Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization. NPJ Digit Med. 2019;2:21. [PMID: 31304368 PMCID: PMC6550169 DOI: 10.1038/s41746-019-0096-y]

Automatic ploidy prediction and quality assessment of human blastocysts using time-lapse imaging

Assessing fertilized human embryos is crucial for in vitro fertilization, a task being revolutionized by artificial intelligence. Existing models used for embryo quality assessment and ploidy detection could be significantly improved by effectively utilizing time-lapse imaging to identify critical developmental time points for maximizing prediction accuracy. Addressing this, we develop and compare various embryo ploidy status prediction models across distinct embryo development stages. We present BELA, a state-of-the-art ploidy prediction model that surpasses previous image- and video-based models without necessitating input from embryologists. BELA uses multitask learning to predict quality scores that are thereafter used to predict ploidy status. By achieving an area under the receiver operating characteristic curve of 0.76 for discriminating between euploidy and aneuploidy embryos on the Weill Cornell dataset, BELA matches the performance of models trained on embryologists' manual scores. While not a replacement for preimplantation genetic testing for aneuploidy, BELA exemplifies how such models can streamline the embryo evaluation process.

Visual interpretability of image-based classification models by generative latent space disentanglement applied to in vitro fertilization

The success of deep learning in identifying complex patterns exceeding human intuition comes at the cost of interpretability. Non-linear entanglement of image features makes deep learning a "black box" lacking human meaningful explanations for the models' decision. We present DISCOVER, a generative model designed to discover the underlying visual properties driving image-based classification models. DISCOVER learns disentangled latent representations, where each latent feature encodes a unique classification-driving visual property. This design enables "human-in-the-loop" interpretation by generating disentangled exaggerated counterfactual explanations. We apply DISCOVER to interpret classification of in vitro fertilization embryo morphology quality. We quantitatively and systematically confirm the interpretation of known embryo properties, discover properties without previous explicit measurements, and quantitatively determine and empirically verify the classification decision of specific embryo instances. We show that DISCOVER provides human-interpretable understanding of "black box" classification models, proposes hypotheses to decipher underlying biomedical mechanisms, and provides transparency for the classification of individual predictions.

Testing an artificial intelligence algorithm to predict fetal heartbeat of vitrified-warmed blastocysts from a single image: predictive ability in different settings

STUDY QUESTION

Could an artificial intelligence (AI) algorithm predict fetal heartbeat from images of vitrified-warmed embryos?

SUMMARY ANSWER

Applying AI to vitrified-warmed blastocysts may help predict which ones will result in implantation failure early enough to thaw another.

WHAT IS KNOWN ALREADY

The application of AI in the field of embryology has already proven effective in assessing the quality of fresh embryos. Therefore, it could also be useful to predict the outcome of frozen embryo transfers, some of which do not recover their pre-vitrification volume, collapse, or degenerate after warming without prior evidence.

STUDY DESIGN, SIZE, DURATION

This retrospective cohort study included 1109 embryos from 792 patients. Of these, 568 were vitrified blastocysts cultured in time-lapse systems in the period between warming and transfer, from February 2022 to July 2023. The other 541 were fresh-transferred blastocysts serving as controls.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Four types of time-lapse images were collected: last frame of development of 541 fresh-transferred blastocysts (FTi), last frame of 467 blastocysts to be vitrified (PVi), first frame post-warming of 568 vitrified embryos (PW1i), and last frame post-warming of 568 vitrified embryos (PW2i). After providing the images to the AI algorithm, the returned scores were compared with the conventional morphology and fetal heartbeat outcomes of the transferred embryos (n = 1098). The contribution of the AI score to fetal heartbeat was analyzed by multivariate logistic regression in different patient populations, and the predictive ability of the models was measured by calculating the area under the receiver-operating characteristic curve (ROC-AUC).

MAIN RESULTS AND THE ROLE OF CHANCE

Fetal heartbeat rate was related to AI score from FTi (P < 0.001), PW1i (P < 0.05), and PW2i (P < 0.001) images. The contribution of AI score to fetal heartbeat was significant in the oocyte donation program for PW2i (odds ratio (OR)=1.13; 95% CI [1.04-1.23]; P < 0.01), and in cycles with autologous oocytes for PW1i (OR = 1.18; 95% CI [1.01-1.38]; P < 0.05) and PW2i (OR = 1.15; 95% CI [1.02-1.30]; P < 0.05), but was not significantly associated with fetal heartbeat in genetically analyzed embryos. AI scores from the four groups of images varied according to morphological category (P < 0.001). The PW2i score differed in collapsed, non-re-expanded, or non-viable embryos compared to normal/viable embryos (P < 0.001). The predictability of the AI score was optimal at a post-warming incubation time of 3.3-4 h (AUC = 0.673).

LIMITATIONS, REASONS FOR CAUTION

The algorithm was designed to assess fresh embryos prior to vitrification, but not thawed ones, so this study should be considered an external trial.

WIDER IMPLICATIONS OF THE FINDINGS

The application of predictive software in the management of frozen embryo transfers may be a useful tool for embryologists, reducing the cancellation rates of cycles in which the blastocyst does not recover from vitrification. Specifically, the algorithm tested in this research could be used to evaluate thawed embryos both in clinics with time-lapse systems and in those with conventional incubators only, as just a single photo is required.

STUDY FUNDING/COMPETING INTERESTS

This study was supported by the Regional Ministry of Innovation, Universities, Science and Digital Society of the Valencian Community (CIACIF/2021/019) and by Instituto de Salud Carlos III (PI21/00283), and co-funded by European Union (ERDF, 'A way to make Europe'). M.M. received personal fees in the last 5 years as honoraria for lectures from Merck, Vitrolife, MSD, Ferring, AIVF, Theramex, Gedeon Richter, Genea Biomedx, and Life Whisperer. There are no other competing interests.

TRIAL REGISTRATION NUMBER

N/A.

Artificial intelligence system for outcome evaluations of human in vitro fertilization-derived embryos

BACKGROUND

In vitro fertilization (IVF) has emerged as a transformative solution for infertility. However, achieving favorable live-birth outcomes remains challenging. Current clinical IVF practices in IVF involve the collection of heterogeneous embryo data through diverse methods, including static images and temporal videos. However, traditional embryo selection methods, primarily reliant on visual inspection of morphology, exhibit variability and are contingent on the experience of practitioners. Therefore, an automated system that can evaluate heterogeneous embryo data to predict the final outcomes of live births is highly desirable.

METHODS

We employed artificial intelligence (AI) for embryo morphological grading, blastocyst embryo selection, aneuploidy prediction, and final live-birth outcome prediction. We developed and validated the AI models using multitask learning for embryo morphological assessment, including pronucleus type on day 1 and the number of blastomeres, asymmetry, and fragmentation of blastomeres on day 3, using 19,201 embryo photographs from 8271 patients. A neural network was trained on embryo and clinical metadata to identify good-quality embryos for implantation on day 3 or day 5, and predict live-birth outcomes. Additionally, a 3D convolutional neural network was trained on 418 time-lapse videos of preimplantation genetic testing (PGT)-based ploidy outcomes for the prediction of aneuploidy and consequent live-birth outcomes.

RESULTS

These two approaches enabled us to automatically assess the implantation potential. By combining embryo and maternal metrics in an ensemble AI model, we evaluated live-birth outcomes in a prospective cohort that achieved higher accuracy than experienced embryologists (46.1% vs. 30.7% on day 3, 55.0% vs. 40.7% on day 5). Our results demonstrate the potential for AI-based selection of embryos based on characteristics beyond the observational abilities of human clinicians (area under the curve: 0.769, 95% confidence interval: 0.709-0.820). These findings could potentially provide a noninvasive, high-throughput, and low-cost screening tool to facilitate embryo selection and achieve better outcomes.

CONCLUSIONS

Our study underscores the AI model's ability to provide interpretable evidence for clinicians in assisted reproduction, highlighting its potential as a noninvasive, efficient, and cost-effective tool for improved embryo selection and enhanced IVF outcomes. The convergence of cutting-edge technology and reproductive medicine has opened new avenues for addressing infertility challenges and optimizing IVF success rates.

Development of an AI-Assisted Embryo Selection System Using Iberian Ribbed Newts for Embryo-Fetal Development Toxicity Testing

Background

The 3Rs (Reduction, Refinement, Replacement) principle is driving the need for alternative methods in animal testing. Despite advancements in in vitro testing, complex systemic toxicity tests still necessitate in vivo approaches. The aim of this study was to develop a developmental toxicity test protocol using the Iberian ribbed newt (Pleurodeles waltl) as a model organism, integrating AI image analysis for embryo selection to improve test accuracy and reproducibility.

Methods

We established a developmental toxicity test protocol based on the zebrafish test. Gonadotropin was administered to induce ovulation, and in vitro fertilization was performed. Embryos were imaged at 5-6 and 6-7 h post-fertilization. AI image analysis was utilized to assess embryo viability. The test chemical was administered 24-48 h post-fertilization, and morphological changes were observed daily until day 8. Additionally, a time-lapse photography system was constructed to monitor embryonic development.

Results

Out of 24 cultured embryos, 75% developed normally to the late tail bud stage or initial hatching stage, whereas 25% experienced developmental arrest or death. AI image analysis achieved high accuracy in classifying embryos, with overall accuracies of 92.0% and 92.9% for two learning models. The AI system demonstrated higher precision in the selection of viable embryos compared to visual inspection.

Conclusion

The Iberian ribbed newt presents a viable alternative model for developmental toxicity testing, adhering to the 3Rs principles. The integration of AI image analysis substantially enhances the accuracy and reproducibility of embryo selection, providing a reliable method for evaluating developmental toxicity in pharmaceuticals.

Deep learning pipeline reveals key moments in human embryonic development predictive of live birth after in vitro fertilization

Demand for in vitro fertilization (IVF) treatment is growing; however, success rates remain low partly due to difficulty in selecting the best embryo to be transferred. Current manual assessments are subjective and may not take advantage of the most informative moments in embryo development. Here, we apply convolutional neural networks (CNNs) to identify key windows in pre-implantation human development that can be linked to embryo viability and are therefore suitable for the early grading of IVF embryos. We show how machine learning models trained at these developmental time points can be used to refine overall embryo viability assessment. Exploiting the well-known capabilities of transfer learning, we illustrate the performance of CNN models for very limited datasets, paving the way for the use on a clinic-by-clinic basis, catering for local data heterogeneity.

Conventional and modern markers of pregnancy of unknown location: Update and narrative review

Pregnancy of unknown location (PUL) is a temporary pathologic or physiologic phenomenon of early pregnancy that requires follow up to determine the final pregnancy outcome. Evidence indicated that PUL patients suffer a remarkably higher rate of adverse pregnancy outcomes, represented by ectopic gestation and early pregnancy loss, than the general population. In the past few decades, discussion about PUL has never stopped, and a variety of markers have been widely investigated for the early and accurate evaluation of PUL, including serum biomarkers, ultrasound imaging features, multivariate analysis, and the diagnosis of ectopic pregnancy based on risk stratification. So far, machine learning (ML) methods represented by M4 and M6 logistic regression have gained a level of recognition and are continually improving. Nevertheless, the heterogeneity of PUL markers, mainly caused by the limited sample size, the differences in population and technical maturity, etc., have hampered the management of PUL. With the advancement of multidisciplinary integration and cutting-edge technologies (e.g. artificial intelligence, prediction model development, and telemedicine), novel markers, and strategies for the management of PUL are expected to be developed. In this review, we summarize both conventional and novel markers (represented by artificial intelligence) for PUL assessment and management, investigate their advancements, limitations and challenges, and propose insights on future research direction and clinical application.

Artificial intelligence-powered assisted ranking of sibling embryos to increase first cycle pregnancy rate

RESEARCH QUESTION

Could EMBRYOLY, an artificial intelligence embryo evaluation tool, assist embryologists to increase first cycle pregnancy rate and reduce cycles to pregnancy for patients?

DESIGN

Data from 11,988 embryos were collected via EMBRYOLY from 2666 egg retrievals (2019-2022) across 11 centres in France, Spain and Morocco using three time-lapse systems (TLS). Data from two independent clinics were also examined. EMBRYOLY's transformer-based model was applied to transferred embryos to evaluate ranking performances against pregnancy and birth outcomes. It was applied to cohorts to rank sibling embryos (including non-transferred) according to their likelihood of clinical pregnancy and to compute the agreement with the embryologist's highest ranked embryo. Its effect on time to pregnancy and first cycle pregnancy rate was evaluated on cohorts with multiple single blastocyst transfers, assuming the embryologist would have considered EMBRYOLY's ranking on the embryos favoured for transfer.

RESULTS

EMBRYOLY's score correlated significantly with clinical pregnancies and live births for cleavage and blastocyst transfers. This held true for clinical pregnancies from blastocyst transfers in two independent clinics. In cases of multiple single embryo transfers, embryologists achieved a 19.8% first cycle pregnancy rate, which could have been improved to 44.1% with the adjunctive use of EMBRYOLY (McNemar's test: P < 0.001). This could have reduced cycles to clinical pregnancy from 2.01 to 1.66 (Wilcoxon test: P < 0.001).

CONCLUSIONS

EMBRYOLY's potential to enhance first cycle pregnancy rates when combined with embryologists' expertise is highlighted. It reduces the number of unsuccessful cycles for patients across TLS and IVF centres.

Leveraging federated learning for boosting data privacy and performance in IVF embryo selection

PURPOSE

To study the effectiveness of federated learning in in vitro fertilization on embryo evaluation tasks.

METHODS

This is a retrospective cohort analysis. Two datasets were used in this study. The ploidy status dataset consisted of 10,065 embryo records, 3760 treatments, and 2479 infertile couples from 5 hospitals. The clinical pregnancy dataset consisted of 4495 embryo records, 4495 treatments, and 3704 infertile couples from 4 hospitals. Federated learning and the gradient boosting decision tree algorithm were utilized for modeling.

RESULTS

On the ploidy status dataset, the areas under the receiver operating characteristic curves of our model trained with federated learning were 71.78%, 73.10%, 69.39%, 69.72%, and 73.46% for 5 hospitals respectively, showing an average increase of 2.5% compared to those of our model trained without federated learning. On the clinical pregnancy dataset, the areas under the receiver operating characteristic curves of our model trained with federated learning were 72.03%, 56.77%, 61.63%, and 58.58% for 4 hospitals respectively, showing an average increase of 3.08%.

CONCLUSIONS

Federated learning can improve data privacy and data security and meanwhile improve the performance of embryo selection tasks by leveraging data from multiple sources. This study demonstrates the effectiveness of federated learning in embryo evaluation, and the results show the promise for future application.

Machine learning in time-lapse imaging to differentiate embryos from young vs old mice†

Time-lapse microscopy for embryos is a non-invasive technology used to characterize early embryo development. This study employs time-lapse microscopy and machine learning to elucidate changes in embryonic growth kinetics with maternal aging. We analyzed morphokinetic parameters of embryos from young and aged C57BL6/NJ mice via continuous imaging. Our findings show that aged embryos accelerated through cleavage stages (from 5-cells) to morula compared to younger counterparts, with no significant differences observed in later stages of blastulation. Unsupervised machine learning identified two distinct clusters comprising of embryos from aged or young donors. Moreover, in supervised learning, the extreme gradient boosting algorithm successfully predicted the age-related phenotype with 0.78 accuracy, 0.81 precision, and 0.83 recall following hyperparameter tuning. These results highlight two main scientific insights: maternal aging affects embryonic development pace, and artificial intelligence can differentiate between embryos from aged and young maternal mice by a non-invasive approach. Thus, machine learning can be used to identify morphokinetics phenotypes for further studies. This study has potential for future applications in selecting human embryos for embryo transfer, without or in complement with preimplantation genetic testing.

Generative artificial intelligence to produce high-fidelity blastocyst-stage embryo images

STUDY QUESTION

Can generative artificial intelligence (AI) models produce high-fidelity images of human blastocysts?

SUMMARY ANSWER

Generative AI models exhibit the capability to generate high-fidelity human blastocyst images, thereby providing substantial training datasets crucial for the development of robust AI models.

WHAT IS KNOWN ALREADY

The integration of AI into IVF procedures holds the potential to enhance objectivity and automate embryo selection for transfer. However, the effectiveness of AI is limited by data scarcity and ethical concerns related to patient data privacy. Generative adversarial networks (GAN) have emerged as a promising approach to alleviate data limitations by generating synthetic data that closely approximate real images.

STUDY DESIGN, SIZE, DURATION

Blastocyst images were included as training data from a public dataset of time-lapse microscopy (TLM) videos (n = 136). A style-based GAN was fine-tuned as the generative model.

PARTICIPANTS/MATERIALS, SETTING, METHODS

We curated a total of 972 blastocyst images as training data, where frames were captured within the time window of 110-120 h post-insemination at 1-h intervals from TLM videos. We configured the style-based GAN model with data augmentation (AUG) and pretrained weights (Pretrained-T: with translation equivariance; Pretrained-R: with translation and rotation equivariance) to compare their optimization on image synthesis. We then applied quantitative metrics including Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) to assess the quality and fidelity of the generated images. Subsequently, we evaluated qualitative performance by measuring the intelligence behavior of the model through the visual Turing test. To this end, 60 individuals with diverse backgrounds and expertise in clinical embryology and IVF evaluated the quality of synthetic embryo images.

MAIN RESULTS AND THE ROLE OF CHANCE

During the training process, we observed consistent improvement of image quality that was measured by FID and KID scores. Pretrained and AUG + Pretrained initiated with remarkably lower FID and KID values compared to both Baseline and AUG + Baseline models. Following 5000 training iterations, the AUG + Pretrained-R model showed the highest performance of the evaluated five configurations with FID and KID scores of 15.2 and 0.004, respectively. Subsequently, we carried out the visual Turing test, such that IVF embryologists, IVF laboratory technicians, and non-experts evaluated the synthetic blastocyst-stage embryo images and obtained similar performance in specificity with marginal differences in accuracy and sensitivity.

LIMITATIONS, REASONS FOR CAUTION

In this study, we primarily focused the training data on blastocyst images as IVF embryos are primarily assessed in blastocyst stage. However, generation of an array of images in different preimplantation stages offers further insights into the development of preimplantation embryos and IVF success. In addition, we resized training images to a resolution of 256 × 256 pixels to moderate the computational costs of training the style-based GAN models. Further research is needed to involve a more extensive and diverse dataset from the formation of the zygote to the blastocyst stage, e.g. video generation, and the use of improved image resolution to facilitate the development of comprehensive AI algorithms and to produce higher-quality images.

WIDER IMPLICATIONS OF THE FINDINGS

Generative AI models hold promising potential in generating high-fidelity human blastocyst images, which allows the development of robust AI models as it can provide sufficient training datasets while safeguarding patient data privacy. Additionally, this may help to produce sufficient embryo imaging training data with different (rare) abnormal features, such as embryonic arrest, tripolar cell division to avoid class imbalances and reach to even datasets. Thus, generative models may offer a compelling opportunity to transform embryo selection procedures and substantially enhance IVF outcomes.

STUDY FUNDING/COMPETING INTEREST(S)

This study was supported by a Horizon 2020 innovation grant (ERIN, grant no. EU952516) and a Horizon Europe grant (NESTOR, grant no. 101120075) of the European Commission to A.S. and M.Z.E., the Estonian Research Council (grant no. PRG1076) to A.S., and the EVA (Erfelijkheid Voortplanting & Aanleg) specialty program (grant no. KP111513) of Maastricht University Medical Centre (MUMC+) to M.Z.E.

TRIAL REGISTRATION NUMBER

Not applicable.

Evaluation of the Clinical Efficacy and Trust in AI-Assisted Embryo Ranking: Survey-Based Prospective Study

BACKGROUND

Current embryo assessment methods for in vitro fertilization depend on subjective morphological assessments. Recently, artificial intelligence (AI) has emerged as a promising tool for embryo assessment; however, its clinical efficacy and trustworthiness remain unproven. Simulation studies may provide additional evidence, provided that they are meticulously designed to mitigate bias and variance.

OBJECTIVE

The primary objective of this study was to evaluate the benefits of an AI model for predicting clinical pregnancy through well-designed simulations. The secondary objective was to identify the characteristics of and potential bias in the subgroups of embryologists with varying degrees of experience.

METHODS

This simulation study involved a questionnaire-based survey conducted on 61 embryologists with varying levels of experience from 12 in vitro fertilization clinics. The survey was conducted via Google Forms (Google Inc) in three phases: (1) phase 1, an initial assessment (December 23, 2022, to January 22, 2023); (2) phase 2, a validation assessment (March 6, 2023, to April 5, 2023); and (3) phase 3 an AI-guided assessment (March 6, 2023, to April 5, 2023). Inter- and intraobserver assessments and the accuracy of embryo selection from 360 day-5 embryos before and after AI guidance were analyzed for all embryologists and subgroups of senior and junior embryologists.

RESULTS

With AI guidance, the interobserver agreement increased from 0.355 to 0.527 and from 0.440 to 0.524 for junior and senior embryologists, respectively, thus reaching similar levels of agreement. In a test of accurate embryo selection with 90 questions, the numbers of correct responses by the embryologists only, embryologists with AI guidance, and AI only were 34 (38%), 45 (50%), and 59 (66%), respectively. Without AI, the average score (accuracy) of the junior group was 33.516 (37%), while that of the senior group was 35.967 (40%), with P<.001 in the t test. With AI guidance, the average score (accuracy) of the junior group increased to 46.581 (52%), reaching a level similar to that of the senior embryologists of 44.833 (50%), with P=.34. Junior embryologists had a higher level of trust in the AI score.

CONCLUSIONS

This study demonstrates the potential benefits of AI in selecting embryos with high chances of pregnancy, particularly for embryologists with 5 years or less of experience, possibly due to their trust in AI. Thus, using AI as an auxiliary tool in clinical practice has the potential to improve embryo assessment and increase the probability of a successful pregnancy.

An artificial intelligence algorithm to select most viable embryos considering current process in IVF labs

Background

The most common Assisted Reproductive Technology is In-Vitro Fertilization (IVF). During IVF, embryologists commonly perform a morphological assessment to evaluate embryo quality and choose the best embryo for transferring to the uterus. However, embryo selection through morphological assessment is subjective, so various embryologists obtain different conclusions. Furthermore, humans can consider only a limited number of visual parameters resulting in a poor IVF success rate. Artificial intelligence (AI) for embryo selection is objective and can include many parameters, leading to better IVF outcomes.

Objectives

This study sought to use AI to (1) predict pregnancy results based on embryo images, (2) assess using more than one image of the embryo in the prediction of pregnancy but based on the current process in IVF labs, and (3) compare results of AI-Based methods and embryologist experts in predicting pregnancy.

Methods

A data set including 252 Time-lapse Videos of embryos related to IVF performed between 2017 and 2020 was collected. Frames related to 19 ± 1, 43 ± 1, and 67 ± 1 h post-insemination were extracted. Well-Known CNN architectures with transfer learning have been applied to these images. The results have been compared with an algorithm that only uses the final image of embryos. Furthermore, the results have been compared with five experienced embryologists.

Results

To predict the pregnancy outcome, we applied five well-known CNN architectures (AlexNet, ResNet18, ResNet34, Inception V3, and DenseNet121). DeepEmbryo, using three images, predicts pregnancy better than the algorithm that only uses one final image. It also can predict pregnancy better than all embryologists. Different well-known architectures can successfully predict pregnancy chances with up to 75.0% accuracy using Transfer Learning.

Conclusion

We have developed DeepEmbryo, an AI-based tool that uses three static images to predict pregnancy. Additionally, DeepEmbryo uses images that can be obtained in the current IVF process in almost all IVF labs. AI-based tools have great potential for predicting pregnancy and can be used as a proper tool in the future.

Dev-ResNet: automated developmental event detection using deep learning

Delineating developmental events is central to experimental research using early life stages, permitting widespread identification of changes in event timing between species and environments. Yet, identifying developmental events is incredibly challenging, limiting the scale, reproducibility and throughput of using early life stages in experimental biology. We introduce Dev-ResNet, a small and efficient 3D convolutional neural network capable of detecting developmental events characterised by both spatial and temporal features, such as the onset of cardiac function and radula activity. We demonstrate the efficacy of Dev-ResNet using 10 diverse functional events throughout the embryonic development of the great pond snail, Lymnaea stagnalis. Dev-ResNet was highly effective in detecting the onset of all events, including the identification of thermally induced decoupling of event timings. Dev-ResNet has broad applicability given the ubiquity of bioimaging in developmental biology, and the transferability of deep learning, and so we provide comprehensive scripts and documentation for applying Dev-ResNet to different biological systems.

Diagnostic or prognostic? Decoding the role of embryo selection on in vitro fertilization treatment outcomes

In this review, we take a fresh look at embryo assessment and selection methods from the perspective of diagnosis and prognosis. On the basis of a systematic search in the literature, we examined the evidence on the prognostic value of different embryo assessment methods, including morphological assessment, blastocyst culture, time-lapse imaging, artificial intelligence, and preimplantation genetic testing for aneuploidy.

A compact, high-throughput semi-automated embryo vitrification system based on hydrogel

RESEARCH QUESTION

What is the efficiency and efficacy of the novel Biorocks semi-automated vitrification system, which is based on a hydrogel?

DESIGN

This comparative experimental laboratory study used mouse model and human day 6 blastocysts. Mouse oocytes and embryos were quality assessed post-vitrification.

RESULTS

The Biorocks system successfully automated the solution exchanges during the vitrification process, achieving a significantly improved throughput of up to 36 embryos/oocytes per hour. Using hydrogel for cryoprotective agent delivery, 12 vessels could be processed simultaneously, fitting comfortably within an assisted reproductive technology (ART) workstation. In tests involving the cryopreservation of oocytes and embryos, the system yielded outcomes equivalent to the manual Cryotop method. For example, the survival rate for mouse oocytes was 98% with the Biorocks vitrification system (n = 46) and 95% for the manual Cryotop method (n = 39), of which 46% and 41%, respectively, progressed to blastocysts on day 5 after IVF. CC-grade day 6 human blastocysts processed with the Biorocks system (n = 39) were associated with a 92% 2 h re-expansion rate, equivalent to the 90% with Cryotop (n = 30). The cooling/warming rates achieved by the Biorocks system were 31,900°C/minute and 24,700°C/minute, respectively. Oocyte quality was comparable or better post-vitrification for Biorocks than Cryotop.

CONCLUSIONS

The Biorocks semi-automated vitrification system offers enhanced throughput without compromising the survival and developmental potential of oocytes and embryos. This innovative system may help to increase the efficiency and standardization of vitrification in ART clinics. Further investigations are needed to confirm its efficacy in a broader clinical context.

Evolution of Minimally Invasive and Non-Invasive Preimplantation Genetic Testing: An Overview

Preimplantation genetic testing (PGT) has become a common supplementary diagnοstic/testing tοol for in vitro fertilization (ΙVF) cycles due to a significant increase in cases of PGT fοr mοnogenic cοnditions (ΡGT-M) and de novο aneuplοidies (ΡGT-A) over the last ten years. This tendency is mostly attributable to the advancement and application of novel cytogenetic and molecular techniques in clinical practice that are capable of providing an efficient evaluation of the embryonic chromosomal complement and leading to better IVF/ICSI results. Although PGT is widely used, it requires invasive biopsy of the blastocyst, which may harm the embryo. Non-invasive approaches, like cell-free DNA (cfDNA) testing, have lower risks but have drawbacks in consistency and sensitivity. This review discusses new developments and opportunities in the field of preimplantation genetic testing, enhancing the overall effectiveness and accessibility of preimplantation testing in the framework of developments in genomic sequencing, bioinformatics, and the integration of artificial intelligence in the interpretation of genetic data.

BlastAssist: a deep learning pipeline to measure interpretable features of human embryos

STUDY QUESTION

Can the BlastAssist deep learning pipeline perform comparably to or outperform human experts and embryologists at measuring interpretable, clinically relevant features of human embryos in IVF?

SUMMARY ANSWER

The BlastAssist pipeline can measure a comprehensive set of interpretable features of human embryos and either outperform or perform comparably to embryologists and human experts in measuring these features.

WHAT IS KNOWN ALREADY

Some studies have applied deep learning and developed 'black-box' algorithms to predict embryo viability directly from microscope images and videos but these lack interpretability and generalizability. Other studies have developed deep learning networks to measure individual features of embryos but fail to conduct careful comparisons to embryologists' performance, which are fundamental to demonstrate the network's effectiveness.

STUDY DESIGN, SIZE, DURATION

We applied the BlastAssist pipeline to 67 043 973 images (32 939 embryos) recorded in the IVF lab from 2012 to 2017 in Tel Aviv Sourasky Medical Center. We first compared the pipeline measurements of individual images/embryos to manual measurements by human experts for sets of features, including: (i) fertilization status (n = 207 embryos), (ii) cell symmetry (n = 109 embryos), (iii) degree of fragmentation (n = 6664 images), and (iv) developmental timing (n = 21 036 images). We then conducted detailed comparisons between pipeline outputs and annotations made by embryologists during routine treatments for features, including: (i) fertilization status (n = 18 922 embryos), (ii) pronuclei (PN) fade time (n = 13 781 embryos), (iii) degree of fragmentation on Day 2 (n = 11 582 embryos), and (iv) time of blastulation (n = 3266 embryos). In addition, we compared the pipeline outputs to the implantation results of 723 single embryo transfer (SET) cycles, and to the live birth results of 3421 embryos transferred in 1801 cycles.

PARTICIPANTS/MATERIALS, SETTING, METHODS

In addition to EmbryoScope™ image data, manual embryo grading and annotations, and electronic health record (EHR) data on treatment outcomes were also included. We integrated the deep learning networks we developed for individual features to construct the BlastAssist pipeline. Pearson's χ2 test was used to evaluate the statistical independence of individual features and implantation success. Bayesian statistics was used to evaluate the association of the probability of an embryo resulting in live birth to BlastAssist inputs.

MAIN RESULTS AND THE ROLE OF CHANCE

The BlastAssist pipeline integrates five deep learning networks and measures comprehensive, interpretable, and quantitative features in clinical IVF. The pipeline performs similarly or better than manual measurements. For fertilization status, the network performs with very good parameters of specificity and sensitivity (area under the receiver operating characteristics (AUROC) 0.84-0.94). For symmetry score, the pipeline performs comparably to the human expert at both 2-cell (r = 0.71 ± 0.06) and 4-cell stages (r = 0.77 ± 0.07). For degree of fragmentation, the pipeline (acc = 69.4%) slightly under-performs compared to human experts (acc = 73.8%). For developmental timing, the pipeline (acc = 90.0%) performs similarly to human experts (acc = 91.4%). There is also strong agreement between pipeline outputs and annotations made by embryologists during routine treatments. For fertilization status, the pipeline and embryologists strongly agree (acc = 79.6%), and there is strong correlation between the two measurements (r = 0.683). For degree of fragmentation, the pipeline and embryologists mostly agree (acc = 55.4%), and there is also strong correlation between the two measurements (r = 0.648). For both PN fade time (r = 0.787) and time of blastulation (r = 0.887), there's strong correlation between the pipeline and embryologists. For SET cycles, 2-cell time (P < 0.01) and 2-cell symmetry (P < 0.03) are significantly correlated with implantation success rate, while other features showed correlations with implantation success without statistical significance. In addition, 2-cell time (P < 5 × 10-11), PN fade time (P < 5 × 10-10), degree of fragmentation on Day 3 (P < 5 × 10-4), and 2-cell symmetry (P < 5 × 10-3) showed statistically significant correlation with the probability of the transferred embryo resulting in live birth.

LIMITATIONS, REASONS FOR CAUTION

We have not tested the BlastAssist pipeline on data from other clinics or other time-lapse microscopy (TLM) systems. The association study we conducted with live birth results do not take into account confounding variables, which will be necessary to construct an embryo selection algorithm. Randomized controlled trials (RCT) will be necessary to determine whether the pipeline can improve success rates in clinical IVF.

WIDER IMPLICATIONS OF THE FINDINGS

BlastAssist provides a comprehensive and holistic means of evaluating human embryos. Instead of using a black-box algorithm, BlastAssist outputs meaningful measurements of embryos that can be interpreted and corroborated by embryologists, which is crucial in clinical decision making. Furthermore, the unprecedentedly large dataset generated by BlastAssist measurements can be used as a powerful resource for further research in human embryology and IVF.

STUDY FUNDING/COMPETING INTEREST(S)

This work was supported by Harvard Quantitative Biology Initiative, the NSF-Simons Center for Mathematical and Statistical Analysis of Biology at Harvard (award number 1764269), the National Institute of Heath (award number R01HD104969), the Perelson Fund, and the Sagol fund for embryos and stem cells as part of the Sagol Network. The authors declare no competing interests.

TRIAL REGISTRATION NUMBER

Not applicable.

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.

Knowledge-embedded spatio-temporal analysis for euploidy embryos identification in couples with chromosomal rearrangements

BACKGROUND

The goal of the assisted reproductive treatment is to transfer one euploid blastocyst and to help infertile women giving birth one healthy neonate. Some algorithms have been used to assess the ploidy status of embryos derived from couples with normal chromosome, who subjected to preimplantation genetic testing for aneuploidy (PGT-A) treatment. However, it is currently unknown whether artificial intelligence model can be used to assess the euploidy status of blastocyst derived from populations with chromosomal rearrangement.

METHODS

From February 2020 to May 2021, we collected the whole raw time-lapse videos at multiple focal planes from in vitro cultured embryos, the clinical information of couples, and the comprehensive chromosome screening results of those blastocysts that had received PGT treatment. Initially, we developed a novel deep learning model called the Attentive Multi-Focus Selection Network (AMSNet) to analyze time-lapse videos in real time and predict blastocyst formation. Building upon AMSNet, we integrated additional clinically predictive variables and created a second deep learning model, the Attentive Multi-Focus Video and Clinical Information Fusion Network (AMCFNet), to assess the euploidy status of embryos. The efficacy of the AMCFNet was further tested in embryos with parental chromosomal rearrangements. The receiver operating characteristic curve (ROC) was used to evaluate the superiority of the model.

RESULTS

A total of 4112 embryos with complete time-lapse videos were enrolled for the blastocyst formation prediction task, and 1422 qualified blastocysts received PGT-A ( n = 589) or PGT for chromosomal structural rearrangement (PGT-SR, n = 833) were enrolled for the euploidy assessment task in this study. The AMSNet model using seven focal raw time-lapse videos has the best real-time accuracy. The real-time accuracy for AMSNet to predict blastocyst formation reached above 70% on the day 2 of embryo culture, and then increased to 80% on the day 4 of embryo culture. Combing with 4 clinical features of couples, the AUC of AMCFNet with 7 focal points increased to 0.729 in blastocysts derived from couples with chromosomal rearrangement.

CONCLUSION

Integrating seven focal raw time-lapse images of embryos and parental clinical information, AMCFNet model have the capability of assessing euploidy status in blastocysts derived from couples with chromosomal rearrangement.

EVATOM: an optical, label-free, machine learning assisted embryo health assessment tool

The combination of a good quality embryo and proper maternal health factors promise higher chances of a successful in vitro fertilization (IVF) procedure leading to clinical pregnancy and live birth. Of these two factors, selection of a good embryo is a controllable aspect. The current gold standard in clinical practice is visual assessment of an embryo based on its morphological appearance by trained embryologists. More recently, machine learning has been incorporated into embryo selection "packages". Here, we report EVATOM: a machine-learning assisted embryo health assessment tool utilizing an optical quantitative phase imaging technique called artificial confocal microscopy (ACM). We present a label-free nucleus detection method with, to the best of our knowledge, novel quantitative embryo health biomarkers. Two viability assessment models are presented for grading embryos into two classes: healthy/intermediate (H/I) or sick (S) class. The models achieve a weighted F1 score of 1.0 and 0.99 respectively on the in-distribution test set of 72 fixed embryos and a weighted F1 score of 0.9 and 0.95 respectively on the out-of-distribution test dataset of 19 time-instances from 8 live embryos.

Seeking arrangements: cell contact as a cleavage-stage biomarker

RESEARCH QUESTION

What can three-dimensional cell contact networks tell us about the developmental potential of cleavage-stage human embryos?

DESIGN

This pilot study was a retrospective analysis of two Embryoscope imaging datasets from two clinics. An artificial intelligence system was used to reconstruct the three-dimensional structure of embryos from 11-plane focal stacks. Networks of cell contacts were extracted from the resulting embryo three-dimensional models and each embryo's mean contacts per cell was computed. Unpaired t-tests and receiver operating characteristic curve analysis were used to statistically analyse mean cell contact outcomes. Cell contact networks from different embryos were compared with identical embryos with similar cell arrangements.

RESULTS

At t4, a higher mean number of contacts per cell was associated with greater rates of blastulation and blastocyst quality. No associations were found with biochemical pregnancy, live birth, miscarriage or ploidy. At t8, a higher mean number of contacts was associated with increased blastocyst quality, biochemical pregnancy and live birth. No associations were found with miscarriage or aneuploidy. Mean contacts at t4 weakly correlated with those at t8. Four-cell embryos fell into nine distinct cell arrangements; the five most common accounted for 97% of embryos. Eight-cell embryos, however, displayed a greater degree of variation with 59 distinct cell arrangements.

CONCLUSIONS

Evidence is provided for the clinical relevance of cleavage-stage cell arrangement in the human preimplantation embryo beyond the four-cell stage, which may improve selection techniques for day-3 transfers. This pilot study provides a strong case for further investigation into spatial biomarkers and three-dimensional morphokinetics.

A clinical consensus-compliant deep learning approach to quantitatively evaluate human in vitro fertilization early embryonic development with optical microscope images

The selection of embryos is a key for the success of in vitro fertilization (IVF). However, automatic quality assessment on human IVF embryos with optical microscope images is still challenging. In this study, we developed a clinical consensus-compliant deep learning approach, named Esava (Embryo Segmentation and Viability Assessment), to quantitatively evaluate the development of IVF embryos using optical microscope images. In total 551 optical microscope images of human IVF embryos of day-2 to day-3 were collected, preprocessed, and annotated. Using the Faster R-CNN model as baseline, our Esava model was constructed, refined, trained, and validated for precise and robust blastomere detection. A novel algorithm Crowd-NMS was proposed and employed in Esava to enhance the object detection and to precisely quantify the embryonic cells and their size uniformity. Additionally, an innovative GrabCut-based unsupervised module was integrated for the segmentation of blastomeres and embryos. Independently tested on 94 embryo images for blastomere detection, Esava obtained the high rates of 0.9940, 0.9121, and 0.9531 for precision, recall, and mAP respectively, and gained significant advances compared with previous computational methods. Intraclass correlation coefficients indicated the consistency between Esava and three experienced embryologists. Another test on 51 extra images demonstrated that Esava surpassed other tools significantly, achieving the highest average precision 0.9025. Moreover, it also accurately identified the borders of blastomeres with mIoU over 0.88 on the independent testing dataset. Esava is compliant with the Istanbul clinical consensus and compatible to senior embryologists. Taken together, Esava improves the accuracy and efficiency of embryonic development assessment with optical microscope images.

Metabolic imaging of human embryos is predictive of ploidy status but is not associated with clinical pregnancy outcomes: a pilot trial

STUDY QUESTION

Does fluorescence lifetime imaging microscopy (FLIM)-based metabolic imaging assessment of human blastocysts prior to frozen transfer correlate with pregnancy outcomes?

SUMMARY ANSWER

FLIM failed to distinguish consistent patterns in mitochondrial metabolism between blastocysts leading to pregnancy compared to those that did not.

WHAT IS KNOWN ALREADY

FLIM measurements provide quantitative information on NAD(P)H and flavin adenine dinucleotide (FAD+) concentrations. The metabolism of embryos has long been linked to their viability, suggesting the potential utility of metabolic measurements to aid in selection.

STUDY DESIGN, SIZE, DURATION

This was a pilot trial enrolling 121 IVF couples who consented to have their frozen blastocyst measured using non-invasive metabolic imaging. After being warmed, 105 couples' good-quality blastocysts underwent a 6-min scan in a controlled temperature and gas environment. FLIM-assessed blastocysts were then transferred without any intervention in management.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Eight metabolic parameters were obtained from each blastocyst (4 for NAD(P)H and 4 for FAD): short and long fluorescence lifetime, fluorescence intensity, and fraction of the molecule engaged with enzyme. The redox ratio (intensity of NAD(P)H)/(intensity of FAD) was also calculated. FLIM data were combined with known metadata and analyzed to quantify the ability of metabolic imaging to differentiate embryos that resulted in pregnancy from embryos that did not. De-identified discarded aneuploid human embryos (n = 158) were also measured to quantify correlations with ploidy status and other factors. Statistical comparisons were performed using logistic regression and receiver operating characteristic (ROC) curves with 5-fold cross-validation averaged over 100 repeats with random sampling. AUC values were used to quantify the ability to distinguish between classes.

MAIN RESULTS AND THE ROLE OF CHANCE

No metabolic imaging parameters showed significant differences between good-quality blastocysts resulting in pregnancy versus those that did not. A logistic regression using metabolic data and metadata produced an ROC AUC of 0.58. In contrast, robust AUCs were obtained when classifying other factors such as comparison of Day 5 (n = 64) versus Day 6 (n = 41) blastocysts (AUC = 0.78), inner cell mass versus trophectoderm (n = 105: AUC = 0.88) and aneuploid (n = 158) versus euploid and positive pregnancy embryos (n = 108) (AUC = 0.82).

LIMITATIONS, REASONS FOR CAUTION

The study protocol did not select which embryo to transfer and the cohort of 105 included blastocysts were all high quality. The study was also limited in number of participants and study sites. Increased power and performing the trial in more sites may have provided a stronger conclusion regarding the merits of the use of FLIM clinically.

WIDER IMPLICATIONS OF THE FINDINGS

FLIM failed to distinguish consistent patterns in mitochondrial metabolism between good-quality blastocysts leading to pregnancy compared to those that did not. Blastocyst ploidy status was, however, highly distinguishable. In addition, embryo regions and embryo day were consistently revealed by FLIM. While metabolic imaging detects mitochondrial metabolic features in human blastocysts, this pilot trial indicates it does not have the potential to serve as an effective embryo viability detection tool. This may be because mitochondrial metabolism plays an alternative role post-implantation.

STUDY FUNDING/COMPETING INTEREST(S)

This study was sponsored by Optiva Fertility, Inc. Boston IVF contributed to the clinical site and services. Becker Hickl, GmbH, provided the FLIM system on loan. T.S. was the founder and held stock in Optiva Fertility, Inc., and D.S. and E.S. had options with Optiva Fertility, Inc., during this study.

TRIAL REGISTRATION NUMBER

The study was approved by WCG Connexus IRB (Study Number 1298156).

When the Embryo Meets the Endometrium: Identifying the Features Required for Successful Embryo Implantation

Evaluation of the optimal number of embryos, their quality, and the precise timing for transfer are critical determinants in reproductive success, although still remaining one of the main challenges in assisted reproduction technologies (ART). Indeed, the success of in vitro fertilization (IVF) treatments relies on a multitude of events and factors involving both the endometrium and the embryo. Despite concerted efforts on both fronts, the overall success rates of IVF techniques continue to range between 25% and 30%. The role of the endometrium in implantation has been recently recognized, leading to the hypothesis that both the "soil" and the "seed" play a central role in a successful pregnancy. In this respect, identification of the molecular signature of endometrial receptivity together with the selection of the best embryo for transfer become crucial in ART. Currently, efforts have been made to develop accurate, predictive, and personalized tests to identify the window of implantation and the best quality embryo. However, the value of these tests is still debated, as conflicting results are reported in the literature. The purpose of this review is to summarize and critically report the available criteria to optimize the success of embryo transfer and to better understand current limitations and potential areas for improvement.

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

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

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.

Associations between the artificial intelligence scoring system and live birth outcomes in preimplantation genetic testing for aneuploidy cycles

BACKGROUND

Several studies have demonstrated that iDAScore is more accurate in predicting pregnancy outcomes in cycles without preimplantation genetic testing for aneuploidy (PGT-A) compared to KIDScore and the Gardner criteria. However, the effectiveness of iDAScore in cycles with PGT-A has not been thoroughly investigated. Therefore, this study aims to assess the association between artificial intelligence (AI)-based iDAScore (version 1.0) and pregnancy outcomes in single-embryo transfer (SET) cycles with PGT-A.

METHODS

This retrospective study was approved by the Institutional Review Board of Chung Sun Medical University, Taichung, Taiwan. Patients undergoing SET cycles (n = 482) following PGT-A at a single reproductive center between January 2017 and June 2021. The blastocyst morphology and morphokinetics of all embryos were evaluated using a time-lapse system. The blastocysts were ranked based on the scores generated by iDAScore, which were defined as AI scores, or by KIDScore D5 (version 3.2) following the manufacturer's protocols. A single blastocyst without aneuploidy was transferred after examining the embryonic ploidy status using a next-generation sequencing-based PGT-A platform. Logistic regression analysis with generalized estimating equations was conducted to assess whether AI scores are associated with the probability of live birth (LB) while considering confounding factors.

RESULTS

Logistic regression analysis revealed that AI score was significantly associated with LB probability (adjusted odds ratio [OR] = 2.037, 95% confidence interval [CI]: 1.632-2.542) when pulsatility index (PI) level and types of chromosomal abnormalities were controlled. Blastocysts were divided into quartiles in accordance with their AI score (group 1: 3.0-7.8; group 2: 7.9-8.6; group 3: 8.7-8.9; and group 4: 9.0-9.5). Group 1 had a lower LB rate (34.6% vs. 59.8-72.3%) and a higher rate of pregnancy loss (26% vs. 4.7-8.9%) compared with the other groups (p < 0.05). The receiver operating characteristic curve analysis verified that the iDAScore had a significant but limited ability to predict LB (area under the curve [AUC] = 0.64); this ability was significantly weaker than that of the combination of iDAScore, type of chromosomal abnormalities, and PI level (AUC = 0.67). In the comparison of the LB groups with the non-LB groups, the AI scores were significantly lower in the non-LB groups, both for euploid (median: 8.6 vs. 8.8) and mosaic (median: 8.0 vs. 8.6) SETs.

CONCLUSIONS

Although its predictive ability can be further enhanced, the AI score was significantly associated with LB probability in SET cycles. Euploid or mosaic blastocysts with low AI scores (≤ 7.8) were associated with a lower LB rate, indicating the potential of this annotation-free AI system as a decision-support tool for deselecting embryos with poor pregnancy outcomes following PGT-A.

Development of an AI-based support system for controlled ovarian stimulation

Purpose

Controlled ovarian stimulation (COS) is vital for IVF. We have developed an AI system to support the implementation of COS protocols in our clinical group.

Methods

We developed two models as AI algorithms of the AI system. One was the oocyte retrieval decision model, to determine the timing of oocyte retrieval, and the other was the prescription inference model, to provide a prescription similar to that of an expert physician. Data was obtained from IVF treatment records from the In Vitro Fertilization (IVF) management system at the Asada Ladies Clinic, and these models were trained with this data.

Results

The oocyte retrieval decision model achieved superior sensitivity and specificity with 0.964 area under the curve (AUC). The prescription inference model achieved an AUC value of 0.948. Four models, namely the hCG prediction model, the hMG prediction model, the Cetrorelix prediction model, and the Estradiol prediction model included in the prescription inference model, achieved AUC values of 0.914, 0.937, 0.966, and 0.976, respectively.

Conclusion

The AI algorithm achieved high accuracy and was confirmed to be useful. The AI system has now been implemented as a COS tool in our clinical group for self-funded treatments.

Interpretable artificial intelligence-assisted embryo selection improved single-blastocyst transfer outcomes: a prospective cohort study

RESEARCH QUESTION

What is the pregnancy and neonatal outcomes of an interpretable artificial intelligence (AI) model for embryo selection in a prospective clinical trial?

DESIGN

This single-centre prospective cohort study was carried out from October 2021 to March 2022. A total of 330 eligible patients were assigned to their preferred groups, with 250 patients undergoing a fresh single-blastocyst transfer cycle after the exclusion criteria had been applied. For the AI-assisted group (AAG), embryologists selected the embryos for transfer based on the ranking recommendations provided by an interpretable AI system, while with the manual group, embryologists used the Gardner grading system to make their decisions.

RESULTS

The implantation rate was significantly higher in the AAG than the manual group (80.87% versus 68.15%, P = 0.022). No significant difference was found in terms of monozygotic twin rate, miscarriage rate, live birth rate and ectopic pregnancy rate between the groups. Furthermore, there was no significant difference in terms of neonatal outcomes, including gestational weeks, premature birth rate, birth height, birthweight, sex ratio at birth and newborn malformation rate. The consensus rate between the AI and retrospective analysis by the embryologists was significantly higher for good-quality embryos (i.e. grade 4BB or higher) versus poor-quality embryos (i.e. less than 4BB) (84.71% versus 25%, P < 0.001).

CONCLUSIONS

These prospective trial results suggest that the proposed AI system could effectively help embryologists to improve the implantation rate with single-blastocyst transfer compared with traditional manual evaluation methods.

Simultaneous transfer of one good-quality and one poor-quality cleavage stage embryo does not improve pregnancy outcomes

Embryo quality and quantity are key factors that determine the success of IVF-ET. Yet it is still unclear if, for those patients with only one good-quality embryo in an IVF cycle, the inclusion of a poor-quality embryo increases the procedure's success rate. This is a common question for both clinicians and patients in determining their course of treatment. The purpose of this work was to answer this intriguing question in the context of prognosis of patients undergoing fresh cycles with only one good-quality and more than one poor-quality cleavage-stage embryos. To control for confounding effects, we only included patients at similar age, body mass index (BMI), level of basal follicle stimulating hormone (FSH) and endometrial thickness from January 2015 to June 2021. A propensity score-matched analysis was performed to extract the matched pairs. Then we evaluated pregnancy outcome, including the rate of clinical pregnancy, live birth, embryo implantation, early miscarriage, and ectopic pregnancy. We found that the clinical pregnancy rate (34.8 vs. 38.0%, p = 0.553), live birth rate (27.1 vs. 29.9%, p = 0.598), early miscarriage rate (18.1 vs. 9.5%, p = 0.171) and ectopic pregnancy rate (1.3 vs. 1.2%, p = 1.000) did not significantly differ between those two groups, notwithstanding significant difference of the implantation rate (34.8 vs. 21.3%, p <0.001). Our work indicates that, for prognosis patients at approximately 34 years old with only one good-quality embryo, having additional poor-quality embryos does not seem to help to improve ART success rates per intended embryo transfer. In conclusion, we found that simultaneous transfer of one good-quality and one poor-quality cleavage stage embryo does not improve pregnancy outcomes.

Identifying predictors of Day 5 blastocyst utilization rate using an artificial neural network

RESEARCH QUESTION

Can artificial intelligence identify predictors of an increased Day 5 blastocyst utilization rate (D5BUR), which is one of the most informative key performance indicators in an IVF laboratory?

DESIGN

This retrospective, multicentre study evaluated six variables for predicting D5BUR using an artificial neural network (ANN): number of metaphase II (MII) oocytes injected (intracytoplasmic sperm injection); use of autologous/donated gametes; maternal age at oocyte retrieval; sperm concentration; progressive sperm motility rate; and fertilization rate. Cycles were divided into training and testing sets through stratified random sampling. D5BUR on Day 5 was grouped into <60% and ≥60% as per the Vienna consensus benchmark values.

RESULTS

The area under the receiver operating characteristic curve (AUC) to predict the D5BUR groups was 80.2%. From the ANN model, all six independent variables were found to be of significant value for the prediction of D5BUR (P<0.0001), with the most important variable being the number of MII oocytes injected. Investigation of the effect of MII oocytes injected on D5BUR indicated an inverse correlation, with injection of an increasing number of MII oocytes resulting in a decreasing D5BUR (r=-0.344, P<0.001) and injection of up to six oocytes resulting in D5BUR ≥60%.

CONCLUSION

The number of MII oocytes injected is the most important predictor of D5BUR. Exploration of additional variables and further validation of models that can predict D5BUR can guide the way towards personalized treatment and increased safety.

Application of artificial neural networks in reproductive medicine

With the emergence of the age of information, the data on reproductive medicine has improved immensely. Nonetheless, healthcare workers who wish to utilise the relevance and implied value of the various data available to aid clinical decision-making encounter the difficulty of statistically analysing such large data. The application of artificial intelligence becoming widespread in recent years has emerged as a turning point in this regard. Artificial neural networks (ANNs) exhibit beneficial characteristics of comprehensive analysis and autonomous learning, owing to which these are being applied to disease diagnosis, embryo quality assessment, and prediction of pregnancy outcomes. The present report aims to summarise the application of ANNs in the field of reproduction and analyse its further application potential.

Integrating imaging-based classification and transcriptomics for quality assessment of human oocytes according to their reproductive efficiency

PURPOSE

Utilising non-invasive imaging parameters to assess human oocyte fertilisation, development and implantation; and their influence on transcriptomic profiles.

METHODS

A ranking tool was designed using imaging data from 957 metaphase II stage oocytes retrieved from 102 patients undergoing ART. Hoffman modulation contrast microscopy was conducted with an Olympus IX53 microscope. Images were acquired prior to ICSI and processed using ImageJ for optical density and grey-level co-occurrence matrices texture analysis. Single-cell RNA sequencing of twenty-three mature oocytes classified according to their competence was performed.

RESULT(S)

Overall fertilisation, blastulation and implantation rates were 73.0%, 62.6% and 50.8%, respectively. Three different algorithms were produced using binary logistic regression methods based on "optimal" quartiles, resulting in an accuracy of prediction of 76.6%, 67% and 80.7% for fertilisation, blastulation and implantation. Optical density, gradient, inverse difference moment (homogeneity) and entropy (structural complexity) were the parameters with highest predictive properties. The ranking tool showed high sensitivity (68.9-90.8%) but with limited specificity (26.5-62.5%) for outcome prediction. Furthermore, five differentially expressed genes were identified when comparing "good" versus "poor" competent oocytes.

CONCLUSION(S)

Imaging properties can be used as a tool to assess differences in the ooplasm and predict laboratory and clinical outcomes. Transcriptomic analysis suggested that oocytes with lower competence may have compromised cell cycle either by non-reparable DNA damage or insufficient ooplasmic maturation. Further development of algorithms based on image parameters is encouraged, with an increased balanced cohort and validated prospectively in multicentric studies.

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.

Predicting the number of oocytes retrieved from controlled ovarian hyperstimulation with machine learning

STUDY QUESTION

Can machine learning predict the number of oocytes retrieved from controlled ovarian hyperstimulation (COH)?

SUMMARY ANSWER

Three machine-learning models were successfully trained to predict the number of oocytes retrieved from COH.

WHAT IS KNOWN ALREADY

A number of previous studies have identified and built predictive models on factors that influence the number of oocytes retrieved during COH. Many of these studies are, however, limited in the fact that they only consider a small number of variables in isolation.

STUDY DESIGN, SIZE, DURATION

This study was a retrospective analysis of a dataset of 11,286 cycles performed at a single centre in France between 2009 and 2020 with the aim of building a predictive model for the number of oocytes retrieved from ovarian stimulation. The analysis was carried out by a data analysis team external to the centre using the Substra framework. The Substra framework enabled the data analysis team to send computer code to run securely on the centre's on-premises server. In this way, a high level of data security was achieved as the data analysis team did not have direct access to the data, nor did the data leave the centre at any point during the study.

PARTICIPANTS/MATERIALS, SETTING, METHODS

The Light Gradient Boosting Machine algorithm was used to produce three predictive models: one that directly predicted the number of oocytes retrieved and two that predicted which of a set of bins provided by two clinicians the number of oocytes retrieved fell into. The resulting models were evaluated on a held-out test set and compared to linear and logistic regression baselines. In addition, the models themselves were analysed to identify the parameters that had the biggest impact on their predictions.

MAIN RESULTS AND THE ROLE OF CHANCE

On average, the model that directly predicted the number of oocytes retrieved deviated from the ground truth by 4.21 oocytes. The model that predicted the first clinician's bins deviated by 0.73 bins whereas the model for the second clinician deviated by 0.62 bins. For all models, performance was best within the first and third quartiles of the target variable, with the model underpredicting extreme values of the target variable (no oocytes and large numbers of oocytes retrieved). Nevertheless, the erroneous predictions made for these extreme cases were still within the vicinity of the true value. Overall, all three models agreed on the importance of each feature which was estimated using Shapley Additive Explanation (SHAP) values. The feature with the highest mean absolute SHAP value (and thus the highest importance) was the antral follicle count, followed by basal AMH and FSH. Of the other hormonal features, basal TSH, LH, and testosterone levels were similarly important and baseline LH was the least important. The treatment characteristic with the highest SHAP value was the initial dose of gonadotropins.

LIMITATIONS, REASONS FOR CAUTION

The models produced in this study were trained on a cohort from a single centre. They should thus not be used in clinical practice until trained and evaluated on a larger cohort more representative of the general population.

WIDER IMPLICATIONS OF FINDINGS

These predictive models for the number of oocytes retrieved from COH may be useful in clinical practice, assisting clinicians in optimizing COH protocols for individual patients. Our work also demonstrates the promise of using the Substra framework for allowing external researchers to provide clinically relevant insights on sensitive fertility data in a fully secure, trustworthy manner and opens a number of exciting avenues for accelerating future research.

STUDY FUNDING/COMPETING INTEREST(S)

This study was funded by the French Public Bank of Investment as part of the Healthchain Consortium. T.Fe., C.He., J.C., C.J., C.-A.P., and C.Hi. are employed by Apricity. C.Hi. has received consulting fees and honoraria from Vitrolife, Merck Serono, Ferring, Cooper Surgical, Dibimed, Apricity, and Fairtility and travel support from Fairtility and Vitrolife, participates on an advisory board for Merck Serono, was the founder and organizer of the AI Fertility conference, has stock in Aria Fertility, TMRW, Fairtility, Apricity, and IVF Professionals, and received free equipment from Planar in exchange for first user feedback. C.J. has received a grant from BPI. J.C. has also received a grant from BPI, is a member of the Merck AI advisory board, and is a board member of Labelia Labs. C.He has a contract for medical writing of this manuscript by CHU Nantes and has received travel support from Apricity. A.R. haș received honoraria from Ferring and Organon. T.Fe. has received a grant from BPI.

TRIAL REGISTRATION NUMBER

N/A.

Discard or not discard, that is the question: an international survey across 117 embryologists on the clinical management of borderline quality blastocysts

STUDY QUESTION

Do embryologists from different European countries agree on embryo disposition decisions ('use' or 'discard') about Day 7 (>144 h post-insemination) and/or low-quality blastocysts (LQB;

SUMMARY ANSWER

The prevalence of 'discard' answers was 38.7%; nevertheless, embryologists' agreement was overall just fair (Fleiss-k = 0.26).

WHAT IS KNOWN ALREADY

The utilization of LQBs and adoption of culture beyond 144 h post-insemination is increasing worldwide. Although morphology and morphokinetics are associated with embryo developmental competence, previous studies demonstrated significant interobserver variability among embryologists regarding embryo quality assessment and disposition decisions for borderline quality blastocysts.

STUDY DESIGN, SIZE, DURATION

An anonymous survey was run in a large network of IVF centers. A total of 117 embryologists from 6 European countries and 29 IVF centers filled in the survey. Randomly selected anonymous time-lapse videos of 50 Day 7 and/or LQB whole embryo preimplantation development were assessed by the embryologists. The key information on patients/cycles was provided along with each video. All cycles entailed preimplantation genetic testing for aneuploidies. Each embryologist specified whether he/she would have discarded or used ('transfer-fresh'/'cryopreserve'/'biopsy') any embryo. Inter-rater agreement was measured with Fleiss-k.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Examiners were asked about their years of experience, center location, average number of cycles and average maternal age, number of colleagues, and use of time-lapse incubators at their centers. All participants were blinded to artificial intelligence (AI) scores generated by two commercially available software packages, chromosomal diagnosis (all blastocysts were tested for aneuploidies), and clinical outcomes after vitrified-warmed euploid single blastocyst transfer. These data were known only by one embryologist not involved in the survey.

MAIN RESULTS AND THE ROLE OF CHANCE

Participants were Italian (40%, N = 47), Spanish (24%, N = 28), Portuguese (5%, N = 6), Czech (5%, N = 6), Swedish (23%, N = 27), and Icelandic (3%, N = 3). In total, 2263 (38.7%) 'discard' and 3587 (61.3%) 'use' decisions were recorded. Czech, Portuguese, and Italian embryologists expressed lower 'discard' decision rates (mean ± SD 17 ± 7%, range 8-24%; 23 ± 14% range 4-46%; and 27 ± 18% range 2-72%, respectively), while Spanish gave intermediate (37 ± 16% range 4-66%) and Nordic gave higher (67 ± 11% range 40-90%) rates. The prevalence of 'discard' answers was 38.7% out of 5850 choices (mean per embryologist: 39 ± 23% range 2-90%). Only embryologists' country and IVF group were associated with this rate. Overall agreement among embryologists was fair (Fleiss-k = 0.26). The prevalence of 'discard' responses per embryo was 37 ± 24% (range 2-87%). Only the number of sibling blastocysts influenced this rate (i.e. the larger the cohort, the higher the inclination to 'discard'). No difference was shown for the two scores between euploid and aneuploid borderline quality blastocysts, while the embryologists were, by chance, more prone to 'discard' the latter (28.3 ± 21% range 9-71% versus 41.6 ± 24.8% range 2-87%, respectively).

LIMITATIONS, REASONS FOR CAUTION

The survey included only private IVF clinics located in Europe. Moreover, a key variable is missing, namely patients' access to care. Indeed, all embryologists involved in the survey were part of the same network of private IVF clinics, while the embryo disposition decisions might be different in a public setting.

WIDER IMPLICATIONS OF THE FINDINGS

Decision-making by European embryologists regarding Day 7 embryos or LQBs is inconsistent with putative clinical consequences, especially in patients with low prognosis. Although the embryologists could make decisions independent from their local regulations, their mindset and clinical background influenced their choices. In the future, AI tools should be trained to assess borderline quality embryos and empowered with cost-effectiveness information to support embryologists' decisions with more objective assessments.

STUDY FUNDING/COMPETING INTEREST(S)

No external funding was obtained for this study. The authors have no conflict of interest to declare.

TRIAL REGISTRATION NUMBER

N/A.

Collapse

Key Words

• Day 7 blastocysts
• artificial intelligence
• decision-making
• embryo competence
• low-quality blastocysts

Collapse

MESH Headings

• Female
• Humans
• Aneuploidy
• Artificial Intelligence
• Blastocyst/physiology
• Embryo Transfer/methods
• Maternal Age
• Retrospective Studies
• Male

Collapse

Grants Collapse

Affiliation(s)

Viviana Chiappetta IVIRMA Global Research Alliance, GENERA, Clinica Valle Giulia, Rome, Italy
Federica Innocenti IVIRMA Global Research Alliance, GENERA, Clinica Valle Giulia, Rome, Italy
Giovanni Coticchio IVIRMA Global Research Alliance, 9.baby, Bologna, Italy
Aisling Ahlström IVIRMA Global Research Alliance, LIVIO, Göteborg, Sweden
Laura Albricci IVIRMA Global Research Alliance, GENERA, Clinica Valle Giulia, Rome, Italy
Vicente Badajoz IVIRMA Global Research Alliance, GINEFIV, Madrid, Spain
Maria Hebles IVIRMA Global Research Alliance, GINEMED, Sevilla, Spain
Miguel Gallardo IVIRMA Global Research Alliance, GINEMED, Lisbon, Portugal
Francesca Benini IVIRMA Global Research Alliance, DEMETRA, Florence, Italy
Stefano Canosa IVIRMA Global Research Alliance, LIVET, Turin, Italy
Jiří Kumpošt IVIRMA Global Research Alliance, FERTICARE, Prague, Czech Republic
Katarina Milton IVIRMA Global Research Alliance, CARL VON LINNÈ KLINIKEN, Uppsala, Sweden
Diletta Montanino Oliva Department of Biology and Biotechnology "Lazzaro Spallanzani", University of Pavia, Pavia, Italy
Roberta Maggiulli IVIRMA Global Research Alliance, GENERA, Clinica Valle Giulia, Rome, Italy
Laura Rienzi IVIRMA Global Research Alliance, GENERA, Clinica Valle Giulia, Rome, Italy Department of Biomolecular Sciences, University of Urbino "Carlo Bo", Urbino, Italy
Danilo Cimadomo IVIRMA Global Research Alliance, GENERA, Clinica Valle Giulia, Rome, Italy

Collapse

Application of artificial intelligence in gametes and embryos selection

Gamete and embryo quality are critical to the success rate of Assisted Reproductive Technology (ART) cycles, but there remains a lack of methods to accurately measure the quality of sperm, oocytes and embryos. The ability of Artificial Intelligence (AI) technology to analyze large amounts of data, especially video and images, is particularly useful in gamete and embryo assessment and selection. The well-trained model has fast calculation speed and high accuracy, which can help embryologists to perform more objective gamete and embryo selection. Various artificial intelligence models have been developed for gamete and embryo assessment, some of which exhibit good performance. In this review, we summarize the latest applications of AI technology in semen analysis, as well as selection for sperm, oocyte and embryo, and discuss the existing problems and development directions of artificial intelligence in this field.

Opening the black box: why do euploid blastocysts fail to implant? A systematic review and meta-analysis

BACKGROUND

A normal chromosomal constitution defined through PGT-A assessing all chromosomes on trophectoderm (TE) biopsies represents the strongest predictor of embryo implantation. Yet, its positive predictive value is not higher than 50-60%. This gap of knowledge on the causes of euploid blastocysts' reproductive failure is known as 'the black box of implantation'.

OBJECTIVE AND RATIONALE

Several embryonic, maternal, paternal, clinical, and IVF laboratory features were scrutinized for their putative association with reproductive success or implantation failure of euploid blastocysts.

SEARCH METHODS

A systematic bibliographical search was conducted without temporal limits up to August 2021. The keywords were '(blastocyst OR day5 embryo OR day6 embryo OR day7 embryo) AND (euploid OR chromosomally normal OR preimplantation genetic testing) AND (implantation OR implantation failure OR miscarriage OR abortion OR live birth OR biochemical pregnancy OR recurrent implantation failure)'. Overall, 1608 items were identified and screened. We included all prospective or retrospective clinical studies and randomized-controlled-trials (RCTs) that assessed any feature associated with live-birth rates (LBR) and/or miscarriage rates (MR) among non-mosaic euploid blastocyst transfer after TE biopsy and PGT-A. In total, 41 reviews and 372 papers were selected, clustered according to a common focus, and thoroughly reviewed. The PRISMA guideline was followed, the PICO model was adopted, and ROBINS-I and ROB 2.0 scoring were used to assess putative bias. Bias across studies regarding the LBR was also assessed using visual inspection of funnel plots and the trim and fill method. Categorical data were combined with a pooled-OR. The random-effect model was used to conduct the meta-analysis. Between-study heterogeneity was addressed using I2. Whenever not suitable for the meta-analysis, the included studies were simply described for their results. The study protocol was registered at http://www.crd.york.ac.uk/PROSPERO/ (registration number CRD42021275329).

OUTCOMES

We included 372 original papers (335 retrospective studies, 30 prospective studies and 7 RCTs) and 41 reviews. However, most of the studies were retrospective, or characterized by small sample sizes, thus prone to bias, which reduces the quality of the evidence to low or very low. Reduced inner cell mass (7 studies, OR: 0.37, 95% CI: 0.27-0.52, I2 = 53%), or TE quality (9 studies, OR: 0.53, 95% CI: 0.43-0.67, I2 = 70%), overall blastocyst quality worse than Gardner's BB-grade (8 studies, OR: 0.40, 95% CI: 0.24-0.67, I2 = 83%), developmental delay (18 studies, OR: 0.56, 95% CI: 0.49-0.63, I2 = 47%), and (by qualitative analysis) some morphodynamic abnormalities pinpointed through time-lapse microscopy (abnormal cleavage patterns, spontaneous blastocyst collapse, longer time of morula formation I, time of blastulation (tB), and duration of blastulation) were all associated with poorer reproductive outcomes. Slightly lower LBR, even in the context of PGT-A, was reported among women ≥38 years (7 studies, OR: 0.87, 95% CI: 0.75-1.00, I2 = 31%), while obesity was associated with both lower LBR (2 studies, OR: 0.66, 95% CI: 0.55-0.79, I2 = 0%) and higher MR (2 studies, OR: 1.8, 95% CI: 1.08-2.99, I2 = 52%). The experience of previous repeated implantation failures (RIF) was also associated with lower LBR (3 studies, OR: 0.72, 95% CI: 0.55-0.93, I2 = 0%). By qualitative analysis, among hormonal assessments, only abnormal progesterone levels prior to transfer were associated with LBR and MR after PGT-A. Among the clinical protocols used, vitrified-warmed embryo transfer was more effective than fresh transfer (2 studies, OR: 1.56, 95% CI: 1.05-2.33, I2 = 23%) after PGT-A. Lastly, multiple vitrification-warming cycles (2 studies, OR: 0.41, 95% CI: 0.22-0.77, I2 = 50%) or (by qualitative analysis) a high number of cells biopsied may slightly reduce the LBR, while simultaneous zona-pellucida opening and TE biopsy allowed better results than the Day 3 hatching-based protocol (3 studies, OR: 1.41, 95% CI: 1.18-1.69, I2 = 0%).

WIDER IMPLICATIONS

Embryo selection aims at shortening the time-to-pregnancy, while minimizing the reproductive risks. Knowing which features are associated with the reproductive competence of euploid blastocysts is therefore critical to define, implement, and validate safer and more efficient clinical workflows. Future research should be directed towards: (i) systematic investigations of the mechanisms involved in reproductive aging beyond de novo chromosomal abnormalities, and how lifestyle and nutrition may accelerate or exacerbate their consequences; (ii) improved evaluation of the uterine and blastocyst-endometrial dialogue, both of which represent black boxes themselves; (iii) standardization/automation of embryo assessment and IVF protocols; (iv) additional invasive or preferably non-invasive tools for embryo selection. Only by filling these gaps we may finally crack the riddle behind 'the black box of implantation'.

An artificial intelligence algorithm for automated blastocyst morphometric parameters demonstrates a positive association with implantation potential

Blastocyst selection is primarily based on morphological scoring systems and morphokinetic data. These methods involve subjective grading and time-consuming techniques. Artificial intelligence allows for objective and quick blastocyst selection. In this study, 608 blastocysts were selected for transfer using morphokinetics and Gardner criteria. Retrospectively, morphometric parameters of blastocyst size, inner cell mass (ICM) size, ICM-to-blastocyst size ratio, and ICM shape were automatically measured by a semantic segmentation neural network model. The model was trained on 1506 videos with 102 videos for validation with no overlap between the ICM and trophectoderm models. Univariable logistic analysis found blastocyst size and ICM-to-blastocyst size ratio to be significantly associated with implantation potential. Multivariable regression analysis, adjusted for woman age, found blastocyst size to be significantly associated with implantation potential. The odds of implantation increased by 1.74 for embryos with a blastocyst size greater than the mean (147 ± 19.1 μm). The performance of the algorithm was represented by an area under the curve of 0.70 (p < 0.01). In conclusion, this study supports the association of a large blastocyst size with higher implantation potential and suggests that automatically measured blastocyst morphometrics can be used as a precise, consistent, and time-saving tool for improving blastocyst selection.

Automatic Ploidy Prediction and Quality Assessment of Human Blastocyst Using Time-Lapse Imaging

Assessing fertilized human embryos is crucial for in vitro-fertilization (IVF), a task being revolutionized by artificial intelligence and deep learning. Existing models used for embryo quality assessment and chromosomal abnormality (ploidy) detection could be significantly improved by effectively utilizing time-lapse imaging to identify critical developmental time points for maximizing prediction accuracy. Addressing this, we developed and compared various embryo ploidy status prediction models across distinct embryo development stages. We present BELA (Blastocyst Evaluation Learning Algorithm), a state-of-the-art ploidy prediction model surpassing previous image- and video-based models, without necessitating subjective input from embryologists. BELA uses multitask learning to predict quality scores that are used downstream to predict ploidy status. By achieving an AUC of 0.76 for discriminating between euploidy and aneuploidy embryos on the Weill Cornell dataset, BELA matches the performance of models trained on embryologists' manual scores. While not a replacement for preimplantation genetic testing for aneuploidy (PGT-A), BELA exemplifies how such models can streamline the embryo evaluation process, reducing time and effort required by embryologists.

Making and selecting the best embryo in the laboratory

Over the past 4 decades our ability to maintain a viable human embryo in vitro has improved dramatically, leading to higher implantation rates. This has led to a notable shift to single blastocyst transfer and the ensuing elimination of high order multiple gestations. Future improvements to embryo culture systems will not only come from new improved innovative media formulations (such as the inclusion of antioxidants), but plausibly by moving away from static culture to more dynamic perfusion-based systems now made a reality owing to the breakthroughs in three-dimensional printing technology and micro fabrication. Such an approach has already made it feasible to create high resolution devices for intracytoplasmic sperm injection, culture, and cryopreservation, paving the way not only for improvements in outcomes but also automation of assisted reproductive technology. Although improvements in culture systems can lead to further increases in pregnancy outcomes, the ability to quantitate biomarkers of embryo health and viability will reduce time to pregnancy and decrease pregnancy loss. Currently artificial intelligence is being used to assess embryo development through image analysis, but we predict its power will be realized through the creation of selection algorithms based on the integration of information related to metabolic functions, cell-free DNA, and morphokinetics, thereby using vast amounts of different data types obtained for each embryo to predict outcomes. All of this will not only make assisted reproductive technology more effective, but it will also make it more cost effective, thereby increasing patient access to infertility treatment worldwide.

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.

Comparing performance between clinics of an embryo evaluation algorithm based on time-lapse images and machine learning

PURPOSE

This article aims to assess how differences in maternal age distributions between IVF clinics affect the performance of an artificial intelligence model for embryo viability prediction and proposes a method to account for such differences.

METHODS

Using retrospectively collected data from 4805 fresh and frozen single blastocyst transfers of embryos incubated for 5 to 6 days, the discriminative performance was assessed based on fetal heartbeat outcomes. The data was collected from 4 clinics, and the discrimination was measured in terms of the area under ROC curves (AUC) for each clinic. To account for the different age distributions between clinics, a method for age-standardizing the AUCs was developed in which the clinic-specific AUCs were standardized using weights for each embryo according to the relative frequency of the maternal age in the relevant clinic compared to the age distribution in a common reference population.

RESULTS

There was substantial variation in the clinic-specific AUCs with estimates ranging from 0.58 to 0.69 before standardization. The age-standardization of the AUCs reduced the between-clinic variance by 16%. Most notably, three of the clinics had quite similar AUCs after standardization, while the last clinic had a markedly lower AUC both with and without standardization.

CONCLUSION

The method of using age-standardization of the AUCs that is proposed in this article mitigates some of the variability between clinics. This enables a comparison of clinic-specific AUCs where the difference in age distributions is accounted for.

Embryo selection through artificial intelligence versus embryologists: a systematic review

STUDY QUESTION

What is the present performance of artificial intelligence (AI) decision support during embryo selection compared to the standard embryo selection by embryologists?

SUMMARY ANSWER

AI consistently outperformed the clinical teams in all the studies focused on embryo morphology and clinical outcome prediction during embryo selection assessment.

WHAT IS KNOWN ALREADY

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.

STUDY DESIGN SIZE DURATION

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.

PARTICIPANTS/MATERIALS SETTING METHODS

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.

MAIN RESULTS AND THE ROLE OF CHANCE

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%).

LIMITATIONS REASONS FOR CAUTION

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.

WIDER IMPLICATIONS OF THE FINDINGS

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.

STUDY FUNDING/COMPETING INTERESTS

This study was funded by Monash Data Future Institute. All authors have no conflicts of interest to declare.

REGISTRATION NUMBER

CRD42021256333.

Deep learning system for classification of ploidy status using time-lapse videos

OBJECTIVE

To develop a spatiotemporal model for de prediction of euploid and aneuploid embryos using time-lapse videos from 10-115 hours after insemination (hpi).

DESIGN

Retrospective study.

MAIN OUTCOME MEASURES

The research used an end-to-end approach to develop an automated artificial intelligence system capable of extracting features from images and classifying them, considering spatiotemporal dependencies. A convolutional neural network extracted the most relevant features from each video frame. A bidirectional long short-term memory layer received this information and analyzed the temporal dependencies, obtaining a low-dimensional feature vector that characterized each video. A multilayer perceptron classified them into 2 groups, euploid and noneuploid.

RESULTS

The model performance in accuracy fell between 0.6170 and 0.7308. A multi-input model with a gate recurrent unit module performed better than others; the precision (or positive predictive value) is 0.8205 for predicting euploidy. Sensitivity, specificity, F1-Score and accuracy are 0.6957, 0.7813, 0.7042, and 0.7308, respectively.

CONCLUSIONS

This article proposes an artificial intelligence solution for prioritizing euploid embryo transfer. We can highlight the identification of a noninvasive method for chromosomal status diagnosis using a deep learning approach that analyzes raw data provided by time-lapse incubators. This method demonstrated potential automation of the evaluation process, allowing spatial and temporal information to encode.

Embryo ploidy status classification through computer-assisted morphology assessment

BACKGROUND

Preimplantation genetic testing for aneuploidy has been proven to be effective in determining the embryo's chromosomal or ploidy status. The test requires a biopsy of embryonic cells on day 3, 5, or 6 from which complete information on the chromosomes would be obtained. The main drawbacks of preimplantation genetic testing for aneuploidy include its relatively invasive approach and the lack of research studies on the long-term effects of preimplantation genetic testing for aneuploidy.

OBJECTIVE

Computer-assisted predictive modeling through machine learning and deep learning algorithms has been proposed to minimize the use of invasive preimplantation genetic testing for aneuploidy. The capability to predict morphologic characteristics of embryo ploidy status creates a meaningful support system for decision-making before further treatment.

STUDY DESIGN

Image processing is a component in developing a predictive model specialized in image classification through which a model is able to differentiate images based on unique features. Image processing is obtained through image augmentation to capture segmented embryos and perform feature extraction. Furthermore, multiple machine learning and deep learning algorithms were used to create prediction-based modeling, and all of the prediction models undergo similar model performance assessments to determine the best model prediction algorithm.

RESULTS

An efficient artificial intelligence model that can predict embryo ploidy status was developed using image processing through a histogram of oriented gradient and then followed by principal component analysis. The gradient boosting algorithm showed an advantage against other algorithms and yielded an accuracy of 0.74, an aneuploid precision of 0.83, and an aneuploid predictive value (recall) of 0.84.

CONCLUSION

This research study proved that machine-assisted technology perceives the embryo differently than human observation and determined that further research on in vitro fertilization is needed. The study finding serves as a basis for developing a better computer-assisted prediction model.

Machine learning assisted health viability assay for mouse embryos with artificial confocal microscopy (ACM)

The combination of a good quality embryo and proper maternal health factors promise higher chances of a successful in vitro fertilization (IVF) procedure leading to clinical pregnancy and live birth. Of these two factors, selection of a good embryo is a controllable aspect. The current gold standard in clinical practice is visual assessment of an embryo based on its morphological appearance by trained embryologists. More recently, machine learning has been incorporated into embryo selection "packages". Here, we report a machine-learning assisted embryo health assessment tool utilizing a quantitative phase imaging technique called artificial confocal microscopy (ACM). We present a label-free nucleus detection method with novel quantitative embryo health biomarkers. Two viability assessment models are presented for grading embryos into two classes: healthy/intermediate (H/I) or sick (S) class. The models achieve a weighted F1 score of 1.0 and 0.99 respectively on the in-distribution test set of 72 fixed embryos and a weighted F1 score of 0.9 and 0.95 respectively on the out-of-distribution test dataset of 19 time-instances from 8 live embryos.

[Interest of iDAScore (intelligent Data Analysis Score) for embryo selection in routine IVF laboratory practice: Results of a preliminary study]

INTRODUCTION

Embryo selection is a major challenge in ART, especially since the generalization of single embryo transfer, and its optimization could lead to the improvement of clinical results in IVF. Recently, several Artificial Intelligence (AI) models, based on deep-learning such as iDAScore, have been developed. These models, trained on time-lapse videos of embryos with known implantation data, can predict the probability of pregnancy for a given embryo, allowing automatization and standardization in embryo selection.

MATERIAL AND METHODS

In this study, we have compared the hierarchical categorization of 311 D5 blastocysts of iDAScore v1.0 and the embryologists of our unit. These 311 D5 blastocysts have been classified as top (70.1%), good (Q+: 10.6%) and poor (Q-: 19.3%) quality by embryologists according to Gardner classification. Median iDAScores were [9.9-8.4],]8.4-7.5] and]7.5-2.1] for top, good and poor-quality blastocysts respectively.

RESULTS

We observed a significantly concordant categorization between iDAScore and embryologists for top, good and poor-quality blastocysts (respectively, 89.5, 36.4 and 48.3%, P < 10-4). Moreover, the hierarchical categorization of the three best blastocysts between iDAScore and the embryologists was as follow: 1st rank: 71.9%; 2nd rank: 61.6%; 3rd rank: 56.8% (P=0.07). One hundred and fifty-one blastocysts with known implantation data were analyzed. The iDAScore of blastocysts that implanted was significantly higher than those that did not implant (implantation+: 9.10±0.57; implantation-: 8.70±0.95, P=0.003).

CONCLUSION

This preliminary study shows that iDAScore is able to perform a reproducible, reliable and immediate hierarchical classification of blastocysts. Moreover, this tool can identify the blastocysts with the highest implantation potential. If these results confirmed on a larger scale of embryos and patients, IA could revolutionize IVF laboratories by standardizing embryo hierarchical selection.