Imaging Of Embryos Research Articles

Using Unlabeled Information of Embryo Siblings from the Same Cohort Cycle to Enhance In Vitro Fertilization Implantation Prediction.

High-content time-lapse embryo imaging assessed by machine learning is revolutionizing the field of in vitro fertilization (IVF). However, the vast majority of IVF embryos are not transferred to the uterus, and these masses of embryos with unknown implantation outcomes are ignored in current efforts that aim to predict implantation. Here, whether, and to what extent the information encoded within "sibling" embryos from the same IVF cohort contributes to the performance of machine learning-based implantation prediction is explored. First, it is shown that the implantation outcome is correlated with attributes derived from the cohort siblings. Second, it is demonstrated that this unlabeled data boosts implantation prediction performance. Third, the cohort properties driving embryo prediction, especially those that rescued erroneous predictions, are characterized. The results suggest that predictive models for embryo implantation can benefit from the overlooked, widely available unlabeled data of sibling embryos by reducing the inherent noise of the individual transferred embryo.

Embryo Selection for IVF using Machine Learning Techniques Based on Light Microscopic Images of Embryo and Additional Factors.

The current process of embryo selection in In Vitro Fertilization (IVF) process is based on morphological criteria, e.g., Istanbul scoring system and manually evaluated by embryologists; consequently, the assessment can be subjective. In the case of multiple embryos that have the same morphological grading, there is no guidance on how embryos should be prioritized to be transferred. This work aims to develop a deep learning-based model to classify viable and non-viable embryos using light microscopic images of an embryo. Additional features according to Istanbul grading system and the patients' age is also included in the model. Various models are evaluated and the best model based on the fusion of embryo images and additional features provides accuracy, sensitivity, and area under curve (AUC) of 65%, 74.29% and 0.72, respectively. The distributions of the prediction score corresponding to each additional feature are analysed and compared with pregnant and non-pregnant ground truths. We have found that the additional factors, such as age, embryo development stage, the quality of inner cell mass (ICM), and trophectoderm (TE) have a positive impact and enhanced the model prediction of implantation potential.

The Crucial Role of CTCF in Mitotic Progression during Early Development of Sea Urchin.

CCCTC-binding factor (CTCF), an insulator protein with 11 zinc fingers, is enriched at the boundaries of topologically associated domains (TADs) in eukaryotic genomes. In this study, we isolated and analyzed the cDNAs encoding HpCTCF, the CTCF homolog in the sea urchin Hemicentrotus pulcherrimus, to investigate its expression patterns and functions during early development of sea urchin. HpCTCF contains nine zinc fingers corresponding to fingers 2-10 of the vertebrate CTCF. The expression pattern analysis revealed that HpCTCF mRNA was detected at all developmental stages and in the entire embryo. Upon expressing the HpCTCF-GFP fusion protein in early embryos, we observed its uniform distribution within interphase nuclei. However, during mitosis, it disappeared from the chromosomes and subsequently reassembled on the chromosome during telophase. Moreover, the morpholino-mediated knockdown of HpCTCF resulted in mitotic arrest during the morula-to-blastula stage. Most of the arrested chromosomes were not phospholylated at serine 10 of histone H3, indicating that mitosis was arrested at the telophase by HpCTCF depletion. Furthermore, impaired sister chromatid segregation was observed using time-lapse imaging of HpCTCF-knockdown embryos. Thus, HpCTCF is essential for mitotic progression during the early development of sea urchins, especially during the telophase-to-interphase transition. However, the normal development of pluteus larvae in CRISPR-mediated HpCTCF-knockout embryos suggests that disruption of zygotic HpCTCF expression has little effect on embryonic and larval development. This article is protected by copyright. All rights reserved.

Flat mount preparation for whole-mount fluorescent imaging of zebrafish embryos.

The zebrafish is a widely used model organism for biomedical research due to its ease of maintenance, external fertilization of embryos, rapid embryonic development, and availability of established genetic tools. One notable advantage of using zebrafish is the transparency of the embryos, which enables high-resolution imaging of specific cells, tissues, and structures through the use of transgenic and knock-in lines. However, as the embryo develops, multiple layers of tissue wrap around the lipid-enriched yolk, which can create a challenge to image tissues located deep within the embryo. While various methods are available, such as two-photon imaging, cryosectioning, vibratome sectioning, and micro-surgery, each of these has limitations. In this study, we present a novel deyolking method that allows for high-quality imaging of tissues that are obscured by other tissues and the yolk. Embryos are lightly fixed in 1% PFA to remove the yolk without damaging embryonic tissues and are then refixed in 4% PFA and mounted on custom-made bridged slides. This method offers a simple way to prepare imaging samples that can be subjected to further preparation, such as immunostaining. Furthermore, the bridged slides described in this study can be used for imaging tissue and organ preparations from various model organisms.

VolumePeeler: a novel FIJI plugin for geometric tissue peeling to improve visualization and quantification of 3D image stacks

MotivationQuantitative descriptions of multi-cellular structures from optical microscopy imaging are prime to understand the variety of three-dimensional (3D) shapes in living organisms. Experimental models of vertebrates, invertebrates and plants, such as zebrafish, killifish, Drosophila or Marchantia, mainly comprise multilayer tissues, and even if microscopes can reach the needed depth, their geometry hinders the selection and subsequent analysis of the optical volumes of interest. Computational tools to “peel” tissues by removing specific layers and reducing 3D volume into planar images, can critically improve visualization and analysis.ResultsWe developed VolumePeeler, a versatile FIJI plugin for virtual 3D “peeling” of image stacks. The plugin implements spherical and spline surface projections. We applied VolumePeeler to perform peeling in 3D images of spherical embryos, as well as non-spherical tissue layers. The produced images improve the 3D volume visualization and enable analysis and quantification of geometrically challenging microscopy datasets.AvailabilityImageJ/FIJI software, source code, examples, and tutorials are openly available in https://cimt.uchile.cl/mcerda

Practical strategies for robust and inexpensive imaging of aqueous-cleared tissues.

Lightsheet microscopy offers an ideal method for imaging of large (mm-cm scale) biological tissues rendered transparent via optical clearing protocols. However the diversity of clearing technologies and tissue types, and how these are adapted to the microscope can make tissue mounting complicated and somewhat irreproducible. Tissue preparation for imaging can involve glues and or equilibration in a variety of expensive and/or proprietary formulations. Here we present practical advice for mounting and capping cleared tissues in optical cuvettes for macroscopic imaging, providing a standardised 3D cell that can be imaged routinely and relatively inexpensively. We show that acrylic cuvettes cause minimal spherical aberration with objective numerical apertures less than 0.65. Furthermore, we describe methods for aligning and assessing the light sheets, discriminating fluorescence from autofluorescence, identifying chromatic artefacts due to differential scattering and removing streak artefacts such that they do not confound downstream 3D object segmentation analyses, with mouse embryo, liver and heart imaging as demonstrated examples.

Cell fragmentation in mouse preimplantation embryos induced by ectopic activation of the polar body extrusion pathway

Cell fragmentation is commonly observed in human preimplantation embryos and is associated with poor prognosis during assisted reproductive technology (ART) procedures. However, the mechanisms leading to cell fragmentation remain largely unknown. Here, light sheet microscopy imaging of mouse embryos reveals that inefficient chromosome separation due to spindle defects, caused by dysfunctional molecular motors Myo1c or dynein, leads to fragmentation during mitosis. Extended exposure of the cell cortex to chromosomes locally triggers actomyosin contractility and pinches off cell fragments. This process is reminiscent of meiosis, during which small GTPase‐mediated signals from chromosomes coordinate polar body extrusion (PBE) by actomyosin contraction. By interfering with the signals driving PBE, we find that this meiotic signaling pathway remains active during cleavage stages and is both required and sufficient to trigger fragmentation. Together, we find that fragmentation happens in mitosis after ectopic activation of actomyosin contractility by signals emanating from DNA, similar to those observed during meiosis. Our study uncovers the mechanisms underlying fragmentation in preimplantation embryos and, more generally, offers insight into the regulation of mitosis during the maternal‐zygotic transition.

Automated contour extraction for light-sheet microscopy images of zebrafish embryos based on object edge detection algorithm.

Embryo contour extraction is the initial step in the quantitative analysis of embryo morphology, and it is essential for understanding the developmental process. Recent developments in light-sheet microscopy have enabled the in toto time-lapse imaging of embryos, including zebrafish. However, embryo contour extraction from images generated via light-sheet microscopy is challenging owing to the large amount of data and the variable sizes, shapes, and textures of objects. In this report, we provide a workflow for extracting the contours of zebrafish blastula and gastrula without contour labeling of an embryo. This workflow is based on the edge detection method using a change point detection approach. We assessed the performance of the edge detection method and compared it with widely used edge detection and segmentation methods. The results showed that the edge detection accuracy of the proposed method wassuperior to those of the Sobel, Laplacian of Gaussian, adaptive threshold, Multi Otsu, and k-means clustering-based methods, and the noise robustness of the proposed method was superior to those of the Multi Otsu and k-means clustering-based methods. The proposed workflow was shown to be useful for automating small-scale contour extractions of zebrafish embryos that cannot be specifically labeled owing to constraints, such as the availability of microscopic channels. This workflow may offer an option for contour extraction when deep learning-based approaches or existing non-deep learning-based methods cannot be applied.

Noninvasive genetic screening: current advances in artificial intelligence for embryo ploidy prediction

This review discusses the use of artificial intelligence (AI) algorithms in noninvasive prediction of embryo ploidy status for preimplantation genetic testing in invitro fertilization procedures. The current gold standard, preimplantation genetic testing for aneuploidy, has limitations, such as an invasive biopsy, financial burden, delays in results reporting, and difficulty in results reporting, Noninvasive ploidy screening methods, including blastocoel fluid sampling, spent media testing, and AI algorithms using embryonic images and clinical parameters, are explored. Various AI models have been developed using different machine learning algorithms, such as random forest classifier and logistic regression, have shown variable performance in predicting euploidy. Static embryo imaging combined with AI algorithms have demonstrated good accuracy in ploidy prediction, with models such as Embryo Ranking Intelligent Classification Algorithm and STORK-A outperforming human grading. Time-lapse embryo imaging analyzed by AI algorithms has also shown promise in predicting ploidy status; however, the inclusion of clinical parameters is crucial to improving the predictive value of these models. Mosaicism, an important aspect of embryo classification, is often overlooked in AI algorithms and should be considered in future studies. The integration of AI algorithms into microscopy equipment and Embryoscope platforms will facilitate noninvasive genetic testing. Further development of algorithms that optimize clinical considerations and incorporate minimal-necessary covariates will also enhance the predictive value of AI in embryo selection. Artificial intelligence-based ploidy prediction has the potential to improve pregnancy rates and reduce costs in invitro fertilization cycles.

O-006 Novel and scalable non-invasive metabolic imaging of early embryos using a lab-on-a-chip approach

Abstract Study question Is it feasible to safely determine metabolic imaging signatures to measure nicotinamide adenine dinucleotide (NADH) associated auto-fluorescence in early embryos using a scalable lab-on-a-chip approach? Summary answer We developed an optofluidic device capable of non-invasively obtain high-resolution 3D images of the metabolic activity of live mouse embryos using a lab-on-a-chip approach. What is known already Selecting the most suitable embryos for implantation and subsequent healthy live birth is crucial to the success rate of assisted reproduction and offspring health. Thus, developing non-invasive methods that are reliable to assess oocyte and embryo quality has been a significant aim for assisted reproduction. Besides morphological evaluation using optical microscopy, a promising alternative is the non-invasive imaging of live embryos to establish metabolic activity performance. However, metabolic imaging has been only achieved using highly complex advanced microscopy such as Fluorescence-lifetime imaging (FLIM) and hyperspectral microscopy, methods that are costly and challenging, limiting the potential for deployment in fertility clinics. Study design, size, duration The non-invasive nature of the system was investigated by assessing the development and viability of live embryos after embryo culture for 67hrs post metabolic imaging at the 2-cell embryo stage (n = 115), including a control for culture conditions and sham controls (system no-illuminated). Embryo quality of developed blastocysts was assessed by immunocytochemistry to quantify trophectoderm and inner mass cells (n = 75). Furthermore, inhibition of metabolic activity (FK866 inhibitor) during embryo culture was also assessed (n = 18). Participants/materials, setting, methods Optofluidic devices were manufactured by cast-moulding using a negative photoresist (SU8-2075; MicroChemicals GmbH, Ulm, Germany) by a standard UV-photolithography process. The microstructures fabricated of polydimethylsiloxane (PDSM) integrated Light Sheet Fluorescence Microscopy into a microfluidic system, including on-chip micro-lenses to generate a light sheet at the center of a microchannel. Super-ovulated F1 (CBA/C57Bl6) mice were used to produce 2-cell embryos and embryo culture experiments. Blastocyst formation rates and embryo quality (immunocytochemistry) were compared between study groups. Main results and the role of chance The optofluidic device was capable of non-invasively obtaining high-resolution 3D images of the metabolic activity in live mouse embryos. The system’s design allowed continuous tracking of the embryo location, including high control displacement through the light-sheet, fast imaging of the embryos (<2 second) and keeping a low dose of light exposure (16 J cm-2 and 8 J cm-2). Optimum settings for keeping sample viability showed that a modest light dosage was capable to obtain 30 times higher signal-noise-ratio images than images obtained with a confocal system (p < 0.00001; t-test). The results showed no significant differences between the control, illuminated and non-illuminated embryos (sham control) for embryo development as well as embryo quality at the blastocyst stage (p > 0.05; Yate’s chi squared test). Additionally, embryos with inhibited metabolic activity showed decreased blastocyst formation rates as well as 47% reduction in metabolic activity measured by non-invasive metabolic imaging (p < 0.0001; t-test). This study reports an optofluidic device capable of non-invasive metabolic imaging of live embryos using a similar concept as previously reported using FLIM technology and hyperspectral microscopy, but allowing a novel, scalable and affordable system with implementation potential in standard IVF laboratory equipment. Limitations, reasons for caution The study was conducted using a mouse model focused on early embryo development. Further safety studies are required to assess embryonic health by investigating the impact of the use of light during embryo development, live birth, embryo gene expression and epigenome stability. Wider implications of the findings This lab-on-a-chip is novel, scalable and has the potential to be used in fertility clinics as a technology platform to enable real-time monitoring of the metabolic function of embryos prior embryo transfer. Future applications include potential integration into existing IVF laboratory equipment such as bench and time-lapse incubators. Trial registration number N/A

O-099 The inner cell mass (ICM) regions can be used to predict pregnancy with a similar accuracy as the original images of the entire embryo

Abstract Study question Can clinical pregnancy be accurately predicted using only ICM and TE regions in an embryo microscopy image? Summary answer The AI model accurately predicted pregnancy using ICM segmented images with a similar accuracy as using original embryo images. What is known already Previous research suggests that ICM and TE are key factors in determining embryo grade and clinical pregnancy. Grad-CAM images on the CNN models in various literature also highlight the significance of ICM and TE regions. However, there have been no studies to compare and assess the importance of the two regions in pregnancy prediction. This study aims to test the significance of each region by evaluating the performance of models after segmenting ICM and TE regions. Study design, size, duration We performed a retrospective study of single static images of 2,555 Day 5 blastocysts from seven in vitro fertilization (IVF) clinics between June 2011 and May 2022. The images were collected from standard optical light microscopes and matched with metadata such as pregnancy outcomes. ICM and TE regions were manually labeled and examined by 5 embryologists with over 10 years of experience. Participants/materials, setting, methods We defined a positive pregnancy indication as the presence of a gestational sac (G-SAC). We built 4 CNN models using original embryo images (“Original model”), ICM segmented images (“ICM model”), TE segmented images (“TE model”) and ICM & TE segmented images (“ICM & TE model”). The performances were measured through 3-fold cross validation. Main results and the role of chance In 3-fold cross validation, the mean and the standard deviation of AUROCs were 0.753±0.005 for Original model, 0.733±0.003 for ICM model, 0.724±0.016 for ICM & TE model and 0.690±0.011 for TE model, respectively. The DeLong test showed significant differences between the AUCs of Original model and ICM model (p = 0.01), and ICM model and ICM & TE model (p = 0.0003). Positive correlations were found between prediction values with pearson correlation [Confidence interval] for Original image and ICM model (0.426 [0.343, 0.495]), Original model and ICM & TE model (0.345 [0.266, 0.419]) and Original model and TE model (0.223 [0.140, 0.304]). Original model showed the highest accuracy and TE model was the least accurate as expected. However, it is noteworthy that ICM model outperformed ICM & TE model. Although it is well known that TE plays a significant role in implantation, forcing the model to utilize both ICM and TE to predict pregnancy could have muddled the analysis. This study proved that pregnancy can be successfully predicted using ICM regions only as well as original embryo images. Limitations, reasons for caution This study has limitations due to its retrospective nature, using embryo images from seven IVF centers. Further study with a larger dataset is warranted to offset the differences in focus, magnification and color of embryo images. Wider implications of the findings We showed that the AI model using ICM segmented images predicted pregnancy with a similarly high accuracy as using original embryo images. However, the model using TE segmented images showed the lowest performances. Utilizing well-focused ICM images may enhance the performance of pregnancy prediction models. Trial registration number not applicable

P-267 Artificial intelligence (AI) can successfully predict pregnancy despite of the visual differences of fresh and frozen-thawed embryos

Abstract Study question Can AI accurately predict pregnancy from fresh and frozen-thawed embryo images that may exhibit visual differences? Summary answer AI was able to distinguish between fresh and frozen images based on visual differences, but these differences did not affect the accuracy of pregnancy prediction. What is known already Frozen-thawed embryos may experience changes to their structure and composition, though these changes are difficult to detect with the human eye. AI has been shown to predict pregnancy by analyzing embryo images in IVF cycles. However, there has been no evidence to suggest that the morphologic changes caused by cryopreservation affect AI's pregnancy predictions. In this study, we developed an AI model to distinguish between images of fresh and frozen-thawed embryos and evaluated if the visual differences affected pregnancy prediction. Study design, size, duration We performed a retrospective study of single static images of 2,237 Day 5 blastocysts from two in vitro fertilization (IVF) clinics between February 2001 and December 2021. The images were collected from standard optical light microscopes and matched with metadata such as pregnancy outcomes, cryopreservation and assisted hatching information. We defined a positive pregnancy indication as the presence of a gestational sac (G-SAC). Participants/materials, setting, methods We constructed two CNN models to verify two hypotheses. The first model was a classification model that utilized day 5 images of fresh and frozen-thawed embryos from two IVF clinics. The proportion of fresh to frozen-thawed at each clinic was 603 to 667 and 402 to 565, respectively. The second model was a CNN designed to predict pregnancy and its performance was compared after incorporating the cryopreservation label through internal validation. Main results and the role of chance The first AI model classified frozen-thawed and fresh embryos with high AUROCs (0.848 and 0.912) and accuracy (0.846 and 0.912) at each clinic. The Grad-CAM images revealed that the AI learned to differentiate the two types of images based on features mainly in the embryo's zona pellucida region. The AUROCs of the second AI model for pregnancy prediction were 0.730 and 0.663 at each clinic, respectively. Adding the cryopreservation label did not significantly change the AUROCs, which remained at 0.734 and 0.650. The study found that the visual differences between fresh and frozen-thawed embryos had no effect on the performance of the pregnancy prediction model. It's important to note that assisted hatching was used in 88% of the frozen-thawed cycles in the study, which may have compensated for the changes to the zona pellucida caused by cryopreservation. Limitations, reasons for caution This study was validated using data from two IVF clinics, and a larger dataset from multiple centers is needed for external validation. Further research on non-assisted hatching (AH) cycles is necessary to confirm the role of AH in frozen-thawed cycles. Wider implications of the findings The study found that AI can accurately differentiate between fresh and frozen-thawed embryos by analyzing the zona pellucida region. The visual differences between the two types of embryos did not impact the accuracy of pregnancy prediction. Assisted hatching may also mitigate any negative effects on frozen-thawed embryos. Trial registration number not applicable

P-279 Comparison of AI model performance in predicting blastulation in old and young mice groups

Abstract Study question Is there a difference in AI performance in predicting blastulation between young and old mice? Summary answer AI performance in predicting blastulation is higher in young mice than in old mice. What is known already Previous studies have demonstrated AI's ability to predict oocyte development using oocyte or embryo images, but there has been no study to determine if AI performance varies with the age of the female. Maternal age influences oocyte quality and development, but other factors such as diet and environment also play a role. Using mouse experiments can minimize these confounding factors. The study aims to determine if there is a difference in AI performance for predicting blastulation using oocyte images from old and young mice. Study design, size, duration We collected oocyte images from 673 B6D2F1 (BDF1) mice at a single research center between July 2022 and January 2023. The samples were separated into two groups based on maternal age, 386 from young mice and 287 from old mice. The development stages including fertilization and blastulation were recorded through daily observation, and the data was divided into a training set of 3 batches and a test set of 2 batches. Participants/materials, setting, methods The mice were divided into two groups: young mice (7-9 weeks old) and old mice (62-68 weeks old). The study used images of MII oocytes collected after superovulation, taken with a 200x inverted microscope, and cultured in a single drop. A CNN was trained to predict blastulation and compared for accuracy between the young and old mouse groups. Blastulation was determined by observing the presence of expanded blastocysts or above on day 4. Main results and the role of chance The study used 203 and 182 oocyte images of young and old mice respectively for training, and 183 and 105 images for testing. Three convolutional neural network models (VGG16, ResNet50, and DenseNet121) were used to predict blastulation, and ResNet50 was selected as the final model. Without considering age, the accuracy, sensitivity, and specificity of the AI for predicting blastulation were 0.75, 0.74, and 0.76, respectively. The AI model used in the study had accuracy of 0.77, sensitivity of 0.75, and specificity of 0.79 in the young mice group. In the old mice group, the model had accuracy of 0.72, sensitivity of 0.70, and specificity of 0.74. When a t-test was performed, there was a statistically significant difference in accuracy (p = 0.014) with better accuracy in young mice. On the contrary, the sensitivity in the old mice group was the lowest, making it difficult to predict blastulation. As oocyte morphology does not always represent aneuploidy, the AI model using oocyte images may not perform well in the old mice group due to increased aneuploidy. Limitations, reasons for caution The limitations of this study include its retrospective design using oocyte images from only one research center. A larger, multicenter study would be beneficial. Wider implications of the findings The study found that AI accurately predicted blastulation using mice oocyte images, with higher accuracy for both positive and negative outcomes in young mice. However, accuracy was lower in old mice, particularly for positive outcome, suggesting the need for additional tests like genetic testing for predicting blastulation in old mice. Trial registration number not applicable

P-144 An artificial intelligence algorithm demonstrates optimal performance for evaluating embryo genetic status at 120 hours post-fertilization

Abstract Study question What is the effect of time-point on performance of a non-invasive artificial intelligence (AI) algorithm for evaluating embryo genetic status? Summary answer While predictive ability was maintained across different time-points on day 5, optimal performance for ranking and selecting euploid embryos was observed at 120 hours post-fertilization. What is known already Studies have shown that it is possible to develop computer vision-based AI algorithms capable of predicting embryo ploidy status using single images of blastocyst-stage embryos. The genetic status of embryos is linked to morphokinetic development, with aneuploidy generally resulting in earlier arrest. Given the dynamic nature of embryo development, it might be expected that the time-point selected for analysis could influence AI performance. The key questions remaining to be answered are to what extent is AI analysis affected by expansion grade, and what does this mean for selection of a time-point for evaluation? Study design, size, duration 2,683 images of day 5 blastocyst-stage embryos with matched ploidy outcomes from pre-implantation genetic testing for aneuploidies (PGT-A) were provided by 10 IVF clinics in the USA, Australia, Malaysia, and India. A subset of 182 embryos had images provided at 110, 115, and 120 hour time points (GERI and EmbryoScope time lapse systems). Participants/materials, setting, methods Images were analysed by a previously developed AI algorithm which evaluates the likelihood of an embryo being euploid according to PGT-A (Diakiw et al, 2022. Hum Reprod, Jul 30;37(8):1746-1759). Evaluation was performed on embryos of each expansion grade, and at three time-points on day 5. Correlations were assessed using Chi-squared test for trend, with pair-wise comparisons conducted using Student’s t-test. Performance was evaluated using ROC-AUC, and a simulated cohort ranking analysis method. Main results and the role of chance AI scores positively correlated with expansion grade, and expansion grade likewise correlated with an increasing proportion of euploid embryos. AI scores also increased over time on day 5, consistent with continued embryo expansion. Scores for grade 4 (expanded) embryos increased more than for grade 5 (hatching) embryos (+2.2-fold and +0.8-fold, respectively), indicative of continued expansion becoming limited at later stages. Despite the valid association of AI scores with expansion grade, results showed the AI could predict euploidy even amongst embryos of the same expansion grade (ROC-AUC ranging from 0.61−0.69). While predictive ability was maintained at each time-point on day 5, ROC-AUC values were highest at 120 hours (0.64, 0.64, and 0.68 for 110, 115, and 120 hours, respectively). Simulated cohort ranking analyses also showed that the AI performed best at 120 hours, selecting a euploid embryo as the top-ranked embryo in 77.1% of patient cohorts (71.4%, 75.1%, and 77.1% for 110, 115, and 120 hours, respectively). These results suggest that regardless of expansion grade, all embryos should be assessed at the same time-point on day 5, preferably closer to the 120 hour time-point. Limitations, reasons for caution The time-point analyses were conducted on a relatively small dataset, and therefore findings should be validated on a larger dataset including embryos of other expansion grades. The analysis was limited to day 5 post-fertilization, however it would be interesting to extend the study to embryos on day 6 also. Wider implications of the findings These results suggest that the AI is providing additional information regarding embryo genetic status, over and above that provided by known morphological parameters. The dynamic nature of AI score related to expansion is of interest as it relates to the optimal time-point for conducting analyses for selection of euploid embryos. Trial registration number Not applicable

P-204 The pattern of the zygote cleavage to three cells must be considered before embryo transfer

Abstract Study question What is the clinical outcome of instant irregular cleavage (IDC) from zygote to three cells? Summary answer IDC embryos, did not develop to blastocysts and did not acieve pregnancy; FC embryos that reached blastocyst stage exerted similar pregnancy rates as control embryos What is known already Evaluation of the zygote morphology is one of the earliest embryonic stages investigated. Several zygote grading systems were proposed based on pronuclei size and NPB (nucleolus precursor bodies) distribution, thus is an effective indicator of the embryo’s potential to result in a life birth. The first cleavage of a zygote is a highly coordinated event. Disruptive timing of the first cleavage, named direct cleavage (DC, less than 5 hours), is associated with formation of poor embryo quality. Early identification of pathological embryos is challenging and impacts the timing of embryo fate decision in ART. Study design, size, duration A total of 1978 fresh IVF cycles from single unit were analyzed and a total of 4012 embryos were studied. Only 2pn embryos, cultured exclusively in time-lapse system for 5 days were included. The morphokinetics of embryos and their outcome were recorded, from z-score analysis through day 5. We discriminated between IDC, FC and normal cleavage pattern of embryos and compared clinical outcome of various morphokinetic parameters. We also evaluated possible early predictors for IDC. Participants/materials, setting, methods We generated three study groups according to embryo cleavage pattern: (I) Control, normal cleavage (n = 551); (II) FC, zygote to three cells within 5 hours (n = 1587); (III) IDC, instant cleavage from zygote to three cells (n = 922). The association between z-score of 138 IDC embryos and their sibling random controls was thoroughly investigated. All time lapse annotations were performed by senior embryologists. Statistical analysis was performed by SPSS software. Main results and the role of chance IDC embryos were mainly arrested at day 3 and the number of usable embryos (reached blastocyst stage and were suitable for embryo transfer or cryopreservation) was negligible; 4/922 (0.4%). In comparison, the amount of usable FC embryos was 108/1587 (6.6%) and control embryos usage reached 180/551 (32.7%). While the pregnancy rate of control and FC embryos, which reached embryo transfer were similar (40.35% and 42.55%, respectively); transfer of IDC embryos did not result in pregnancy. Additionally, the timetable as measured by time of PN fading and time from fading to first cleavage, differed significantly between the three groups. Therefore, we performed a thorough analysis of zygote morphology data of IDC embryos compared to control sibling embryos in search of early possible markers for these findings. We have not detected significant differences in z-score analysis, reflected by number and size of nucleoli, as well as pronuclear symmetry. Limitations, reasons for caution IDC embryos number used for z-score analysis was limited since many didn’t meet the inclusion criteria (lack of overlapping of the pronuclei, presence of random of control embryo and good quality image). Wider implications of the findings The decision regarding the fate of IDC and FC embryos should include the pattern of first cycle cleavage. Culture IDC and FC embryos for 5 days up to the blastocyst will spare transfer of embryos that are fated to arrest even when their morphological grade on day 3 is acceptable. Trial registration number 0043-22-MMC

O-158 Prediction of implantation of vitrified-warmed blastocysts using a deep learning algorithm on a single post-warming image of each embryo

Abstract Study question Can a deep learning algorithm determine the implantation likelihood of vitrified blastocysts from single time-point post-warming time-lapse images obtained from EmbryoScope? Summary answer A significant positive correlation was found between the score given by the deep learning algorithm and the implantation rate of the frozen blastocysts analyzed. What is known already Despite the safety and success of the vitrification technique, many of the best morphologically classified embryos prior to vitrification do not maintain their characteristics when returned to room temperature. Since artificial intelligence (AI) has been shown to be useful in assessing the quality of fresh embryos at different stages, it could also be used to predict the outcome of frozen embryo transfers. This is the first attempt to distinguish vitrified blastocysts that will implant from those that will not by applying deep learning on a single image taken in the period between warming and transfer. Study design, size, duration This retrospective single-centre study included 689 blastocysts with known implantation data. All of them were vitrified and warmed using the Cryotop method (Kitazato, Biopharma, Japan). Warmed embryos were assessed by experienced embryologists according to the ASEBIR morphological scoring system and the degree of expansion. Immediately after warming, blastocysts were placed in EmbryoScope (Vitrolife, Denmark) time-lapse incubators for 2-5 hours to let them re-expand until embryo transfer. Participants/materials, setting, methods A pre-transfer embryo image was provided to the algorithm (Life Whisperer Viability), which returned scores from 0 to 10. Data were analyzed by chi-square test or one-way ANOVA. Multivariate logistic regression analysis was performed including embryo score, oocyte origin (donated vs. autologous), oocyte age, patient age, oocyte handling (fresh vs. vitrified eggs), and day of vitrification (5 vs. 6). The area under the receiver operating characteristic (ROC) curve (AUC) was used to calculate evaluation performance. Main results and the role of chance There was a significant difference between the scores given to vitrified implanted and non-implanted embryos. The mean value was 4.98 [95% CI 4.70-5.26]* for non-implanted embryos and 6.16 [95% CI 5.84-6.48]* for implanted embryos. When dividing the embryo score by quartiles, the implantation rate for each quartile was 27.7% for Q1, 33.7% for Q2 (Odds ratio (OR)=1.31 [0.82–2.09]), 44.8% for Q3 (OR = 2.05 [1.30–3.22]*) and 48.3% for Q4 (OR = 2.46 [1.56–3.87]*). The contribution of each increased unit of the algorithm score to the implantation (OR = 1.16 [95% CI: 1.09–1.23]*) was statistically significant. The deep learning algorithm score successfully predicted implantation with an AUC of 0.65 [95% CI: 0.60–0.69]*. Moreover, the algorithm performed better than the ASEBIR morphological classification, which achieved an AUC of 0,62 [95% CI: 0.58–0.66] in predicting implantation. *P < 0.001. Limitations, reasons for caution Our clinic was not involved in the development of the algorithm. Furthermore, it was designed to assess fresh embryos prior to vitrification but not thawed ones, so this study should be considered an external trial. A post-warming full video analysis by AI could possibly provide additional information. Wider implications of the findings The use of predictive models on vitrified cycles may help to select the best frozen embryo for transfer and predict which embryos will result in implantation failure early enough to thaw another one with a better chance of success. It also indicates that AI can generalize to thawed embryo assessment. Trial registration number -

P-295 Application of a Time-Lapse Optical Coherence Tomography (OCT) approach in a pilot study to visualise oocytes and embryos in depth

Abstract Study question Can we visualise model oocytes and embryos during embryo development using OCT non-invasively? Summary answer This approach, new to embryology, OCT, allows visualising cells in a 3D perspective, providing more detailed information than standard microscopy from the oocyte or embryo. What is known already Time-lapse is a well-established technique in human IVF, but it is limited in its depth of view due to the limitations of classical microscopy. To overcome this limitation, the approach of Optical Coherence Tomography (OCT), allows non-invasive visualisation through optical cross-sections of the embryo or oocyte to produce 3D images. The obtained information can be extended to 4 or 5 dimensions to track movement and elasticity, using a low-power light source and no staining to ensure the minimum effect on the cell. Here, a pilot study was performed in model (porcine) samples using a newly developed “in incubator” system. Study design, size, duration A pilot basic study was performed where 16 oocytes and 16 cleavage embryos were obtained and prepared to be visualised using OCT. Participants/materials, setting, methods Pig ovaries were obtained from a slaughterhouse, from which follicles were aspirated in order to retrieve oocytes. The best-quality oocytes were cultured for maturation for 44 hours and 16 oocytes were selected for OCT imaging. before fertilisation for 2 hours. Sperm was previously prepared by Percoll gradient. Zygotes were cultured for 6 days until visualisation through OCT. For imaging, samples were prepared in a 16-well Primo Vision dish. Main results and the role of chance Oocytes and embryos were successfully imaged, allowing the identification of distinct cellular features. In oocytes, it was possible to identify the germinal vesicle (nucleus) and polar bodies, individual blastomeres in cleavage stage embryos and trophectoderm, ICM and blastocoel in blastocysts. As images were taken throughout different optical sections, it was possible to correlate the position of the areas within the oocytes/embryos and create a 3D image from a blastocyst, understanding the size of the inner cell mass compared with the embryo's overall size. Interestingly, images were obtained non-invasively and under optimal conditions (in an incubator), demonstrating the future utility of OCT for embryo imaging. Limitations, reasons for caution An experimental OCT system was developed and placed in the incubator, and all images obtained were in a format of a pilot study. Future imaging sessions are planned to obtain more data points and assess the viability of the embryo. Wider implications of the findings Although in the present study, OCT was applied in pig oocytes and embryos, this new approach can be employed in future for human IVF to overcome the current imaging limitations, proving more information on the oocytes and embryos’ quality and assisting Artificial Intelligence analysis. Trial registration number not applicable

P-158 Effect of women body mass index on in vitro embryos development and effectiveness of «Assisted reproductive technologies»

Abstract Study question Does a woman's body mass index (BMI) affect the development of an embryo in vitro? Summary answer Evaluation of the development of embryos indicates that the overweight affects the development of the embryo and associated with a lower rate of live births. What is known already Excess weight and obesity - as a cause of infertility, occures against the background of existing metabolic disorders. Severe thinness and, like obesity, often lead to violations of the interval and reproductive functions of a woman. An increase in adipose tissue of more than 20% or more leads to dysfunction of the hypothalamic-pituitary-ovarian system. With obesity and emaciation of the body, a woman has various forms of menstrual disorders, the frequency of uterine bleeding and also endometrial pathology increases. Study design, size, duration This study included the retrospective analysis of Assisted Reproductive Technologies (ART) cycles using statistical data on the development of embryos in the Embryological laboratory, pregnancy and childbirth was carried out from 2016 to 2018. Morphological studies were carried out using Time-Lapse embryo imaging. Participants/materials, setting, methods In this study, morphological and biostatistical methods were used. The cohort of patients aged 20 to 45 years was divided into four groups: 1623 embryos from 243 underweight women; 19542 embryos from 2270 normal weight women (control group); 9701 embryos from 1069 overweight women; and 2668 embryos from 343 obese women. Main results and the role of chance In the group of underweight women the pregnancy rate is 46%, which is 3% less than in overweight and obese group of women, while the percentage of the control group is 47.5%. However, the results of live births in group of women with obesity is 7% less than in women of normal weight, which is 29 and 36 percent respectively. In addition, a comparative analysis of the number of fertilized eggs showed that at a normal BMI, 6.3 ± 0.4 oocytes were fertilized, while in the group of women with second-degree obesity only 4.2 ± 0.3 oocytes. Based on the results of the T-test, it can be concluded that these indicators have differences with a significance level of less than 0.05. Also, the results obtained indicate differences in the maturity of embryos at the blastocyst stage, where blastocysts of excellent quality matured in the control group of 3.4 ± 0.4 embryos, and in the experimental group with obese women 2.4 ± 0.1 embryos. Furthermore, the frequency of live births showed a relationship between the norm and high BMI. In the control group, the result was 0.7 ± 0.02, while in first-degree obesity, the result was 0.2 ± 0.06. Limitations, reasons for caution The main limitation of this study is a verity of women with different anamnesis, which were not taken into account. The grading of blastocysts is subjected to a human factor. The limitation of the Time-lapse technology is the inability to rotate the embryos making it very difficult to observe. Wider implications of the findings This method needs further investigations about limitations, such as the age of patients, type and heaviness of infertility, existing diseases and previous pregnancies in anamnesis. Trial registration number Not Applicable

Efficient red-emitting carbon dots for bioimaging and spectral engineering by polyetherimide modification

A novel type of red-emitting carbon dots was synthesized using urea and neutral red via the solvothermal method at a temperature of 200 °C for 4 h. The resulting CDs, named NR-CDs, display a distinct red emission at 620 nm when excited at a wavelength of 470 nm, achieving a quantum yield of 61.11% in acetone. Interestingly, NR-CDs exhibit strict solvent polarity dependence, i.e. the emission wavelength of NR-CDs red-shifts with an increase in solvent polarity. Besides, when incubated with NR-CDs and excited by an excitation wavelength of 470 nm, 4-T1 cells emit a clear red fluorescence. Meanwhile, high-quality in-vivo fluorescent images of zebrafish embryos and larvae were obtained by incubating with NR-CDs. Moreover, by modifying with polyetherimide (PEI), the peak value of PEI-NR-CDs shifts from 620 nm to 596 nm, and the emission is increased by 264 %. Co-localization experiment with commercial dye (Lyso-Tracker Green) shows that PEI-NR-CDs are localized in lysosomes and could be used as a lysosomal tracer for cells. Furthermore, PEI-NR-CDs were prepared into fluorescent ink, which exhibited orange fluorescence under UV light. All results demonstrate that as-obtained NR-CDs and PEI-NR-CDs can be used as reagent for fluorescent-imaging application.

Embryo selection through artificial intelligence versus embryologists: a systematic review.

What is the present performance of artificial intelligence (AI) decision support during embryo selection compared to the standard embryo selection by embryologists? AI consistently outperformed the clinical teams in all the studies focused on embryo morphology and clinical outcome prediction during embryo selection assessment. The ART success rate is ∼30%, with a worrying trend of increasing female age correlating with considerably worse results. As such, there have been ongoing efforts to address this low success rate through the development of new technologies. With the advent of AI, there is potential for machine learning to be applied in such a manner that areas limited by human subjectivity, such as embryo selection, can be enhanced through increased objectivity. Given the potential of AI to improve IVF success rates, it remains crucial to review the performance between AI and embryologists during embryo selection. The search was done across PubMed, EMBASE, Ovid Medline, and IEEE Xplore from 1 June 2005 up to and including 7 January 2022. Included articles were also restricted to those written in English. Search terms utilized across all databases for the study were: ('Artificial intelligence' OR 'Machine Learning' OR 'Deep learning' OR 'Neural network') AND ('IVF' OR 'in vitro fertili*' OR 'assisted reproductive techn*' OR 'embryo'), where the character '*' refers the search engine to include any auto completion of the search term. A literature search was conducted for literature relating to AI applications to IVF. Primary outcomes of interest were accuracy, sensitivity, and specificity of the embryo morphology grade assessments and the likelihood of clinical outcomes, such as clinical pregnancy after IVF treatments. Risk of bias was assessed using the Modified Down and Black Checklist. Twenty articles were included in this review. There was no specific embryo assessment day across the studies-Day 1 until Day 5/6 of embryo development was investigated. The types of input for training AI algorithms were images and time-lapse (10/20), clinical information (6/20), and both images and clinical information (4/20). Each AI model demonstrated promise when compared to an embryologist's visual assessment. On average, the models predicted the likelihood of successful clinical pregnancy with greater accuracy than clinical embryologists, signifying greater reliability when compared to human prediction. The AI models performed at a median accuracy of 75.5% (range 59-94%) on predicting embryo morphology grade. The correct prediction (Ground Truth) was defined through the use of embryo images according to post embryologists' assessment following local respective guidelines. Using blind test datasets, the embryologists' accuracy prediction was 65.4% (range 47-75%) with the same ground truth provided by the original local respective assessment. Similarly, AI models had a median accuracy of 77.8% (range 68-90%) in predicting clinical pregnancy through the use of patient clinical treatment information compared to 64% (range 58-76%) when performed by embryologists. When both images/time-lapse and clinical information inputs were combined, the median accuracy by the AI models was higher at 81.5% (range 67-98%), while clinical embryologists had a median accuracy of 51% (range 43-59%). The findings of this review are based on studies that have not been prospectively evaluated in a clinical setting. Additionally, a fair comparison of all the studies were deemed unfeasible owing to the heterogeneity of the studies, development of the AI models, database employed and the study design and quality. AI provides considerable promise to the IVF field and embryo selection. However, there needs to be a shift in developers' perception of the clinical outcome from successful implantation towards ongoing pregnancy or live birth. Additionally, existing models focus on locally generated databases and many lack external validation. This study was funded by Monash Data Future Institute. All authors have no conflicts of interest to declare. CRD42021256333.