby delivery were tested via the area under the curve (AUC) obtained from the receiver operating characteristic (ROC). In the training data group, the DynScore allowed the blastocyst formation prediction (AUC = 0.634, p < 0.001), this approach was the higher among the set of the tested scores. Similar results were found with the global setting data group (AUC = 0.638, p < 0.001) and it was possible to increase the AUC of the DynScore with a regular update of the prediction system by reinforcement, with an AUC able to reach a value above 0.9. As only the best blastocysts were transferred, none of the tested scores was able to predict delivery. In conclusion, the DynScore seems to be able to predict the fate of an embryo. The reinforcement of the prediction system allows maintaining the predictive capacity of DynScore irrespective of the various events that may occur during the ART process. The DynScore could be implemented in any TLM system and adapted by itself to the data of any ART center.Abbreviations: ART: assisted reproduction technology; TLM: time lapse monitoring system; AUC: area under the curve; ROC: receiver operating characteristic; eSET: elective single embryo transfer; AIS: artificial intelligence system; KID: known implantation data; AMH: anti-Müllerian hormone; BMI: body mass index; WHO: World Health Organization; c-IVF: conventional in-vitro fertilization; ICSI: intracytoplasmic sperm injection; PNf: pronuclear formation; D3: day 3; D5: day 5; D6: day 6; GnRH: gonadotrophin releasing hormone; FSH: follicle stimulating hormone; LH: luteinizing hormone; hCG: human chorionic gonadotropin; PVP: polyvinyl pyrrolidone; PNf: time of pronuclear fading; tx: time of cleavage to x blastomeres embryo; ICM: inner cell mass; TE: trophectoderm; NbCell_t: number of cells at t time; FIFO: first in first out; TD: training data group; SD: setting data group; R: real world.

The optimal number of embryo cells for effective pregnancy and decrease of multiple pregnancy rate in frozen-thawed embryo transfer

To investigate the effect of the number of embryo cells on the clinical outcome of frozen-thawed embryo transfer and explore the optimal policy for decreases of multiple pregnancy rate, patients who experienced day 3 vitrified double frozen-thawed embryo transfer were retrospectively analyzed. According to the number of embryonic cells in each pre-frozen embryo, the patients were divided into six groups: 8C₂ (two 8-cell embryos), 8C₁- < 8C₁ (one 8-cell embryo and one under-8-cell embryo), 8C₁- > 8C₁ (one 8-cell embryo and one over-8-cell embryo), < 8C₂ (two under-8-cell embryos), < 8C₁- > 8C₁ (one under-8-cell embryo and one over-8-cell embryo), and > 8C₂ (two over-8-cell embryos). The clinical data were analyzed. The classification decision tree was used to analyze the optimal transfer strategy. A total of 2184 cycles of day 3 vitrified double frozen-thawed embryo transfer were enrolled. In day 3 double frozen-thawed embryo cycles, the 8C₂ group and 8C₁- > 8C₁ group had significantly (P < 0.05) higher pregnancy and multiple pregnancy rates than the other groups. No significant (P > 0.05) difference existed in the pregnancy rate and live birth rate between the 8C₁- < 8C₁ group, 8C₂ group and 8C₁- > 8C₁ group, but the implantation rate and multiple pregnancy rate in the 8C₁- < 8C₁ group were significantly (P < 0.05) lower than in the other two groups. Compared with the multiple pregnancy rate of all cycles, the cycles in two branches showed significantly (P < 0.05) higher multiple pregnancy rates (≤ 29 years old: 8C₂ / 8C₁- > 8C₁; 29 < age ≤ 36 years for the first transfer: 8C₂ / 8C₁- < 8C₁ / 8C₁- > 8C₁, one branch showed similar rate (≤ 29 years old: 8C₂ / 8C₁- > 8C₁) for the first transfer, and the remaining four branches demonstrated significantly (P < 0.05) lower rates. The clinical pregnancy rates before and after optimization were 51.0% vs 50.5%, and the multiple pregnancy rates were 38.5% vs 16.9%. In conclusion, the number of pre-frozen embryonic cells is an important factor affecting the clinical outcome of frozen-thawed embryo transfer in day 3 double good embryos frozen-thawed cycles. The age of patient, number of embryo cells, and the first time of transfer are the most valuable parameters for prediction. For women ≤ 29 years old, the single embryo transfer (SET) strategy was to choose an embryo ≥ 8 cells, and for women with < 29 age ≤ 36 years old, the SET strategy in the first transfer was to choose an embryo ≥ 8 cells.

Comparison of single euploid blastocyst transfer cycle outcome derived from embryos with normal or abnormal cleavage patterns

RESEARCH QUESTION

To assess incidence of abnormal cleavage among biopsied blastocysts; to compare euploidy rates of the blastocysts with abnormal and normal cleavage; and to compare single euploid blastocyst transfer (SEBT) outcome derived from embryos with normal or abnormal cleavage.

DESIGN

Retrospective analysis of prospectively collected data in a private IVF clinic. Consecutive 554 patients (749 cycles) undergoing preimplantation genetic testing for aneuploidy (n = 497; 671 cycles) or monogenic diseases (n = 57; 78 cycles) were included. All assessments for abnormal cleavage were carried out retrospectively; presence of abnormal cleavage was not a factor in deciding which euploid embryo to transfer. A total of 1015 blastocysts were biopsied and 295 SEBT procedures were carried out. Main outcome measure was live birth rate (LBR).

RESULTS

Incidence of reverse cleavage, direct cleavage, and reverse plus direct cleavage, were 7.7%, 6.4% and 2.3%, respectively. Of the 1015 biopsied blastocysts, 35.0% were euploid. Blastocysts with abnormal cleavage, in total, had a significantly higher euploidy rate compared with blastocysts with normal cleavage (44.6% [74/166] versus 33.1% [281/849]; P = 0.017). The LBR after SEBT with normal, reverse and direct cleavage, and direct cleavage plus reverse cleavage, was 133/238 (55.9%), 6/26 (23.1%), 8/24 (33.3%) and 0/3 (0.0%) (P < 0.001). Generalized estimating equation analysis showed that the presence of abnormal cleavage pattern was the only independent predictor of LBR (OR 0.316; 95% CI 0.115 to 0.867; P = 0.013).

CONCLUSIONS

Blastocysts with direct or reverse cleavage should be biopsied in preimplantation genetic testing cycles if they are morphologically eligible. Euploid blastocysts with abnormal cleavage, however, have approximately half the LBR of those euploid blastocyst with normal cleavage, hence, blastocysts with abnormal cleavage should have lower priority for transfer.

Time-lapse technology improves total cumulative live birth rate and shortens time to live birth as compared to conventional incubation system in couples undergoing ICSI

PURPOSE

The improvement of clinical outcome provided by time-lapse technology (TLT) in IVF over conventional incubation (CI) still remains controversial. This study aimed at evaluating whether the exclusive use of time-lapse technology (TLT) during whole IVF care improves total cumulative live birth rate (TCLBR) and shortens time to live birth (TTLB) as compared to the use of CI in couples undergoing ICSI.

METHODS

This retrospective cohort study was conducted in couples with male infertility undergoing their first ICSI cycle in 2014-2015 and for whom embryo culture system remained the same during their whole IVF care, i.e., TLT or CI. Couples were followed up up to 2020, including all following frozen-embryo transfers and ICSI cycles (if any). Survival analysis was used to compare clinical outcome and time-related endpoints between both groups.

RESULTS

A total of 151 and 250 couples underwent their whole IVF care with the exclusive use of TLT and CI, respectively. Survival analysis showed that TCLBR after whole IVF care was significantly higher in TLT than in CI group (66.9 vs 56.4%, p=0.02, log-rank test). Median live birth time was significantly shorter in TLT than CI group (464 vs 596 days, p=0.01).

CONCLUSIONS

We found that TCLBR and TTLB were significantly improved with TLT over CI in couples undergoing ICSI for male factor. This study fuels the debate on the clinical benefit of using TLT. The use of time-related endpoints adds important information for both patients and practitioners.

Ovulatory-Based FET Cycles May Achieve Higher Pregnancy Rates in the General Population and among Anovulatory Women

This study evaluated which endometrial preparation protocol in frozen embryo transfer (FET) cycles provides the best results for polycystic ovarian syndrome (PCOS) patients and the general population. This retrospective study of 634 FET cycles was conducted 2016-2018. Cycles were divided into Group A: Artificial endometrial preparations for FET (aFET; n = 348), Group B: Ovulatory cycle (n = 286) to compare two methods of endometrial preparation for FET. Artificial endometrial preparation with exogenous estrogen and progesterone versus natural ovulation cycles, modified natural cycles using hCG for the final triggering and letrozole-induced ovulation with hCG. Anovulatory patients were analyzed separately. Anovulatory PCOS patients had significantly higher pregnancy rates with letrozole treatment compared with aFET cycles (44% vs. 22.5%; p = 0.044). For the entire cohort, ovulatory cycles and aFET were similar in terms of patient characteristics, demographics, infertility causes, treatment protocols and number of embryos transferred. Although the mean ESHRE score of the transferred embryos was higher in the aFET group, we found higher clinical pregnancy rate in the ovulatory cycle FET (41.3% vs. 27.3%, p < 0.0001). A better pregnancy rate was found after ovulatory cycle FET. In the ovulatory cycles, the outcome of letrozole-induced and non-induced cycles were comparable. PCOS patients, as well as the general population, may benefit from ovulation induced FET cycles, with significantly better outcomes in FET in ovulatory cycles.

An investigation into the effect of potential confounding patient and treatment parameters on human embryo morphokinetics

OBJECTIVE

To determine the effect of patient and treatment parameters on 19 embryo morphokinetic parameters using pronuclear fading as time zero.

DESIGN

Single-site, retrospective cohort analysis.

SETTING

Fertility treatment center.

PATIENTS(S)

Patients undergoing treatment between September 2014 and January 2016 (n = 639) whose embryos were cultured in the EmbryoScope for 6 days (n = 2,376).

INTERVENTION(S)

None.

MAIN OUTCOME MEASURE(S)

Multiple regression analysis of body mass index; maternal age; infertility diagnosis; treatment type; suppression protocol on time to each cellular division (tn): t2, t3, t4, t5, t6, t7, t8, t9, time to start of compaction (tM), start of blastulation (tSB), full blastocyst (tB); and interval measurements: s2, s3, cc2, cc3, cc4, t9-tM, tM-tSB, and tSB-tB. Beta coefficients were analyzed to quantify any significant effects.

RESULT(S)

Embryos appeared to be subtly affected by patient and treatment parameters, exhibiting complex relationships between various morphokinetic parameters and specific patient and treatment factors, rather than a systemic effect.

CONCLUSION(S)

These findings outline the need for the consideration of confounding factors when assessing an embryo's ability to achieve implantation. Although morphokinetic parameters have been related to embryo viability, it is likely that this will vary depending on the embryo's origin.

The clinical use of time-lapse in human-assisted reproduction

A major challenge in the assisted reproduction laboratory is to set up reproducible and efficient criteria to identify the embryo with the highest developmental potential. Over the years, several methods have been used worldwide with this purpose. Initially, standard morphology assessment was the only available strategy. It is now universally recognized that besides being a very subjective embryo selection strategy, morphology evaluation alone has a very poor prognostic value. More recently, the availability of time-lapse incubators allowed a continuous monitoring of human embryo development. This technology has spread quickly and many fertility clinics over the world produced a remarkable amount of data. To date, however, a general consensus on which variables, or combination of variables, should play a central role in embryo selection is still lacking. Many confounding factors, concerning both patient features and clinical and biological procedures, have been observed to influence embryo development. In addition, several studies have reported unexpected positive outcomes, even in the presence of abnormal developmental criteria. While it does not seem that time-lapse technology is ready to entirely replace the more invasive preimplantation genetic testing in identifying the embryo with the highest implantation potential, it is certainly true that its application is rapidly growing, becoming progressively more accurate. Studies involving artificial intelligence and deep-learning models as well as combining morphokinetic with other non-invasive markers of embryo development, are currently ongoing, raising hopes for its successful applicability for clinical purpose in the near future. The present review mainly focuses on data published starting from the first decade of 2000, when time-lapse technology was introduced as a routine clinical practice in the infertility centers.

Mining of variables from embryo morphokinetics, blastocyst's morphology and patient parameters: an approach to predict the live birth in the assisted reproduction service

Based on growing demand for assisted reproduction technology, improved predictive models are required to optimize in vitro fertilization/intracytoplasmatic sperm injection strategies, prioritizing single embryo transfer. There are still several obstacles to overcome for the purpose of improving assisted reproductive success, such as intra- and inter-observer subjectivity in embryonic selection, high occurrence of multiple pregnancies, maternal and neonatal complications. Here, we compare studies that used several variables that impact the success of assisted reproduction, such as blastocyst morphology and morphokinetic aspects of embryo development as well as characteristics of the patients submitted to assisted reproduction, in order to predict embryo quality, implantation or live birth. Thereby, we emphasize the proposal of an artificial intelligence-based platform for a more objective method to predict live birth.

Blastocyst score, a blastocyst quality ranking tool, is a predictor of blastocyst ploidy and implantation potential

Objective

To convert blastocyst (BL) morphological grade and BL day into a numeric blastocyst score (BS).

Design

Retrospective cohort study.

Setting

Academic center.

Patient(s)

A total of 5,653 BL of known implantation (fetal heart, FH) and 11,348 biopsied BL.

Intervention(s)

Based on their FH rates and/or significance, a score (1–4) was assigned to each BL grade component. The BL morphological score (BMS) is the sum (BS = BMS on day 5; BS = BMS + 2 on day 6).

Main Outcome Measure(s)

Statistics characterized the FH and euploidy odds with BS.

Result(s)

All three morphology grade components and BL day were associated with implantation and euploidy probability. The FH rate and euploidy odds decrease with larger BS. The BS was the most important factor (odds ratio [OR] per unit change = 0.807, 95% confidence interval [CI] 0.784, 0.831) for untested and euploid BL implantation, and the sole one for euploid BL (OR/unit change = 0.845, 95% CI 0.803, 0.889). The BS is the second most significant factor after maternal age for euploidy probability (OR/unit change = 0.808, 95% CI 0.795, 0.822). In training and validation sets (75:25), the BS can predict implantation with similar area under the curve [AUC] (training = 0.628, 95% CI 0.613, 0.643; validation = 0.606, 95% CI 0.581, 0.631). The BS has better euploidy prediction ability (training AUC = 0.683, 95% CI 0.673, 0.693; validation AUC = 0.698, 95% CI 0.681, 0.715). The BS can stratify BL into good (3–5), fair (6–9), and poor (10–14) groups, reflecting their FH, live birth rates, and ploidy status. Advanced maternal age was associated with lower untested BL implantation and lower euploidy odds across all groups.

Conclusion(s)

The BS is a predictor of BL ploidy and FH implantation.

Novel and conventional embryo parameters as input data for artificial neural networks: an artificial intelligence model applied for prediction of the implantation potential

OBJECTIVE

To describe novel embryo features capable of predicting implantation potential as input data for an artificial neural network (ANN) model.

DESIGN

Retrospective cohort study.

SETTING

University-affiliated private IVF center.

PATIENT(S)

This study included 637 patients from the oocyte donation program who underwent single-blastocyst transfer during two consecutive years.

INTERVENTION(S)

None.

MAIN OUTCOME MEASURE(S)

The research was divided into two phases. Phase 1 consisted of the description and analysis of the following embryo features in implanted and nonimplanted embryos: distance and speed of pronuclear migration, blastocyst expanded diameter, inner cell mass area, and trophectoderm cell cycle length. Phase 2 consisted of the development of an ANN algorithm for implantation prediction. Results were obtained for four models fed with different input data. The predictive power was measured with the use of the area under the receiver operating characteristic curve (AUC).

RESULT(S)

Out of the five novel described parameters, blastocyst expanded diameter and trophectoderm cell cycle length had statistically different values in implanted and nonimplanted embryos. After the ANN models were trained and validated using fivefold cross-validation, they were capable of predicting implantation on testing data with AUCs of 0.64 for ANN1 (conventional morphokinetics), 0.73 for ANN2 (novel morphodynamics), 0.77 for ANN3 (conventional morphokinetics + novel morphodynamics), and 0.68 for ANN4 (discriminatory variables from statistical test).

CONCLUSION(S)

The novel proposed embryo features affect the implantation potential, and their combination with conventional morphokinetic parameters is effective as input data for a predictive model based on artificial intelligence.

Time-lapse imaging: the state of the art†

The introduction of time-lapse imaging to clinical in vitro fertilization practice enabled the undisturbed monitoring of embryos throughout the entire culture period. Initially, the main objective was to achieve a better embryo development. However, this technology also provided an insight into the novel concept of morphokinetics, parameters regarding embryo cell dynamics. The vast amount of data obtained defined the optimal ranges in the cell-cycle lengths at different stages of embryo development. This added valuable information to embryo assessment prior to transfer. Kinetic markers became part of embryo evaluation strategies with the potential to increase the chances of clinical success. However, none of them has been established as an international standard. The present work aims at describing new approaches into time-lapse: progress to date, challenges, and possible future directions.

Can novel early non-invasive biomarkers of embryo quality be identified with time-lapse imaging to predict live birth?

STUDY QUESTION

Can time-lapse imaging systems make it possible to identify novel early non-invasive biomarkers to predict live birth?

SUMMARY ANSWER

From mostly high-grade embryos, out of 35 morphometric, morphologic and morphokinetic variables, only pronuclei (PN) position at time of PN juxtaposition and the absence of multinucleated blastomeres at the 2-cell stage (MNB2cell), were potentially associated with live birth.

WHAT IS KNOWN ALREADY

Previous studies indicate that some kinetic markers may be predictive of blastocyst development and embryonic implantation. Certain teams have suggested including some of them in decisional algorithms for embryo transfers.

STUDY DESIGN, SIZE, DURATION

Using a time-lapse incubator (EmbryoScope, Unisense FertiliTech), we retrospectively explored the associations between the morphometric, morphologic and morphokinetic parameters of oocytes, zygotes and embryos, and their associations with live birth. This study assessed 232 embryos from single embryo transfers after ICSI cycles performed between January 2014 and December 2017.

PARTICIPANTS/MATERIALS, SETTING, METHODS

The morphometric, morphologic and morphokinetic parameters (18, 4 and 13, respectively) of oocytes, zygotes and early embryos were studied retrospectively. The associations between these parameters were examined using a Spearman's correlation, Mann-Whitney or chi-squared test as appropriate. We examined whether these parameters were associated with outcomes in univariate and multivariate logistic regression analyses.

MAIN RESULTS AND THE ROLE OF CHANCE

Central PN juxtaposition was associated with a 2-fold increase in the odds of live birth (OR = 2.20; 95% CI, [1.26-3.89]; P = 0.006), while the presence of MNB2cell was associated with half the odds of live birth (OR = 0.51; 95% CI, [0.27-0.95]; P = 0.035). These two parameters were independent of embryo kinetics. The 33 remaining parameters had no significant association with the capacity of transferred embryos to develop to term.

LIMITATIONS, REASONS FOR CAUTION

Even though the population size was relatively small, our analyses were based on homogeneous cycles, i.e. young women whose transferred embryos were found to be high-grade according to conventional morphology evaluation. In addition, our conclusions were established from a specific, highly selected population, so other study populations, such as women in an older age bracket, may yield different results. Finally, because we assessed day 2/3 transfers, our findings cannot be generalized to embryos cultured up to the blastocyst stage.

WIDER IMPLICATIONS OF THE FINDINGS

It would be interesting to explore, prospectively, whether PN localisation is a relevant measure to predict embryo development when added into further algorithms and whether this parameter could be suitable for use in other IVF clinics. Further studies are needed, notably to explore the added value of timing evaluation in cohorts of embryos with low or intermediate morphology grade, as well as in other maternal populations (i.e. older women).

STUDY FUNDING/COMPETING INTEREST(S)

No external funding was used for this study. P. Sagot received funding from the following commercial companies: Merck Serono, Finox Biotech, Ferring, MSD France SAS, Teva Sante ́ SAS, Allergan France, Gedeon Richter France, Effik S.A., Karl Storz Endoscopie France, GE Medical Systems SCS, Laboratoires Genevrier, H.A.C. Pharma and Ipsen.All the authors confirm that none of this funding was used to support the research in this study. There are no patents, products in development or marketed products to declare. This does not alter the authors' adherence to all the journal policies on sharing data and materials.

LIF in embryo culture medium is a predictive marker for clinical pregnancy following IVF-ET of patients with fallopian tube obstruction

Leukemia inhibitory factor (LIF) has played a vital role in a series of reproductive events, including follicle growth, embryo growth and differentiation. However, it is unclear whether the level of LIF in embryo culture medium can be used as a marker for clinical pregnancy. In this study, we aimed to investigate whether LIF level in embryo culture medium can act as a predictive marker for pregnancy outcome of in vitro fertilization-embryo transfer (IVF-ET) in infertile women due to tubal problems. A total of 208 infertile women due to tubal problems underwent IVF-ET treatment. The women were divided into two groups according to whether they were clinically pregnant. The level of LIF in the embryo culture medium was measured, and the correlation between LIF level and embryo quality and clinical pregnancy outcome was analyzed. The embryo culture medium was collected on the day of blastocyst transplantation. Compared to non-pregnant group, LIF level in the embryo culture medium on the day of blastocyst transplantation was significantly higher in the pregnant group. LIF level in the embryo culture medium may be used as a non-invasive auxiliary biomarker for predictive clinical pregnancy in infertile women with tubal problems that using single blastocyst transfer method.

Noninvasive sexing of human preimplantation embryos using RT-PCR in the spent culture media: A proof-of-concept study

Preimplantation genetic testing (PGT) routinely requires biopsy which is an invasive approach. The aim of this study was to examine a noninvasive approach for sexing of preimplantation embryos using polymerase chain reaction (PCR)/reverse transcriptase-PCR (RT-PCR) based on the presence of SRY DNA/RNA in the spent culture medium. Two groups were evaluated: in group 1, 40 embryos of routine PGT volunteers were cultured individually after biopsy and in group 2, 31 embryos were cultured individually until Day-5 post-fertilization. Each group was further divided into three subgroups: RNA extraction (RE), nucleic acid (NA) and DNase treated (DT). In the NA and DT subgroups, cDNA synthesis was performed directly on culture medium with or without DNase treatment in DT and NA subgroups, respectively. The results of sexing based on the PCR/RT-PCR in the culture medium, were compared with the results of sexing by fluorescence in situ hybridization (FISH) technique. In group 1, all samples were correctly diagnosed. In group 2, five female samples were misdiagnosed. Test's sensitivity, specificity and accuracy were 100 %, 94.44 % and 96.88 %, in RE, 100 %, 81.82 % and 93.55 % in DT and 100 %, 71.43 % and 85.71 % in NA, respectively. Preimplantation sexing without embryo biopsy, in the spent embryo culture media using RNA amplification based methods including RE and DT seem to be more reliable while nucleic acid based method, NA, led to the highest misdiagnoses probably due to DNA contamination. Since all male samples were correctly diagnosed in all subgroups of this preliminary study, preimplantation noninvasive sexing on culture medium seems feasible, however all sources of nucleic acid contamination must be carefully avoided.

Time of morulation and trophectoderm quality are predictors of a live birth after euploid blastocyst transfer: a multicenter study

OBJECTIVE

To investigate whether the morphodynamic characterization of a euploid blastocyst's development allows a higher prediction of a live birth after single-embryo-transfer (SET).

DESIGN

Observational cohort study conducted in two phases: training and validation.

SETTING

Private in vitro fertilization centers.

PATIENT(S)

Euploid blastocysts: 511 and 319 first vitrified-warmed SETs from 868 and 546 patients undergoing preimplantation genetic testing for aneuploidies (PGT-A) in the training and validation phase, respectively.

INTERVENTION(S)

Data collected from time of polar body extrusion to time of starting blastulation, and trophectoderm and inner-cell-mass static morphology in all embryos cultured in a specific time-lapse incubator with a continuous medium. Logistic regressions conducted to outline the variables showing a statistically significant association with live birth. In the validation phase, these variables were tested in an independent data set.

MAIN OUTCOME MEASURE(S)

Live births per SET.

RESULT(S)

The average live birth rate (LBR) in the training set was 40% (N = 207/511). Only time of morulation (tM) and trophectoderm quality were outlined as putative predictors of live birth at two IVF centers. In the validation set, the euploid blastocysts characterized by tM <80 hours and high-quality trophectoderm resulted in a LBR of 55.2% (n = 37/67), while those with tM ≥ 80 hours and a low-quality trophectoderm resulted in a LBR of 25.5% (N = 13/51).

CONCLUSION(S)

Time of morulation and trophectoderm quality are better predictors of a euploid blastocyst's reproductive competence. Our evidence was reproducible across different centers under specific culture conditions. These data support the crucial role of morulation for embryo development, a stage that involves massive morphologic, cellular, and molecular changes and deserves more investigation.

Between-laboratory reproducibility of time-lapse embryo selection using qualitative and quantitative parameters: a systematic review and meta-analysis

PURPOSE

To investigate the between-laboratory reproducibility of embryo selection/deselection effectiveness using qualitative and quantitative time-lapse parameters.

METHODS

A systematic search was performed on MEDLINE, EMBASE, and the Cochrane Library (up to February 2020) without restriction on date, language, document type, and publication status. Measuring outcomes included implantation, blastulation, good-quality blastocyst formation, and euploid blastocyst.

RESULTS

We detected 6 retrospective cohort studies externally validating the first clinical time-lapse model (Meseguer) emphasizing quantitative parameters, of which 3 (including one involving 2 independent centers) were included for the pooled analysis. Receiver operating characteristics analysis showed reduced predictive power of the model when either including or not including sister clinic validation. Fifteen cohort studies evaluating qualitative parameters were included for meta-analysis, and the mean Newcastle-Ottawa Scale was 5.3. Overall, meta-analysis showed significantly adverse association between the presence of ≥ 1 cleavage abnormalities and embryo implantation rates (11 studies, n = 7266; RR = 0.39[0.28, 0.55]_{95% CI}; I² = 57%). Further analysis showed adverse impacts of direct cleavage (7 studies, n = 7065; RR = 0.28 [0.15, 0.54] _{95% CI}; I² = 46%), reverse cleavage (2 studies, n = 3622; RR = 0.16 [0.03, 0.75] _{95% CI}; I² = 0%), chaotic cleavage (2 studies, n = 3643; RR = 0.11 [0.02, 0.69] _{95% CI}; I² = 24%), and multinucleation (5 studies, n = 2576; RR = 0.59 [0.50, 0.69] _{95% CI}; I² = 0%), but not the < 6 intercellular contact points at the 4-cell stage (1 study, n = 185; RR = 0.17 [0.02, 1.15] _{95% CI}).

CONCLUSIONS

Qualitative time-lapse parameters are reliably associated with embryo developmental potential among laboratories, whereas the reproducibility of time-lapse embryo selection model that emphasizes quantitative parameters may be compromised when externally applied.

Time-lapse technology for embryo culture and selection

Culturing of human embryos in optimal conditions is crucial for a successful in vitro fertilisation (IVF) programme. In addition, the capacity to assess and rank embryos correctly for quality will allow for transfer of the potentially 'best' embryo first, thereby shortening the time to pregnancy, although not improving cumulative pregnancy and live birth rates. It will also encourage and facilitate the implementation of single embryo transfers, thereby increasing safety for mother and offspring. Time-lapse technology introduces the concept of stable culture conditions, in connection with the possibility of continuous viewing and documenting of the embryo throughout development. However, so far, even when embryo quality scoring is based on large datasets, or when using the time-lapse technology, the morphokinetic scores are still mainly based on subjective and intermittent annotations of morphology and timings. Also, the construction of powerful algorithms for widespread use is hampered by large variations in culture conditions between individual IVF laboratories. New methodology, involving machine learning, where every image from the time-lapse documentation is analysed by a computer programme, looking for patterns that link to outcome, may in the future provide a more accurate and non-biased embryo selection.

Optimization of a single-embryo transfer in patients with good ovarian reserve

Due to refinements of assisted reproductive technology, the number of multiple pregnancies has increased substantially. Time-lapse microscopy (TLM) is a tool for selecting quality embryos for transfer. This study aimed to assess the outcomes of single-embryo transfer of autologous oocytes performed on day 5 of embryo incubation in a TLM-equipped system in patients with good ovarian reserve. The study was carried out in 208 infertile women with good ovarian reserve (over 8 oocytes retrieved). Single-embryo transfer following incubation in a TLM-equipped incubator was performed in 95 patients, who formed the main group; the control group consisted of 113 patients undergoing single-embryo transfer following a traditional culture and embryo selection procedure. We assessed the quality of transferred embryos, the rates of clinical pregnancy and pregnancy loss. Two subgroups were identified in each group of the participants: the 5SET subgroup (nonelective single-embryo transfer), which included 45 patients from the main group and 67 controls, and the 5eSET subgroup (elective single-embryo transfer), which consisted of 50 main group patients and 46 controls. The groups did not differ in terms of age, infertility factors and infertility duration. The quality of transferred embryos was excellent or good in all main group patients (100%); in the control group, the quality of transferred embryos was excellent or good in 93.8% of cases (p = 0.037). Clinical pregnancies were achieved in 64.2% of women in the main group and in 60.2% of controls (p = 0.65). Delivery rates were 54% and 51.1% in the 5eSET and 5SET subgroups of the main group, respectively (p = 0.940). For the control group, delivery rates were 54.4% and 34.3% in the 5eSET and 5SET subgroups, respectively (p = 0.052, Fisher exact test). Elective single-embryo transfer (5eSET) and the use of TLM increased the chance of pregnancy 2.17-fold (p = 0.01).

Impact of sperm characteristics on time-lapse embryo morphokinetic parameters and clinical outcome of conventional in vitro fertilization

BACKGROUND

Sperm abnormalities may negatively affect embryo development.

OBJECTIVES

To determine the influence of sperm abnormalities (morphology, motility, DNA fragmentation) on embryo morphokinetic variables and clinical outcome of conventional IVF.

MATERIALS AND METHODS

Participants were 86 couples undergoing in vitro fertilization (IVF). Sperm morphology was evaluated according to the strict criteria proposed by Kruger/Tygerberg. CASA system was applied for sperm motility assessment. Sperm DNA fragmentation was assessed by the chromatin structure assay (SCSA). Morphokinetic parameters were determined in 223 embryos obtained from conventional IVF only and cultured in a single-step medium using time-lapse imaging technology.

RESULTS

Time-lapse variables from the initial embryo development, such as time of pronuclei fading (tPNf) and time for two cells (t2), were those more strongly related with abnormalities of sperm motility, morphology, and DNA fragmentation. Sperm morphological abnormalities rather than sperm motility were more closely associated with embryo morphokinetics. Sperm head defects were mainly correlated with the last stages of embryonic development (t9 to tHB), sperm midpiece defects with intermediate cleaving embryos (t5-t9), and sperm tail defects with the initial stages of embryonic development (tPNa-t4). Excess residual cytoplasm was positively correlated with all embryo morphokinetic parameters except t2 and tM. Absence of acrosomes, pinheads, coiled tails, and multiple sperm morphological defects correlated negatively with time-lapse embryo morphokinetic variables.

DISCUSSION

A large number of sperm-related variables, including frequency of specific morphological defects, morphological indexes, DNA fragmentation and motility, and time-lapse embryo variables, such as time intervals based mainly of 15 time points were recorded.

CONCLUSION

There were strong associations between specific sperm defects of the head, midpiece, and tail with certain stages of embryonic development from observation of pronuclei to the hatched blastocyst. Coiled tail, cumulative head defects, and multiple abnormalities index (MAI) were associated both with embryo morphokinetics and the implantation success.

Performance of Day 5 KIDScore™ morphokinetic prediction models of implantation and live birth after single blastocyst transfer

PURPOSE

While several studies reported the association between morphokinetic parameters and implantation, few predictive models were developed to predict implantation after day 5 embryo transfer, generally without external validation. The objective of this study was to evaluate the respective performance of 2 commercially available morphokinetic-based models (KIDScore™ Day 5 versions 1 and 2) for the prediction of implantation and live birth after day 5 single blastocyst transfer.

METHODS

This monocentric retrospective study was conducted on 210 ICSI cycles with single day 5 embryo transfer performed with a time-lapse imaging (TLI) system between 2013 and 2016. The association between both KIDScore™ and the observed implantation and live birth rates was calculated, as well as the agreement between embryologist's choice for transfer and embryo ranking by the models.

RESULTS

Implantation and live birth rate were both 35.7%. A significant positive correlation was found between both models and implantation rate (r = 0.96 and r = 0.90, p = 0.01) respectively. Both models had statistically significant but limited predictive power for implantation (AUC 0.60). There was a fair agreement between the embryologists' choice and both models (78% and 61% respectively), with minor differences in case of discrepancies.

CONCLUSIONS

KIDScore™ Day 5 predictive models are significantly associated with implantation rates after day 5 single blastocyst transfer. However, their predictive performance remains perfectible. The use of these predictive models holds promises as decision-making tools to help the embryologist select the best embryo, ultimately facilitating the implementation of SET policy. However, embryologists' expertise remains absolutely necessary to make the final decision.

Assessing the impact of delayed blastulation using time lapse morphokinetics and preimplantation genetic testing in an IVF patient population

PURPOSE

There is clinical evidence that early cleavage timing parameters predictive of blastocyst development also correlate with embryo implantation potential. The aim of this study is to determine the developmental competency of embryos with delayed blastulation.

METHODS

Retrospective study performed from 2015 to 2016 at the Division of Reproductive Endocrinology and Infertility at Northwestern University.

RESULTS

A total of 2,292 embryos from 524 patients were included. Day 6 blastocysts had statistically significant longer times for every time point analyzed than day 5 blastocysts (p < 0.001). We found no statistically significant difference in euploidy rates between day 5 (44%) and day 6 (41%) embryos (p = 0.573). t7 and t8 time points were independent predictors of euploidy after controlling for day of biopsy (p < 0.015 and p < 0.014, respectively). Intrauterine pregnancy (IUP) and live birth (LB) were less likely to occur after transferring day 6 embryos (p = 0.0033 and p = 0.0359) without previous genetic testing. However, in embryos that undergo preimplantation genetic testing for aneuploidy (PGT-A), there were no significant differences in IUP or LB rates.

CONCLUSION

Early time-lapse points can be used to predict embryo development. Day of blastulation may be an independent predictor IUP, with day 6 blastocysts having lower pregnancy and live birth rates. Our data suggests that day 5 and day 6 PGT-A tested embryos show similar rates of euploidy, suggesting that differences in PR seen in the non-PGT-A tested group may be caused by factors other than aneuploidy. Genetic testing technologies in combination with time-lapse microscopy may provide further information to improve IVF outcomes.

Embryo development stage prediction algorithm for automated time lapse incubators

BACKGROUND AND OBJECTIVE

Time-lapse microscopy has become an important tool for studying the embryo development process. Embryologists can monitor the entire embryo growth process and thus select the best embryos for fertilization. This time and the resource consuming process are among the key factors for success of pregnancies. Tools for automated evaluation of the embryo quality and development stage prediction are developed for improving embryo selection.

METHODS

We present two-classifier vote-based method for embryo image classification. Our classification algorithms have been trained with features extracted using a Convolutional Neural Network (CNN). Prediction of embryo development stage is then completed by comparing confidence of two classifiers. Images are labeled depending on which one receives a larger confidence rating.

RESULTS

The evaluation has been done with imagery of real embryos, taken in the ESCO Time Lapse incubator from four different developing embryos. The results illustrate the most effective combination of two classifiers leading to an increase of prediction accuracy and achievement of overall 97.62% accuracy for a test set classification.

CONCLUSIONS

We have presented an approach for automated prediction of the embryo development stage for microscopy time-lapse incubator image. Our algorithm has extracted high-complexity image feature using CNN. Classification is done by comparing prediction of two classifiers and selecting the label of that classifier, which has a higher confidence value. This combination of two classifiers has allowed us to increase the overall accuracy of CNN from 96.58% by 1.04% up to 97.62%. The best results are achieved when combining the CNN and Discriminant classifiers. Practical implications include improvement of embryo selection process for in vitro fertilization.