Live births after embryo selection using morphokinetics versus conventional morphology: a retrospective analysis

Predicting IVF live -birth probability using time-lapse data: Implications of including or excluding age in a day 2 embryo transfer model

The primary objective of this study was to develop predictive models for the likelihood of live births following In Vitro Fertilisation (IVF) treatment, based on a retrospective analysis of time-lapse data from Day 2 embryo transfers at Klinikk Hausken, Norway. This analysis encompassed 1,506 IVF treatment cycles, which included 865 single and 641 double embryo transfer cycles, totalling 2,147 embryos transferred. The model covariates included nucleation error, timing of two-cell stage (t2) and duration between t2 and the three-cell stage (t3). The predictive ability was assessed using Area Under Curve (AUC). Generalised Additive Mixed Models (GAMM) were utilised to address clustering effects from Single Embryo Transfers (SET) and Double Embryo Transfers (DETs), as well as the non-linear effects of female age and t2 timings. A stratification of age and model scores demonstrated the impact of incorporating age into the model. The" Base Model, not incorporating age, achieved an AUC of 0.641, while the "Age Model", using maternal age, significantly enhanced AUC to 0.745, as estimated through bootstrap analysis. However, when the Age Model was subjected to average ages across three respective age intervals, the AUC values were comparable to the Base Model, rather than the original Age Model scores. Adjusting the Intracytoplasmic Sperm Injection (ICSI) timing by ± 2 hours, purely as a theoretical exercise, has minimal impacts on model predictions. This highlights the value of including t2 despite fertilisation timing variations between ICSI and IVF. The Age Model did not show superiority in predicting live birth within single treatment cohorts. However, given its distinct AUC values for broader age ranges, the Age Model can serve as a counselling tool on live-birth probabilities. With further validation, we suggest only using the Age Model for general counselling, while the Base Model is preferable for the embryo selection decision support.

Is there a relationship between morphokinetic parameters and obstetrical complications? An analysis of singleton live births after single fresh embryo transfer

BACKGROUND

With the advancement in embryology and the introduction of time-lapse monitoring system, the embryologists' goal might be to find not only the embryo with the highest probability of live birth, but also the embryo with the highest probability to progress to a healthy full-term delivery. Thus, we aimed to investigate the association between morphokinetic time-lapse parameters and obstetrical and perinatal complications.

METHODS

A cohort study reviewing fertility and delivery files of all singletone births from IVF patients whose embryos were cultured in a time-lapse monitoring system and had a single fresh embryo transfer at our center between 2013-2019. We conducted multiple comparisons between complicated and uncomplicated pregnancies of each perinatal complication, including: gestational diabetes mellitus (GDM); small for gestational age (SGA); pre-eclamptic toxemia (PET); preterm labor < 37 weeks of gestation (PTL); and third stage of labor complications. A comparison between pregnancies with and without a composite outcome of placental complications including GDM, SGA, PET and PTL was also conducted. Baseline characteristics, treatment and morphokinetic parameters in complicated and uncomplicated gestations were compared. Logistic regression analysis was utilized to adjust results for potential confounders.

RESULTS

One hundred seventy-six single embryo transfers resulted in 176 live births. Morphokinetic time-lapse parameters were similar between the groups, except for a shorter time to full blastulation in the SGA group (tB-tPNf = 75.5 ± 1.3 h vs. 79.5 ± 4.8 in the non-SGA group, p < 0.001), and shorter third cell cycle duration in the PET group (CC3 = 12.4 ± 1.1 h vs. 13.6 ± 2.9 in the non-PET group, p = 0.02). On multivariate regression analysis, none of the morphokinetic parameters were found to be significantly correlated with any of the perinatal complications.

CONCLUSION

Time-lapse morphokinetic parameters of the embryo transferred are not associated with adverse obstetric and perinatal outcomes.

ESHRE Guideline Group on the Number of Embryos to Transfer, Alteri A, Arroyo G, Baccino G, Craciunas L, De Geyter C, Ebner T, Koleva M, Kordic K, Mcheik S, Mertes H, Pavicic Baldani D, Rodriguez-Wallberg KA, Rugescu I, Santos-Ribeiro S, Tilleman K, Woodward B, Vermeulen N, Veleva Z. ESHRE guideline: number of embryos to transfer during IVF/ICSI†

STUDY QUESTION

Which clinical and embryological factors should be considered to apply double embryo transfer (DET) instead of elective single embryo transfer (eSET)?

SUMMARY ANSWER

No clinical or embryological factor per se justifies a recommendation of DET instead of eSET in IVF/ICSI.

WHAT IS KNOWN ALREADY

DET is correlated with a higher rate of multiple pregnancy, leading to a subsequent increase in complications for both mother and babies. These complications include preterm birth, low birthweight, and other perinatal adverse outcomes. To mitigate the risks associated with multiple pregnancy, eSET is recommended by international and national professional organizations as the preferred approach in ART.

STUDY DESIGN, SIZE, DURATION

The guideline was developed according to the structured methodology for development and update of ESHRE guidelines. Literature searches were performed in PUBMED/MEDLINE and Cochrane databases, and relevant papers published up to May 2023, written in English, were included. Live birth rate, cumulative live birth rate, and multiple pregnancy rate were considered as critical outcomes.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Based on the collected evidence, recommendations were discussed until a consensus was reached within the Guideline Development Group (GDG). A stakeholder review was organized after the guideline draft was finalized. The final version was approved by the GDG and the ESHRE Executive Committee.

MAIN RESULTS AND THE ROLE OF CHANCE

The guideline provides 35 recommendations on the medical and non-medical risks associated with multiple pregnancies and on the clinical and embryological factors to be considered when deciding on the number of embryos to transfer. These recommendations include 25 evidence-based recommendations, of which 24 were formulated as strong recommendations and one as conditional, and 10 good practice points. Of the evidence-based recommendations, seven (28%) were supported by moderate-quality evidence. The remaining recommendations were supported by low (three recommendations; 12%), or very low-quality evidence (15 recommendations; 60%). Owing to the lack of evidence-based research, the guideline also clearly mentions recommendations for future studies.

LIMITATIONS, REASONS FOR CAUTION

The guideline assessed different factors one by one based on existing evidence. However, in real life, clinicians' decisions are based on several prognostic factors related to each patient's case. Furthermore, the evidence from randomized controlled trials is too scarce to formulate high-quality evidence-based recommendations.

WIDER IMPLICATIONS OF THE FINDINGS

The guideline provides health professionals with clear advice on best practice in the decision-making process during IVF/ICSI, based on the best evidence currently available, and recommendations on relevant information that should be communicated to patients. In addition, a list of research recommendations is provided to stimulate further studies in the field.

STUDY FUNDING/COMPETING INTEREST(S)

The guideline was developed and funded by ESHRE, covering expenses associated with the guideline meetings, the literature searches, and the dissemination of the guideline. The guideline group members did not receive payment. DPB declared receiving honoraria for lectures from Merck, Ferring, and Gedeon Richter. She is a member of ESHRE EXCO, and the Mediterranean Society for reproductive medicine and the president of the Croatian Society for Gynaecological Endocrinology and Reproductive Medicine. CDG is the past Chair of the ESHRE EIM Consortium and a paid deputy member of the Editorial board of Human Reproduction. IR declared receiving reimbursement from ESHRE and EDCD for attending meetings. She holds an unpaid leadership role in OBBCSSR, ECDC Sohonet, and AER. KAR-W declared receiving grants for clinical researchers and funding provision to the institution from the Swedish Cancer Society (200170F), the Senior Clinical Investigator Award, Radiumhemmets Forskningsfonder (Dnr: 201313), Stockholm County Council FoU (FoUI-953912) and Karolinska Institutet (Dnr 2020-01963), NovoNordisk, Merck and Ferring Pharmaceuticals. She received consulting fees from the Swedish Ministry of Health and Welfare. She received honoraria from Roche, Pfizer, and Organon for chairmanship and lectures. She received support from Organon for attending meetings. She participated in advisory boards for Merck, Nordic countries, and Ferring. She declared receiving time-lapse equipment and grants with payment to institution for pre-clinical research from Merck pharmaceuticals and from Ferring. SS-R received research funding from Roche Diagnostics, Organon/MSD, Theramex, and Gedeo-Richter. He received consulting fees from Organon/MSD, Ferring Pharmaceuticals, and Merck Serono. He declared receiving honoraria for lectures from Ferring Pharmaceuticals, Besins, Organon/MSD, Theramex, and Gedeon Richter. He received support for attending Gedeon Richter meetings and participated in the Data Safety Monitoring Board of the T-TRANSPORT trial. He is the Deputy of ESHRE SQART special interest group. He holds stock options in IVI Lisboa and received equipment and other services from Roche Diagnostics and Ferring Pharmaceuticals. KT declared receiving payment for honoraria for giving lectures from Merck Serono and Organon. She is member of the safety advisory board of EDQM. She holds a leadership role in the ICCBBA board of directors. ZV received reimbursement from ESHRE for attending meetings. She also received research grants from ESHRE and Juhani Aaltonen Foundation. She is the coordinator of EHSRE SQART special interest group. The other authors have no conflicts of interest to declare.

DISCLAIMER

This guideline represents the views of ESHRE, which were achieved after careful consideration of the scientific evidence available at the time of preparation. In the absence of scientific evidence on certain aspects, a consensus between the relevant ESHRE stakeholders has been obtained. Adherence to these clinical practice guidelines does not guarantee a successful or specific outcome, nor does it establish a standard of care. Clinical practice guidelines do not replace the need for application of clinical judgement to each individual presentation, nor variations based on locality and facility type. ESHRE makes no warranty, express or implied, regarding the clinical practice guidelines and specifically excludes any warranties of merchantability and fitness for a particular use or purpose (full disclaimer available at https://www.eshre.eu/Guidelines-and-Legal).

Prediction of live birth - selection of embryos using morphokinetic parameters

BACKROUND

The goal of assisted reproduction is for a couple treated with IVF techniques to end the treatment by giving birth to a healthy baby. A neccessary presumption for success is the identification of the best embryo with high implantation and developmental potential. One option is to select an euploid embryo by invasive preimplantaion genetic testing for aneuploidy (PGT-A) or it is possible to select the best embryo by non-invasive time-lapse monitoring (TLM), specifically based on morphokinetic parameters and morphological markers that are able to identify an embryo with high developmental potential.

MATERIALS AND METHODS

The study involved a total of 1060 embryos (585 euploid and 475 aneuploid embryos after PGT-A) with good morphology from 329 patients in the period 01/2016-10/2021. All embryos were cultured in a time-lapse incubator, trophectoderm (TE) cells biopsies for PGT-A examination were performed on day 5 (D5) or day 6 (D6) of culture. During the study period, 225 frozen embryo transfers (FET) of one euploid embryo were performed. Based on the treatment outcome, the embryos were divided into 2 groups - euploid embryos, which led to the birth of a healthy child, and euploid embryos that did not show fetal heartbeat (FHB) after FET.

RESULTS

Based on the statistical analysis of the embryos without implantation and the embryos with live birth, it is clear that the morphokinetic parameters t5 (time of division into 5 cells) and tSB (time of start of blastulation) are significantly different.

CONCLUSION

The results suggest that of the morphokinetic parameters tSB and t5 are predictive indicators for selecting an embryo with high developmental potential and with a high probability of achieving the birth of a healthy child.

Considerations for future modification of The Association for the Study of Reproductive Biology embryo grading system incorporating time-lapse observations

The Association for the Study of Reproductive Biology (ASEBIR) Interest Group in Embryology (in Spanish 'Grupo de Interés de Embriología') reviewed key morphokinetic parameters to assess the contribution of time-lapse technology (TLT) to the ASEBIR grading system. Embryo grading based on morphological characteristics is the most widely used method in human assisted reproduction laboratories. The introduction and implementation of TLT has provided a large amount of information that can be used as a complementary tool for morphological embryo evaluation and selection. As part of IVF treatments, embryologists grade embryos to decide which embryos to transfer or freeze. At the present, the embryo grading system developed by ASEBIR does not consider dynamic events observed through TLT. Laboratories that are using TLT consider those parameters as complementary data for embryo selection. The aim of this review was to evaluate review time-specific morphological changes during embryo development that are not included in the ASEBIR scoring system, and to consider them as candidates to add to the scoring system.

Atypical initial cleavage patterns minimally impact rhesus macaque in vitro embryo morphokinetics and embryo outgrowth development†

Embryo morphokinetic analysis through time-lapse embryo imaging is envisioned as a method to improve selection of developmentally competent embryos. Morphokinetic analysis could be utilized to evaluate the effects of experimental manipulation on pre-implantation embryo development. The objectives of this study were to establish a normative morphokinetic database for in vitro fertilized rhesus macaque embryos and to assess the impact of atypical initial cleavage patterns on subsequent embryo development and formation of embryo outgrowths. The cleavage pattern and the timing of embryo developmental events were annotated retrospectively for unmanipulated in vitro fertilized rhesus macaque blastocysts produced over four breeding seasons. Approximately 50% of the blastocysts analyzed had an abnormal early cleavage event. The time to the initiation of embryo compaction and the time to completion of hatching was significantly delayed in blastocysts with an abnormal early cleavage event compared to blastocysts that had cleaved normally. Embryo hatching, attachment to an extracellular matrix, and growth during the implantation stage in vitro was not impacted by the initial cleavage pattern. These data establish normative morphokinetic parameters for in vitro fertilized rhesus macaque embryos and suggest that cleavage anomalies may not impact embryo implantation rates following embryo transfer.

Faster Fertilization and Cleavage Kinetics Reflect Competence to Achieve a Live Birth: Data from Single-Embryo Transfer Cycles

The aim of this study was to assess the relationship between early developmental kinetics and the competence to result in a live birth as well as the impact of maternal age and the number of retrieved oocytes. This retrospective cohort study included 3,021 single-embryo transfer cycles and assessed live birth outcomes paired with morphokinetic data; 1,412 transfers resulted in live births (LB), and 1,609 did not (NLB). Early morphokinetic parameters between LB and NLB embryos were compared from patients stratified into four age groups (20-25, 26-30, 31-36, and ≥37 years) and between embryos in the same competence groups within the age groups. Early morphokinetic parameters were also compared between LB and NLB embryos from patients stratified into four groups based on the number of oocytes harvested (≤7, 8-14, 15-21, and ≥22). The association between morphokinetic parameters and LB was tested using univariate and multivariate analyses. This study indicated that embryos resulting in LB generally exhibit faster developmental dynamic parameters than embryos that do not. However, this difference decreased in the younger (20-25 years) and older (≥37 years) age groups. In addition, when the number of harvested oocytes was low (≤7) or high (≥22), this difference was less obvious. The morphokinetic parameters of embryonic cleavage are an effective reference value for embryo selection strategies aimed at increasing live birth rates, especially for patients aged 26–36 years, with 8–21 harvested oocytes.

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)

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.

Shallow artificial networks with morphokinetic time-lapse parameters coupled to ART data allow to predict live birth

Purpose

The purpose of this work was to construct shallow neural networks (SNN) using time-lapse technology (TLT) from morphokinetic parameters coupled to assisted reproductive technology (ART) parameters in order to assist the choice of embryo(s) to be transferred with the highest probability of achieving a live birth (LB).

Methods

A retrospective observational single-center study was performed, 654 cycles were included. Three SNN: multilayers perceptron (MLP), simple recurrent neuronal network (simple RNN) and long short term memory RNN (LSTM-RNN) were trained with K-fold cross-validation to avoid sampling bias. The predictive power of SNNs was measured using performance scores as AUC (area under curve), accuracy, precision, Recall and F1 score.

Results

In the training data group, MLP and simple RNN provide the best performance scores; however, all AUCs were above 0.8. In the validating data group, all networks were equivalent with no performance scores difference and all AUC values were above 0.8.

Conclusion

Coupling morphokinetic parameters with ART parameters allows to SNNs to predict the probability of LB, and all SNNs seems to be efficient according to the performance scores. An automatic time recognition system coupled to one of these SNNs could allow a complete automation to choose the blastocyst(s) to be transferred.

Optimisation of the timing of fertilisation assessment for oocytes cultured in standard incubation: lessons learnt from time-lapse imaging of 78 348 embryos

STUDY QUESTION

Using time-lapse data, can the current consensus for the timing of fertilisation assessment of oocytes, cultured in standard incubation, be optimised?

SUMMARY ANSWER

The optimum time to perform fertilisation assessment for oocytes cultured in standard incubation is 16.5 ± 0.5 h post-insemination (hpi), and the current consensus requires modification in order to minimise the chance of fertilisation being missed.

WHAT IS KNOWN ALREADY

Time-lapse incubation allows the embryologist to retrospectively review collated images of oocytes and embryos to capture important embryological observations that may otherwise be missed in standard incubation. According to expert consensus, the optimum time to perform the assessment of fertilisation is 17 ± 1 hpi.

STUDY DESIGN, SIZE, DURATION

A retrospective, multicentre analysis utilised data obtained from 54 746 ICSI-derived embryos and 23 602 IVF-derived embryos cultured in time-lapse incubation between January 2011 and November 2019.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Using time-lapse imaging (TLI), the precise time of pronuclei appearance and disappearance was recorded, where applicable, and the number of oocytes with two pronuclei observable during 10 30-min intervals from 15 hpi to 20 hpi was determined.

MAIN RESULTS AND THE ROLE OF CHANCE

Between 15 and 17.5 hpi, the average number of oocytes exhibiting normal fertilisation, elicited as two pronuclei, was 98.19% with the highest proportion of oocytes having visible pronuclei at 16-16.5 hpi (98.32%). At 18-18.5 hpi, the number of visible pronuclei reduced to 95.53% and continued to fall to 87.02% at 19.5-20 hpi.

LIMITATIONS, REASONS FOR CAUTION

The authors' expectation is that these findings are transferable to other settings, however it is possible that, with alternative culture media and incubation environments, calibration of this timing may be required. As data cannot readily be recorded for pronuclear appearance for IVF-derived embryos, it is not possible to determine the optimum time to perform the fertilisation assessment for IVF-derived embryos.

WIDER IMPLICATIONS OF THE FINDINGS

By fine-tuning the time at which fertilisation assessment takes place the accuracy of the assessment can be increased to maximise the number of fertilised oocytes identified, thereby increasing the number of usable embryos for the patient. Without TLI and following current consensus guidelines, over 11% (n = 3000) of oocytes would have been marked as unfertilised within this cohort. Further to this, depending on the time of a standard fertilisation assessment, up to 300 embryos which resulted in live births could have been categorised as unfertilised, as they presented no visible pronuclei at the conventional assessment time-point.

STUDY FUNDING/COMPETING INTEREST(S)

A.C. is a minor shareholder in CARE Fertility Limited. Validated algorithmic time-lapse embryo selection is offered to patients at CARE Fertility at an additional charge as an adjuvant treatment option.

TRIAL REGISTRATION NUMBER

N/A.

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.

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.

Deep learning neural network analysis of human blastocyst expansion from time-lapse image files

RESEARCH QUESTION

Can artificial intelligence (AI) discriminate a blastocyst's cellular area from unedited time-lapse image files using semantic segmentation and a deep learning optimized U-Net architecture for use in selecting single blastocysts for transfer?

DESIGN

This platform was retrospectively applied to time-lapse files from 101 sequentially transferred single blastocysts that were prospectively selected for transfer by their highest expansion ranking within cohorts using a 10 h expansion assay rather than standard grading.

RESULTS

The AI platform provides expansion curves and raw data files to classify and compare blastocyst phenotypes within both cohorts and populations. Of 35 sequential unbiopsied single blastocyst transfers, 23 (65.7%) resulted in a live birth. Of 66 sequential single euploid blastocyst transfers, also selected for their most robust expansion, 49 (74.2%) resulted in live birth. The AI platform revealed that the averaged expansion rate was significantly (P = 0.007) greater in euploid blastocysts that resulted in live births compared with those resulting in failure to give a live birth. The platform further provides a framework to analyse fragmentation phenotypes that can test new hypotheses for developmental regulation during the preimplantation period.

CONCLUSIONS

AI can be used to quantitatively describe blastocyst expansion from unedited time-lapse image files and can be used to quantitatively rank-order blastocysts for transfer. Early clinical results from such single blastocyst selection suggests that live birth rates without biopsy may be comparable to those found using single euploid blastocysts in younger, good responder patients.

An artificial intelligence model based on the proteomic profile of euploid embryos and blastocyst morphology: a preliminary study

RESEARCH QUESTION

The study aimed to develop an artificial intelligence model based on artificial neural networks (ANNs) to predict the likelihood of achieving a live birth using the proteomic profile of spent culture media and blastocyst morphology.

DESIGN

This retrospective cohort study included 212 patients who underwent single blastocyst transfer at IVI Valencia. A single image of each of 186 embryos was studied, and the protein profile was analysed in 81 samples of spent embryo culture medium from patients included in the preimplantation genetic testing programme. The information extracted from the analyses was used as input data for the ANN. The multilayer perceptron and the back-propagation learning method were used to train the ANN. Finally, predictive power was measured using the area under the curve (AUC) of the receiver operating characteristic curve.

RESULTS

Three ANN architectures classified most of the embryos correctly as leading (LB+) or not leading (LB-) to a live birth: 100.0% for ANN1 (morphological variables and two proteins), 85.7% for ANN2 (morphological variables and seven proteins), and 83.3% for ANN3 (morphological variables and 25 proteins). The artificial intelligence model using information extracted from blastocyst image analysis and concentrations of interleukin-6 and matrix metalloproteinase-1 was able to predict live birth with an AUC of 1.0.

CONCLUSIONS

The model proposed in this preliminary report may provide a promising tool to select the embryo most likely to lead to a live birth in a euploid cohort. The accuracy of prediction demonstrated by this software may improve the efficacy of an assisted reproduction treatment by reducing the number of transfers per patient. Prospective studies are, however, needed.

Are morphokinetic parameters of embryo development associated with adverse perinatal outcomes following fresh blastocyst transfer?

RESEARCH QUESTION

Are obstetric and perinatal complications associated with morphokinetic parameters of embryo development?

DESIGN

This proof-of-concept pilot study included a retrospective analysis of embryo morphokinetic parameters of 85 live births following day 5 single blastocyst transfer. Kinetic variables included time interval (hours) from time of pronuclei fading (tPNf) to: time of 2 cells (tPNf-t2), 9 cells (tPNf-t9), morula (tPNf-tM), start of blastulation (tPNf-tSB), full blastocyst (tPNf-tB) and expanded blastocyst (tPNf-tEB). Multivariable logistic models were used to calculate the risk of perinatal complications after adjustment for confounders.

RESULTS

The mean interval of tPNf-tSB was significantly longer for newborns with congenital anomalies compared with healthy newborns (79.49 ± 5.78 versus 71.7 ± 6.3, respectively, P = 0.01) and for embryos of women who had gestational diabetes mellitus compared with normoglycemic women (76.56 ± 7.55 versus 71.5 ± 6.13, respectively, P = 0.015). The mean interval of tPNf-t9 was significantly longer for low-birthweight newborns compared with normal weight (49.25 ± 5.54 versus 45.47 ± 4.77, respectively, P = 0.01). Preterm delivery was associated with several longer intervals of cell divisions compared with delivery at term (tPNf-t5: 28.76 ± 3.13 versus 26.64 ± 2.40, respectively, P = 0.01; tPNf-t6: 30.10 ± 3.05 versus 27.68 ± 2.30, respectively, P < 0.001; tPNf-t7: 32.08 ± 4.11 versus 28.70 ± 2.67, respectively, P < 0.001; tPNf-t8: 34.75 ± 4.95 versus 30.70 ± 4.10, respectively, P < 0.001; tPNf-t9: 50.23 ± 5.87 versus 45.44 ± 4.67, respectively, P < 0.001). For each of the outcomes, the association remained significant after adjusting for confounders.

CONCLUSION

This study indicates that there may be a possible association between adverse perinatal outcomes and morphokinetic parameters. Larger studies are needed to establish this association.

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.

Necessity is the mother of invention and the evolutionary force driving the success of in vitro fertilization

During the last few decades, millions of healthy children have been born with the aid of in vitro fertilization (IVF). This success belies the fact that IVF treatment is comprised of a complex series of interventions starting with a customized control ovarian stimulation protocol. This is followed by the induction of oocyte maturation, the retrieval of mature oocytes and in vitro fertilization, which often involves the microinjection of a single sperm into the oocyte. After fertilization, the resulting embryos are cultured for up to 7 days. The best embryos are transferred into the uterus where the embryo implants and hopefully develops into a healthy child. However, frequently the best embryos are biopsied and frozen. The biopsied cells are analyzed to identify those embryos without chromosomal abnormalities. These embryos are eventually thawed and transferred with pregnancy rates as good if not better than embryos that are not biopsied and transferred in a fresh cycle. Thus, IVF treatment requires the coordinated efforts of physicians, nurses, molecular biologists and embryologists to conduct each of these multifaceted phases in a seamless and flawless manner. Even though complex, IVF treatment may seem routine today, but it was not always the case. In this review the evolution of human IVF is presented as a series of innovations that resolved a technical hurdle in one component of IVF while creating challenges that eventually lead to the next major advancement. This step-by-step evolution in the treatment of human infertility is recounted in this review.

Faster fertilization and cleavage kinetics reflect competence to achieve a live birth after intracytoplasmic sperm injection, but this association fades with maternal age

OBJECTIVE

To assess the relationship of early developmental kinetics with competence to provide a live birth and the impact of maternal age in this context.

DESIGN

Retrospective cohort study including 4,915 embryos, of which 1,390 were transferred and provided a clinical outcome paired with morphokinetic data; 168 of them resulted in a live birth (LB), and 1,222 did not (NLB). Early morphokinetic parameters were compared between LB and NLB embryos from patients stratified into two age groups (<37 and ≥37 years), and between embryos at the same competence group from patients aged <37 and ≥37 years. The association of morphokinetic parameters with live birth was tested by univariate and multivariate analyses.

SETTING

Fertility clinic.

PATIENT(S)

The study population included 1,066 patients undergoing autologous intracytoplasmic sperm injection cycles with fresh single (SET), double (DET) or triple (TET) embryo transfers on day 2 or 3. Of them, 669 patients produced NLB embryos and 134 produced LB embryos.

INTERVENTION(S)

None.

MAIN OUTCOME MEASURE(S)

Fertilization and cleavage morphokinetic parameters and live birth.

RESULT(S)

In the total patient population, all morphokinetic parameters were achieved earlier in LB compared with NLB embryos. The same was observed in patients aged <37 years (P<.015), but not ≥37 years. Except for the t8 (time at which an 8-blastomere embryo was identified), all morphokinetic parameters were reached earlier in LB embryos from patients aged <37 years compared with LB embryos from patients aged ≥37 years. Univariate analysis revealed that earlier occurrence of all morphokinetic parameters was associated with live birth, although only earlier t2 (time at which two separate and distinct cells were identified) was associated with live birth independently from maternal age in the multivariate analysis.

CONCLUSION(S)

Despite its retrospective nature and performance in a single IVF center, this study presents novel data indicating that embryos competent to provide a live birth display overall faster early developmental kinetics compared with embryos that do not achieve a live birth after transfer, a difference that, however, narrows as maternal age advances. The findings suggest that fertilization and cleavage morphokinetic parameters may constitute valuable references for embryo selection strategies aiming to improve live birth rates, specifically before advanced maternal age while holding limited usefulness in advanced maternal age.

Blastocyst collapse as an embryo marker of low implantation potential: a time-lapse multicentre study

Spontaneous blastocyst collapse during in vitro embryo development has been suggested as a novel marker of embryo quality. Therefore, the aim of this multicentre study was to carry out a retrospective multicentre analysis to investigate the correlation between blastocyst collapse and pregnancy outcome. Here, 1297 intracytoplasmic sperm injection (ICSI)/in vitro fertilization (IVF) fresh cycles, with an elective single blastocyst transfer (eSET) were included in this study. Embryos were cultured individually in 6.0% CO2, 5.0% O2, 89.0% N2, using single step medium (GTLTM VitroLife, Sweden) or sequential medium (CookTM, Cook Medical, Australia) and selected for transfer using standard morphological criteria. With the use of time-lapse monitoring (TLM), blastocysts were analyzed by measuring the maximum volume reduction and defined as having collapsed, if there was ≥ 50% volume reduction from the expanded blastocyst and the collapse event. Following embryo replacement, each blastocyst was retrospectively allocated to one of two groups (collapsed or not collapsed). Here, 259 blastocysts collapsed once or more during development (19.9%) and the remaining 1038 either contracted minimally or not collapsed (80.1%). A significantly higher ongoing pregnancy rate (OPR) of 51.9% (95% CI 48.9-59.9%) was observed when blastocysts that had not collapsed were replaced compared with cycles in which collapsed blastocysts were transferred 37.5% (95% CI 31.6-43.4%). This study suggests that human blastocysts that collapse spontaneously during development are less likely to implant and generate a pregnancy compared with embryos that do not. Although this is a retrospective study, the results demonstrated the utility of collapse episodes as new marker of embryo selection following eSET at blastocyst stage.

Follicular environment as a predictive tool for embryo development and kinetics in cattle

Follicular fluid composition and the transcription pattern of granulosa cells were analysed to better comprehend associations between embryo development and morphokinetics. Bovine follicles were punctured and their respective follicular fluid and granulosa cells were collected. Cumulus-oocyte complexes derived from these follicles were matured and fertilised invitro. Embryo morphology and kinetics were evaluated at 40h after insemination, when embryos were classified as fast (FCL, four or more cells), slow (SCL, 2-3 cells) or non-cleaved (NCL). Their development was followed until the blastocyst stage. Glucose, pyruvate, cholesterol and oestradiol were quantified in the follicular fluid and the transcription pattern of 96 target genes was evaluated in granulosa cells by large-scale quantitative reverse transcription polymerase chain reaction. Follicular fluid from the blastocyst group had increased levels of glucose, total cholesterol and pyruvate compared to the non-blastocyst group, whereas higher levels of oestradiol were observed in the follicular fluid of embryos and blastocysts with fast cleavage. The transcriptional pattern revealed altered metabolic pathways between groups, such as lipid metabolism, cellular stress and cell signalling. In conclusion, both follicular fluid and granulosa cells are associated with the possibility of identifying follicles that may generate embryos with high potential to properly develop to the blastocyst stage.

Early blastocyst expansion in euploid and aneuploid human embryos: evidence for a non-invasive and quantitative marker for embryo selection

RESEARCH QUESTION

How can the kinetics of human blastocyst expansion be used to evaluate an embryo's ploidy identified using preimplantation genetic testing for aneuploidy (PGT-A)?

DESIGN

This was a retrospective observational study of 188 autologous blastocysts from 34 sequential treatment cycles using PGT-A and blastocyst biopsy. Using time-lapse imaging, blastocyst expansion was evaluated using a quantitative standardized expansion assay (qSEA). Trophectoderm cell division was examined in selected, unbiopsied embryos (n = 7) to evaluate the contribution of mitosis to the expansion rate.

RESULTS

The averaged euploid blastocyst expansion rate was significantly (52.8%) faster than in aneuploid blastocysts (P = 0.0041). Scatterplots, representing 'expansion maps', revealed that both populations showed a similarly overlapping distribution of blastocyst formation times at 80-140 h from fertilization. Euploidy and aneuploidy were better distinguished in regions of higher and lower expansion, respectively, in expansion maps. Based upon the expansion slopes, rank-ordering of individual embryos within cohorts resulted in more than 90% euploid embryos in the first two ranks in patients less than 35 years of age. Additional detailed time-lapse image analysis provided evidence that rapid expansion was associated with robust, integrative cellular mitosis in trophectoderm cells.

CONCLUSIONS

The kinetics of human blastocyst expansion are related to an embryo's ploidy. These preliminary observations describe a new quantitative, non-invasive approach to embryo assessment that may be useful to identify single blastocysts for transfer, particularly in younger patient groups. However, this approach may also be useful for euploid embryo selection after PGT-A. The results support the hypothesis that aneuploidy universally impairs general cellular processes, including cell division, in differentiated cells.

Association between early embryo morphokinetics plus cumulus cell gene expression and assisted reproduction outcomes in polycystic ovary syndrome women

RESEARCH QUESTION

Can a combination of time-lapse morphokinetic parameters and cumulus cell gene expression in polycystic ovary syndrome (PCOS) women be used to predict assisted reproductive treatment outcome?

DESIGN

A total of 547 embryos from 100 intracytoplasmic sperm injection (ICSI) cycles were evaluated. Fifty women with PCOS and 50 women who were categorized as tubal factor infertility were recruited. Time-lapse records were annotated for time to pronuclear fading (tPNf), time to 2 to 8 cells (t2-t8), reverse cleavage, direct cleavage and also for the presence of multinucleation. Expression levels of three genes involved in mitotic divisions, diaphanous-related formin 2 (DIAPH2), nibrin (NBN) and NIMA-related protein kinase (NEK4), were measured in 100 associated cumulus cell samples using quantitative real-time polymerase chain reaction.

RESULTS

Expression of DIAPH2 and NBN was significantly higher in the embryos of PCOS patients that resulted in implantation, biochemical and clinical pregnancies as well as live birth compared with embryos that were negative for these outcomes (P <0.01). However, in the tubal factor group, NBN gene expression was significantly higher in embryos resulting in biochemical pregnancy, clinical pregnancy and live birth (P <0.01) only. Multivariate logistic regression analysis showed that tPNf together with DIAPH2 gene expression were independent prognostic factors of clinical pregnancy rate and live birth in both groups.

CONCLUSIONS

Some time-lapse embryo parameters may be related to cumulus gene expression and clinical outcome. Furthermore, the expressions of cumulus cell genes involved in mitotic divisions are significantly associated with ICSI outcome using Day 3 embryo transfer.

Early blastulation of day 4 embryo correlates with the increased euploid rate of preimplantation genetic screening cycles

OBJECTIVE

It is known that embryos with faster growing potential, especially in blastocyst development, correlate with the increased euploid rate. Our study investigated the preimplantation genetic screening cycle to analyze the correlation between early blastulation (EB) on day 4 embryo and the euploid rate.

MATERIALS AND METHODS

This is a retrospective study examining 273 biopsied blastocysts after preimplantation genetic screening obtained from 54 patients from March 2013 to March 2017. Of the 273 biopsied embryos, 81 had early blastulation on day 4 and were classified as the EB (+) group, while the other 192 had no early blastulation and were classified as the EB (-) group. Euploid rates were compared between the two groups. A total of 34 single euploid embryos were transferred, with 14 from the EB (+) group and 20 from the EB (-) group. Clinical pregnancy was compared between the groups.

RESULTS

There is a statistically significant increase in the euploid rate in the EB (+) group (49.4% vs. 34.4%, p = 0.02). The clinical pregnancy rate was also increased in the single euploid embryo transfer group with early blastulation, but did not reach statistical significance (71.4% vs. 50.0%, p = 0.211).

CONCLUSIONS

Early blastulation of day 4 embryo correlates significantly with the euploid rate. Early blastulation of day 4 embryo may serve as a potential aid for embryo selection for transfer in preimplantation genetic screening cycles.

A high-throughput and open-source platform for embryo phenomics

Phenomics has the potential to facilitate significant advances in biology but requires the development of high-throughput technologies capable of generating and analysing high-dimensional data. There are significant challenges associated with building such technologies, not least those required for investigating dynamic processes such as embryonic development, during which high rates of temporal, spatial, and functional change are inherently difficult to capture. Here, we present EmbryoPhenomics, an accessible high-throughput platform for phenomics in aquatic embryos comprising an Open-source Video Microscope (OpenVIM) that produces high-resolution videos of multiple embryos under tightly controlled environmental conditions. These videos are then analysed by the Python package Embryo Computer Vision (EmbryoCV), which extracts phenomic data for morphological, physiological, behavioural, and proxy traits during the process of embryonic development. We demonstrate the broad-scale applicability of EmbryoPhenomics in a series of experiments assessing chronic, acute, and multistressor responses to environmental change (temperature and salinity) in >30 million images of >600 embryos of two species with markedly different patterns of development—the pond snail Radix balthica and the marine amphipod Orchestia gammarellus. The challenge of phenomics is significant but so too are the rewards, and it is particularly relevant to the urgent task of assessing complex organismal responses to current rates of environmental change. EmbryoPhenomics can acquire and process data capturing functional, temporal, and spatial responses in the earliest, most dynamic life stages and is potentially game changing for those interested in studying development and phenomics more widely.

EmbryoPhenomics is an open-source technology platform for high-throughput phenome screening of aquatic embryos. This paper demonstrates its application in experiments assessing the sensitivity of aquatic embryos to environmental stress, consisting of more than 600 embryos and more than 30 million images.

Phenomics is the collection of high-dimensional phenotypic data on an organism-wide scale, and it requires high-throughput technologies. However, a lack of technologies for efficiently visualising and measuring whole-organism responses to different environments represents a serious challenge for biologists. This challenge is most apparent when studying complex responses, such as those occurring during the dynamic period of embryonic development, when the phenotype changes markedly through time. Here, we present EmbryoPhenomics (www.embryophenomics.org), a new open-source technological platform comprising high-throughput bioimaging hardware that produces high-resolution video of multiple, developing embryos maintained under controlled environmental conditions and software for automatically quantifying embryo responses from these videos. We demonstrate the broad applicability of EmbryoPhenomics using four experiments assessing responses to global change (elevated temperature and salinity) in which we generate data for more than 600 embryos produced from video comprising more than 30 million images. EmbryoPhenomics was used to capture functional, temporal, and spatial change in morphological, physiological, and behavioural responses in the earliest, most dynamic life stages and addresses a serious bottleneck in biology. Such capabilities are urgently required, particularly within the context of assessing the response of embryos to the current unprecedented rates of global environmental change.

Time-lapse imaging systems in IVF laboratories: a French national survey

PURPOSE

Although the clinical value of time-lapse imaging (TLI) systems in in vitro fertilization (IVF) cycles is still debated, its prevalence worldwide seems to be expanding. The situation of TLI in the USA has been recently surveyed, but these results might not be transposable to other countries with different IVF regulation and funding such as France. This study evaluated the TLI situation in French IVF laboratories.

METHODS

An anonymous online cross-sectional survey was sent by email to 210 embryologists in September and October 2017. Laboratories, demographics, TLI clinical use, purchasing plan, and embryologists' opinions were analyzed using logistic regression to calculate odds ratio.

RESULTS

Of the 210 lab directors surveyed, 78 responded (37.1%), 43 (55%) working in private IVF laboratories and 35 (45%) in public hospitals. Thirty (38.5%) were TLI users. The odds of TLI possession were not statistically different according to laboratory sector or size. Most embryologists (n = 21, 70%) used TLI for unselected patients. Cost was the main reason given by non-users for not implementing TLI (n = 24, 50%). Most respondents were convinced that TLI is superior to standard morphology (n = 52, 73.2%) and that TLI improves culture conditions (n = 62, 84.9%). However, half (n = 39, 54.9%) indicated that evidence was still lacking to assert TLI clinical usefulness.

CONCLUSION

The prevalence of TLI systems and embryologists' opinion in France was slightly different from the American situation. The different regulation and funding policy might account for some differences in terms of TLI use and perception.

Assessing ICSI outcome by combining non-invasive indicators: Early time-lapse morphokinetics and apoptosis in associated cumulus cells among women with the polycystic ovarian syndrome

Cumulus cells features and embryo developmental events can be considered as noninvasive indicators for embryo selection and clinical outcomes. A combination of time-lapse morphokinetic parameters and cumulus cell apoptosis in women with polycystic ovarian syndrome (PCOS) was evaluated for predicting pregnancy outcome. We assessed a total of 547 embryos from 100 intracytoplasmic sperm injection (ICSI) cycles. Time-lapse records were interpreted in time to pronuclear fading (tPNf), time to 2 to 8 cells (t2-t8), direct cleavage, reverse cleavage, and also for the presence of multinucleation. Percentages of apoptosis were identified in 100 associated cumulus cell samples using the TDT-mediated dUTP-biotin nick end-labeling assay. The significant decrease of apoptotic cumulus cells was detected in patients with chemical and clinical pregnancies as well as live birth among patients PCOS and in the tubal infertility group (p > 0.05). Furthermore, significantly higher implantation rate and also significantly lower cases of early pregnancy loss were observed in the group of oocytes with less apoptotic cumulus cells. Multivariate logistic regression analysis showed that tPNf together with cumulus cell apoptosis were independent prognostic factors of chemical pregnancy, clinical pregnancy rate, and live birth. Time-lapse embryo parameters may not reflect the cumulus cell apoptosis rate. However, the rate of apoptotic cumulus cells is significantly associated with ICSI outcome using Day 3 embryo transfer.

Embryo culture conditions are significantly improved during uninterrupted incubation: A randomized controlled trial

A parallel group superiority prospective randomised controlled trial was devised to compare the culture characteristics of human pre-implantation stage embryos during uninterrupted culture in a time lapse incubator (TLI) versus the conventional model of interrupted culture in a standard incubator (SI) under low oxygen tension using a single step medium. 221 patients aged 35-and-under, 124 patients aged between 36 and 39 and 86 patients aged 40-and-over years were randomised and cultured either in a SI or in a TLI. Patients in the three age groups were distributed between the TLI and SI in a 1:1 ratio. The development of embryos on days 2, 3 and 5, and the clinical pregnancy and implantation rates were recorded. The fertilisation rate, development of day 2 and clinical pregnancy rates were similar in both treatments but the 8-cell development rate in all age groups combined (p = 0.016), blastocyst development rate (p = 0.0022) and the implantation rate (p = 0.0022) was significantly higher for the uninterrupted culture. These findings demonstrated significant differences between the two incubation groups. It also indicated less efficacious embryonic development with age in both treatments which appeared more pronounced in the conventional incubator. In conclusion uninterrupted culture is superior compared to the interrupted incubation culture system.