WISE: whole-scenario embryo identification using self-supervised learning encoder in IVF.

PURPOSE: To study the effectiveness of whole-scenario embryo identification using a self-supervised learning encoder (WISE) in in vitro fertilization (IVF) on time-lapse, cross-device, and cryo-thawed scenarios. METHODS: WISE was based on the vision transformer (ViT) architecture and masked autoencoders (MAE), a self-supervised learning (SSL) method. To train WISE, we prepared three datasets including the SSL pre-training dataset, the time-lapse identification dataset, and the cross-device identification dataset. To identify whether pairs of images were from the same embryos in different scenarios in the downstream identification tasks, embryo images including time-lapse and microscope images were first pre-processed through object detection, cropping, padding, and resizing, and then fed into WISE to get predictions. RESULTS: WISE could accurately identify embryos in the three scenarios. The accuracy was 99.89% on the time-lapse identification dataset, and 83.55% on the cross-device identification dataset. Besides, we subdivided a cryo-thawed evaluation set from the cross-device test set to have a better estimation of how WISE performs in the real-world, and it reached an accuracy of 82.22%. There were approximately 10% improvements in cross-device and cryo-thawed identification tasks after the SSL method was applied. Besides, WISE demonstrated improvements in the accuracy of 9.5%, 12%, and 18% over embryologists in the three scenarios. CONCLUSION: SSL methods can improve embryo identification accuracy even when dealing with cross-device and cryo-thawed paired images. The study is the first to apply SSL in embryo identification, and the results show the promise of WISE for future application in embryo witnessing.

A novel machine-learning framework based on early embryo morphokinetics identifies a feature signature associated with blastocyst development.

BACKGROUND: Artificial Intelligence entails the application of computer algorithms to the huge and heterogeneous amount of morphodynamic data produced by Time-Lapse Technology. In this context, Machine Learning (ML) methods were developed in order to assist embryologists with automatized and objective predictive models able to standardize human embryo assessment. In this study, we aimed at developing a novel ML-based strategy to identify relevant patterns associated with the prediction of blastocyst development stage on day 5. METHODS: We retrospectively analysed the morphokinetics of 575 embryos obtained from 80 women who underwent IVF at our Unit. Embryo morphokinetics was registered using the Geri plus® time-lapse system. Overall, 30 clinical, morphological and morphokinetic variables related to women and embryos were recorded and combined. Some embryos reached the expanded blastocyst stage on day 5 (BL Group, n = 210), some others did not (nBL Group, n = 365). RESULTS: The novel EmbryoMLSelection framework was developed following four-steps: Feature Selection, Rules Extraction, Rules Selection and Rules Evaluation. Six rules composed by a combination of 8 variables were finally selected, and provided a predictive power described by an AUC of 0.84 and an accuracy of 81%. CONCLUSIONS: We provided herein a new feature-signature able to identify with an high performance embryos with the best developmental competence to reach the expanded blastocyst stage on day 5. Clear and clinically relevant cut-offs were identified for each considered variable, providing an objective tool for early embryo developmental assessment.

Time-Lapse Imaging of Migrating Neurons and Glial Progenitors in Embryonic Mouse Brain Slices.

During the development of the cerebral cortex, neurons and glial cells originate in the ventricular zone lining the ventricle and migrate toward the brain surface. This process is crucial for proper brain function, and its dysregulation can result in neurodevelopmental and psychiatric disorders after birth. In fact, many genes responsible for these diseases have been found to be involved in this process, and therefore, revealing how these mutations affect cellular dynamics is important for understanding the pathogenesis of these diseases. This protocol introduces a technique for time-lapse imaging of migrating neurons and glial progenitors in brain slices obtained from mouse embryos. Cells are labeled with fluorescent proteins using in utero electroporation, which visualizes individual cells migrating from the ventricular zone with a high signal-to-noise ratio. Moreover, this in vivo gene transfer system enables us to easily perform gain-of-function or loss-of-function experiments on the given genes by co-electroporation of their expression or knockdown/knockout vectors. Using this protocol, the migratory behavior and migration speed of individual cells, information that is never obtained from fixed brains, can be analyzed.

Image restoration of degraded time-lapse microscopy data mediated by near-infrared imaging.

Time-lapse fluorescence microscopy is key to unraveling biological development and function; however, living systems, by their nature, permit only limited interrogation and contain untapped information that can only be captured by more invasive methods. Deep-tissue live imaging presents a particular challenge owing to the spectral range of live-cell imaging probes/fluorescent proteins, which offer only modest optical penetration into scattering tissues. Herein, we employ convolutional neural networks to augment live-imaging data with deep-tissue images taken on fixed samples. We demonstrate that convolutional neural networks may be used to restore deep-tissue contrast in GFP-based time-lapse imaging using paired final-state datasets acquired using near-infrared dyes, an approach termed InfraRed-mediated Image Restoration (IR2). Notably, the networks are remarkably robust over a wide range of developmental times. We employ IR2 to enhance the information content of green fluorescent protein time-lapse images of zebrafish and Drosophila embryo/larval development and demonstrate its quantitative potential in increasing the fidelity of cell tracking/lineaging in developing pescoids. Thus, IR2 is poised to extend live imaging to depths otherwise inaccessible.

Embryo ranking agreement between embryologists and artificial intelligence algorithms.

OBJECTIVE: To evaluate the degree of agreement of embryo ranking between embryologists and eight artificial intelligence (AI) algorithms. DESIGN: Retrospective study. PATIENT(S): A total of 100 cycles with at least eight embryos were selected from the Weill Cornell Medicine database. For each embryo, the full-length time-lapse (TL) videos, as well as a single embryo image at 120 hours, were given to five embryologists and eight AI algorithms for ranking. INTERVENTION(S): None. MAIN OUTCOME MEASURE(S): Kendall rank correlation coefficient (Kendall's τ). RESULT(S): Embryologists had a high degree of agreement in the overall ranking of 100 cycles with an average Kendall's tau (K-τ) of 0.70, slightly lower than the interembryologist agreement when using a single image or video (average K-τ = 0.78). Overall agreement between embryologists and the AI algorithms was significantly lower (average K-τ = 0.53) and similar to the observed low inter-AI algorithm agreement (average K-τ = 0.47). Notably, two of the eight algorithms had a very low agreement with other ranking methodologies (average K-τ = 0.05) and between each other (K-τ = 0.01). The average agreement in selecting the best-quality embryo (1/8 in 100 cycles with an expected agreement by random chance of 12.5%; confidence interval [CI]95: 6%-19%) was 59.5% among embryologists and 40.3% for six AI algorithms. The incidence of the agreement for the two algorithms with the low overall agreement was 11.7%. Agreement on selecting the same top two embryos/cycle (expected agreement by random chance corresponds to 25.0%; CI95: 17%-32%) was 73.5% among embryologists and 56.0% among AI methods excluding two discordant algorithms, which had an average agreement of 24.4%, the expected range of agreement by random chance. Intraembryologist ranking agreement (single image vs. video) was 71.7% and 77.8% for single and top two embryos, respectively. Analysis of average raw scores indicated that cycles with low diversity of embryo quality generally resulted in a lower overall agreement between the methods (embryologists and AI models). CONCLUSION(S): To our knowledge, this is the first study that evaluates the level of agreement in ranking embryo quality between different AI algorithms and embryologists. The different concordance methods were consistent and indicated that the highest agreement was intraembryologist agreement, followed by interembryologist agreement. In contrast, the agreement between some of the AI algorithms and embryologists was similar to the inter-AI algorithm agreement, which also showed a wide range of pairwise concordance. Specifically, two AI models showed intra- and interagreement at the level expected from random selection.

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.

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

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

The effect of embryo selection using time-lapse monitoring on IVF/ICSI outcomes: A systematic review and meta-analysis.

AIM: To explore the effect of embryo selection using the time-lapse monitoring (TLM) system compared with conventional morphological selection (CMS) on in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) outcomes. METHODS: We searched PubMed, Ovid-Embase, and The Cochrane Library for the following studies: At Comparison 1, embryo selection using TLM images in a TLM incubator based on morphology versus embryo selection using CMS in a conventional incubator based on morphology; at Comparison 2, embryo selection using TLM based on morphokinetics versus embryo selection using CMS based on morphology. The primary outcomes were the live birth rate (LBR), ongoing pregnancy rate (OPR), clinical pregnancy rate (CPR), and implantation rate (IR), and the secondary outcome was the miscarriage rate (MR). RESULTS: A total of 14 randomized control trials (RCTs) were included. Both based on morphology, TLM incubators increased the IR (risk ratio [RR]: 1.10; 95% confidence interval [CI]: 1.01, 1.18; I2 = 0%, moderate-quality evidence) compared to conventional incubators. Low- to moderate-quality evidence suggests that TLM incubators did not improve LBR, OPR, CPR, and MR compared to conventional incubators. In addition, low- to moderate-quality evidence indicates that embryo selection using TLM based on morphokinetics did not improve LBR, OPR, CPR, IR, or MR compared to CMS based on morphology. CONCLUSIONS: Low- to moderate-quality evidence suggests that neither TLM incubators nor embryo selection using TLM based on morphokinetics improved clinical outcomes (LBR, OPR, CPR, and MR) compared with CMS based on morphology. TLM is still an investigational procedure for IVF/ICSI practice.

Evaluation of an automated dish preparation system for IVF and embryo culture using a mouse mode.

Manual dish preparation for IVF in human fertility clinics or animal laboratories heavily relies on embryologists' experience, which can lead to occupational illness due to long-term and monotonous operation. Therefore, introducing an automated technique to replace traditional methods is crucial for improving working efficiency and reducing work burden for embryologists. In the current study in the mouse, both manual and automated methods were used to prepare IVF or embryo culture dishes. A one-way analysis of variance was conducted to compare several factors, including preparation time, qualified rates, media osmolality of dishes, fertilization rates, and embryonic development to assess the efficiency and potential of automated preparation. The results showed that automation system significantly reduced the required time and increased the efficiencies and qualified rates of dish preparation, especially for embryo culture dishes, without significantly altering medium osmolalities. There were no significant differences between two preparations in fertilization rates and embryo development in mice. Thus, automated dish preparation can improve working efficiency and qualified rates while maintaining fertilization rates and subsequent embryonic development without compromising osmolality stability of medium. It presents a superior alternative to manual preparation, reducing the workload of embryologists and facilitating the standardization of operational procedures.

ALFI: Cell cycle phenotype annotations of label-free time-lapse imaging data from cultured human cells.

Detecting and tracking multiple moving objects in a video is a challenging task. For living cells, the task becomes even more arduous as cells change their morphology over time, can partially overlap, and mitosis leads to new cells. Differently from fluorescence microscopy, label-free techniques can be easily applied to almost all cell lines, reducing sample preparation complexity and phototoxicity. In this study, we present ALFI, a dataset of images and annotations for label-free microscopy, made publicly available to the scientific community, that notably extends the current panorama of expertly labeled data for detection and tracking of cultured living nontransformed and cancer human cells. It consists of 29 time-lapse image sequences from HeLa, U2OS, and hTERT RPE-1 cells under different experimental conditions, acquired by differential interference contrast microscopy, for a total of 237.9 hours. It contains various annotations (pixel-wise segmentation masks, object-wise bounding boxes, tracking information). The dataset is useful for testing and comparing methods for identifying interphase and mitotic events and reconstructing their lineage, and for discriminating different cellular phenotypes.

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.

Automated detection of apoptotic bodies and cells in label-free time-lapse high-throughput video microscopy using deep convolutional neural networks.

MOTIVATION: Reliable label-free methods are needed for detecting and profiling apoptotic events in time-lapse cell-cell interaction assays. Prior studies relied on fluorescent markers of apoptosis, e.g. Annexin-V, that provide an inconsistent and late indication of apoptotic onset for human melanoma cells. Our motivation is to improve the detection of apoptosis by directly detecting apoptotic bodies in a label-free manner. RESULTS: Our trained ResNet50 network identified nanowells containing apoptotic bodies with 92% accuracy and predicted the onset of apoptosis with an error of one frame (5 min/frame). Our apoptotic body segmentation yielded an IoU accuracy of 75%, allowing associative identification of apoptotic cells. Our method detected apoptosis events, 70% of which were not detected by Annexin-V staining. AVAILABILITY AND IMPLEMENTATION: Open-source code and sample data provided at https://github.com/kwu14victor/ApoBDproject.

DeepSea is an efficient deep-learning model for single-cell segmentation and tracking in time-lapse microscopy.

Time-lapse microscopy is the only method that can directly capture the dynamics and heterogeneity of fundamental cellular processes at the single-cell level with high temporal resolution. Successful application of single-cell time-lapse microscopy requires automated segmentation and tracking of hundreds of individual cells over several time points. However, segmentation and tracking of single cells remain challenging for the analysis of time-lapse microscopy images, in particular for widely available and non-toxic imaging modalities such as phase-contrast imaging. This work presents a versatile and trainable deep-learning model, termed DeepSea, that allows for both segmentation and tracking of single cells in sequences of phase-contrast live microscopy images with higher precision than existing models. We showcase the application of DeepSea by analyzing cell size regulation in embryonic stem cells.

How and when to measure pH in IVF culture media: validation of a portable blood gas analyzer in two IVF culture dishes for time lapse and conventional incubators.

PURPOSE: Maintaining a stable pH at optimal level in human embryo culture media is crucial for embryo development but poses a challenge for all IVF laboratories. We validate analytically reliable conditions for pH measurement that are as close as possible to the embryo microenvironment during IVF. METHODS: This was a multicentric study. A Siemens EPOC portable blood gas analyzer was used. The analytical validation was carried out under the culture medium (Global Total HSA®) conditions of use (microdroplets, under oil overlay, in a IVF incubator with (EmbryoScope®) or without a time lapse system (K system G210+®) and using IVF dishes. The validation included repeatability ("within-run" precision), total precision (between-day precision), trueness based on inter-laboratory comparison, inaccuracy based on external quality assessment and comparison to the reference technique. We also assessed the pre-analytical medium incubation time required to obtain a target value. RESULTS: A measurement after an incubation period of 24 to 48 h is more representative of the pH to which the embryo will be exposed throughout the culture. The "within-run" and "between-day" precision show very low coefficients of variation (CV%): 0.17 to 0.22% and 0.13 to 0.34%, respectively, with IVF culture media. Trueness (% bias) range from - 0.07 to - 0.03%. We demonstrate good correlation between EPOC and reference pH electrode with an overestimation of 0.03 pH units of EPOC. CONCLUSION: Our method demonstrates good analytical performance for IVF laboratories wishing to implement a robust quality assurance system to monitor pH in embryo culture media. Compliance with stringent pre-analytical and analytical conditions is essential.

Time-lapse imaging: Morphokinetic analysis of in vitro fertilization outcomes.

Time-lapse imaging (TLI) allows continuous monitoring of embryo development without disturbing culture conditions by removing embryos from the incubator. The study of embryo kinetics using TLI has given rise to some new markers for embryo selection that are able to document and evaluate embryo morphology and the timing of developmental events through continuous live image tracking. Time-lapse imaging has emerged as a powerful tool for creating predictive models of in vitro fertilization outcomes. Fourty-seven articles were included in the present review to investigate the current situation of TLI in in vitro fertilization laboratories. Morphokinetics of the embryo during its in vitro development have been described using parameters indicative of the different events capable of predicting the ability to reach blastocyst stage, implantation and pregnancy rates, live birth outcome, and embryo ploidy.

Real-time image and time-lapse technology to select the single blastocyst to transfer in assisted reproductive cycles.

The success of an assisted reproduction cycle should be the achievement of a healthy singleton live birth following the replacement of one embryo. Therefore, one of the most critical points for embryologists has been the selection criteria and how to choose the best embryo to transfer with high implantation potential. In this vein, morphological evaluation has been historically the method applied. However, this practice relies on a limited number of single observations and is associated with high operator variability. Recently, a major innovation in embryo culture has been the introduction of a new type of incubator with integrated time-lapse monitoring, which enables the embryologist to analyze the dynamic events of embryo development, from fertilization to blastocyst formation. This novel practice is quickly growing and has been implemented in many IVF clinics worldwide. Therefore, the main aim of this review is to illustrate the benefits of time-lapse technology in a modern embryology laboratory. In particular, we discuss the blastocyst collapse(s) event and morphometric blastocyst assessment and analyse their association with embryo viability and implantation potential.

Time-lapse embryo monitoring: does it add to standard in-vitro fertilization/intra cytoplasmic sperm injection?

Since the first pioneering studies on time-lapse systems (TLSs) for embryo incubation, many things have changed. Two main factors influence the development of modern time-lapse incubators for human in-vitro fertilization (IVF): 1) the switch from traditional cell culture incubators to benchtops incubators, more suitable for human IVF; and 2) the improvement of imaging technology. Another major factor for the increase in the utilization of TLSs in IVF labs over the last decade was the advances in computer/wireless and smartphone/tablet technology, which allowed patients to see the footage of their growing embryos. Hence, more user-friendly features have allowed their introduction and routine use in IVF labs while image-capturing software has enabled storage and providing additional information to the patients concerning the development of their embryos. This review aims to describe the history and the different TLSs available in the market, to summarize the research and clinical results obtained by using this technology, and to reflect on how this technology is changing the modern IVF laboratory. The current limitations of TLSs will be also reviewed.

Deep learning for embryo evaluation using time-lapse: a systematic review of diagnostic test accuracy.

OBJECTIVE: This study aimed to investigate the accuracy of convolutional neural network models in the assessment of embryos using time-lapse monitoring. DATA SOURCES: A systematic search was conducted in PubMed and Web of Science databases from January 2016 to December 2022. The search strategy was carried out by using key words and MeSH (Medical Subject Headings) terms. STUDY ELIGIBILITY CRITERIA: Studies were included if they reported the accuracy of convolutional neural network models for embryo evaluation using time-lapse monitoring. The review was registered with PROSPERO (International Prospective Register of Systematic Reviews; identification number CRD42021275916). METHODS: Two reviewer authors independently screened results using the Covidence systematic review software. The full-text articles were reviewed when studies met the inclusion criteria or in any uncertainty. Nonconsensus was resolved by a third reviewer. Risk of bias and applicability were evaluated using the QUADAS-2 tool and the modified Joanna Briggs Institute or JBI checklist. RESULTS: Following a systematic search of the literature, 22 studies were identified as eligible for inclusion. All studies were retrospective. A total of 522,516 images of 222,998 embryos were analyzed. Three main outcomes were evaluated: successful in vitro fertilization, blastocyst stage classification, and blastocyst quality. Most studies reported >80% accuracy, and embryologists were outperformed in some. Ten studies had a high risk of bias, mostly because of patient bias. CONCLUSION: The application of artificial intelligence in time-lapse monitoring has the potential to provide more efficient, accurate, and objective embryo evaluation. Models that examined blastocyst stage classification showed the best predictions. Models that predicted live birth had a low risk of bias, used the largest databases, and had external validation, which heightens their relevance to clinical application. Our systematic review is limited by the high heterogeneity among the included studies. Researchers should share databases and standardize reporting.

Clinical outcomes of uninterrupted embryo culture with or without time-lapse-based embryo selection versus interrupted standard culture (SelecTIMO): a three-armed, multicentre, double-blind, randomised controlled trial.

BACKGROUND: Time-lapse monitoring is increasingly used in fertility laboratories to culture and select embryos for transfer. This method is offered to couples with the promise of improving pregnancy chances, even though there is currently insufficient evidence for superior clinical results. We aimed to evaluate whether a potential improvement by time-lapse monitoring is caused by the time-lapse-based embryo selection method itself or the uninterrupted culture environment that is part of the system. METHODS: In this three-armed, multicentre, double-blind, randomised controlled trial, couples undergoing in-vitro fertilisation or intracytoplasmic sperm injection were recruited from 15 fertility clinics in the Netherlands and randomly assigned using a web-based, computerised randomisation service to one of three groups. Couples and physicians were masked to treatment group, but embryologists and laboratory technicians could not be. The time-lapse early embryo viability assessment (EEVA; TLE) group received embryo selection based on the EEVA time-lapse selection method and uninterrupted culture. The time-lapse routine (TLR) group received routine embryo selection and uninterrupted culture. The control group received routine embryo selection and interrupted culture. The co-primary endpoints were the cumulative ongoing pregnancy rate within 12 months in all women and the ongoing pregnancy rate after fresh single embryo transfer in a good prognosis population. Analysis was by intention to treat. This trial is registered on the ICTRP Search Portal, NTR5423, and is closed to new participants. FINDINGS: 1731 couples were randomly assigned between June 15, 2017, and March 31, 2020 (577 to the TLE group, 579 to the TLR group, and 575 to the control group). The 12-month cumulative ongoing pregnancy rate did not differ significantly between the three groups: 50·8% (293 of 577) in the TLE group, 50·9% (295 of 579) in the TLR group, and 49·4% (284 of 575) in the control group (p=0·85). The ongoing pregnancy rates after fresh single embryo transfer in a good prognosis population were 38·2% (125 of 327) in the TLE group, 36·8% (119 of 323) in the TLR group, and 37·8% (123 of 325) in the control group (p=0·90). Ten serious adverse events were reported (five TLE, four TLR, and one in the control group), which were not related to study procedures. INTERPRETATION: Neither time-lapse-based embryo selection using the EEVA test nor uninterrupted culture conditions in a time-lapse incubator improved clinical outcomes compared with routine methods. Widespread application of time-lapse monitoring for fertility treatments with the promise of improved results should be questioned. FUNDING: Health Care Efficiency Research programme from Netherlands Organisation for Health Research and Development and Merck.

No difference in morphokinetics between male and female preimplantation embryos from ART.

RESEARCH QUESTION: Do morphokinetic parameters vary between male and female preimplantation embryos? DESIGN: This was a retrospective cohort study of 175 cycles between March 2018 and June 2021 at two reproductive centres. It included time-lapse data from 92 female and 83 male preimplantation embryos exclusively issued from fresh oocyte donation and undergoing intracytoplasmic sperm injection (ICSI). Only fresh elective single-embryo transfers on day 5 were assessed, and the sex of the embryo was confirmed at birth. The morphokinetic parameters analysed were measured in hours post-insemination (hpi). A two-tailed Student's t-test was used to compare the morphokinetics between embryo sexes and a value of P < 0.05 was considered statistically significant. RESULTS: Following strict inclusion criteria to avoid poor-quality preimplantation embryos, no significant differences were found in morphokinetic parameters when comparing cycles that resulted in female versus male live births for the following: time to pronuclear fading (22.1 ± 2.4 versus 22.4 ± 2.9 hpi; P = 0.52); time to the 2-cell stage (24.6 ± 2.5 versus 25.0 ± 2.5 hpi; P = 0.34); time to the 3-cell stage (35.3 ± 3.3 versus 35.8 ± 3.1 hpi; P = 0.28); time to the 4-cell stage (36.3 ± 3.4 versus 36.9 ± 3.7 hpi; P = 0.20); time to the 5-cell stage (47.9 ± 4.6 versus 48.0 ± 4.8 hpi; P = 0.88); time to the 8-cell stage (54.0 ± 6.5 versus 54.1 ± 6.5 hpi; P = 0.91); time to the start of blastulation (86.3 ± 14.6 versus 85.7 ± 15.5 hpi; P = 0.78); and time to the full blastocyst stage (93.0 ± 16.9 versus 93.2 ± 17.2 hpi; P = 0.94). CONCLUSIONS: There are no significant differences in morphokinetics between male and female preimplantation embryos.