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

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.

Does cleavage stage morphology increase the discriminatory power of prediction in blastocyst transfer outcome?

PURPOSE

To evaluate the contribution of the cleavage stage morphological parameters to the prediction of blastocyst transfer outcomes.

METHODS

A retrospective study was conducted on 8383 single-blastocyst transfer cycles including 2246 fresh and 6137 vitrified-warmed cycles. XGboost, LASSO, and GLM algorithms were employed to establish models for assessing the predictive value of the cleavage stage morphological parameters in transfer outcomes. Four models were developed using each algorithm: all-in model with or without day 3 morphology and embryo quality-only model with or without day 3 morphology.

RESULTS

The live birth rate was 48.04% in the overall cohort. The AUCs of the models with the algorithm of XGboost were 0.83, 0.82, 0.63, and 0.60; with LASSO were 0.66, 0.66, 0.61, and 0.60; and with GLM were 0.66, 0.66, 0.61, and 0.60 respectively. In models 1 and 2, female age, basal FSH, peak E2, endometrial thickness, and female BMI were the top five critical features for predicting live birth; In models 3 and 4, the most crucial factor was blastocyst formation on D5 rather than D6. In model 3, incorporating cleavage stage morphology, including early cleavage, D3 cell number, and fragmentation, was significantly associated with successful live birth. Additionally, the live birth rates for blastocysts derived from on-time, slow, and fast D3 embryos were 49.7%, 39.5%, and 52%, respectively.

CONCLUSIONS

The value of cleavage stage morphological parameters in predicting the live birth outcome of single blastocyst transfer is limited.

Novel embryo selection strategies-finding the right balance

The use of novel technologies in the selection of embryos during in vitro fertilisation (IVF) has the potential to improve the chances of pregnancy and birth of a healthy child. However, it is important to be aware of the potential risks and unintended consequences that may arise from the premature implementation of these technologies. This article discusses the ethical considerations surrounding the use of novel embryo selection technologies in IVF, including the growing uptake of genetic testing and others, and argues that prioritising embryos for transfer using these technologies is acceptable, but discarding embryos based on unproven advances is not. Several historical examples are provided, which demonstrate possible harms, where the overall chance of pregnancy may have been reduced, and some patients may have missed out on biological parenthood altogether. We emphasise the need for caution and a balanced approach to ensure that the benefits of these technologies outweigh any potential harm. We also highlight the primacy of patients' autonomy in reproductive decision-making, especially when information gained by utilising novel technologies is imprecise.

Impact of having surplus blastocysts cryopreserved on the ongoing pregnancy rate following a fresh transfer

PURPOSE

This study aimed to investigate whether a surplus of vitrified blastocysts correlated with ongoing pregnancy by analyzing the clinical outcomes of fresh transfer cycles with/without a surplus of vitrified blastocysts.

METHODS

This was a retrospective analysis carried out in the Reproductive Medicine Center of Guizhou Medical University Affiliated Hospital between January 2020 and December 2021. Overall, 2482 fresh embryo transfer cycles were included in this study, including 1731 cycles with a surplus of vitrified blastocysts (group A) and 751 cycles with no surplus of vitrified blastocysts (group B). The clinical outcomes of fresh embryo transfer cycles were analyzed and compared between the two groups.

RESULTS

In total, the clinical pregnancy rate (CPR) and ongoing pregnancy rate (OPR) after fresh transfer in group A were significantly higher than those in group B (59% vs. 34.1%, p < .001; 51.9% vs. 27.8%, p < .001, respectively). Moreover, the miscarriage rate was significantly lower in group A when compared to that in group B (10.8% vs. 16.8%, p = .008). When grouped by either female age or the number of good-quality embryos transferred, the same trends for CPR and OPR were seen in all subgroups. After adjusting for potential confounding factors in multivariate analysis, a surplus of vitrified blastocysts remained significantly associated with a higher OPR (OR: 1.52; 95% CI:1.21-1.92).

CONCLUSION

Ongoing pregnancy outcome increases significantly in fresh transfer cycle with a surplus of vitrified blastocysts.

Advancing bovine in vitro fertilization through 3D printing: the effect of the 3D printed materials

Nowadays there is an increasing demand for assisted reproductive technologies due to the growth of infertility problems. Naturally, fertilization occurs in the oviduct, where the oviductal epithelial cells (OECs) secrete many molecules that affect the embryo's metabolism and protect it from oxidative stress. When the OECs are grown in 3D culture systems, they maintain a great part of their functional characteristics, making them an excellent model for in vitro fertilization (IVF) studies. In this work, we aimed to evaluate the suitability of different 3D-printing processes in conjunction with the corresponding set of commercially available biomaterials: extrusion-based processing using polylactic acid (PLA) and polycaprolactone (PCL) and stereolithography or digital-light processing using polyethylene-glycol-diacrylate (PEGDA) with different stiffness (PEGDA500, PEGDA200, PEGDA PhotoInk). All the 3D-printed scaffolds were used to support IVF process in a bovine embryo assay. Following fertilization, embryo development and quality were assessed in terms of cleavage, blastocyst rate at days 7 and 8, total cell number (TCN), inner cell mass/trophectoderm ratio (ICN/TE), and apoptotic cell ratio (ACR). We found a detrimental effect on cleavage and blastocyst rates when the IVF was performed on any medium conditioned by most of the materials available for digital-light processing (PEGDA200, PEGDA500). The observed negative effect could be possibly due to some leaked compound used to print and stabilize the scaffolds, which was not so evident however with PEGDA PhotoInk. On the other hand, all the extrusion-based processable materials did not cause any detrimental effect on cleavage or blastocyst rates. The principal component analysis reveals that embryos produced in presence of 3D-printed scaffolds produced via extrusion exhibit the highest similarity with the control embryos considering cleavage, blastocyst rates, TCN, ICN/TE and ACR per embryo. Conversely, all the photo-cross linkable materials or medium conditioned by PLA, lead to the highest dissimilarities. Since the use of PCL scaffolds, as well as its conditioned medium, bring to embryos that are more similar to the control group. Our results suggest that extrusion-based 3D printing of PCL could be the best option to be used for new IVF devices, possibly including the support of OECs, to enhance bovine embryo development.

The anti-infective crotalicidin peptide analog RhoB-Ctn[1-9] is harmless to bovine oocytes and able to induce parthenogenesis in vitro

Crotalicidin is a cathelicidin-related anti-infective (antimicrobial) peptide expressed in the venom glands of the South American rattlesnake Crotalus durissus terrificus. Congener peptides of crotalicidin, named vipericidins, are found in other pit vipers inhabiting South America. Crotalicidin is active against bacteria and pathogenic yeasts and has anti-proliferative activity for some cancer cells. The structural dissection of crotalicidin produced fragments (e.g., Ctn [15-34]) with multiple biological functionalities that mimic the native peptide. Another structural characteristic of crotalidicin and congeners is a unique repetitive stretch of amino acid sequences in tandem embedded in their primary structures. One of the encrypted vipericidn peptides (Ctn [1-9]) was synthesized, and the analog covalently conjugated with rhodamine B (RhoB-Ctn [1-9]) displayed considerable antimicrobial activity and selective cytotoxicity. Methods to evaluate antimicrobial peptides' toxicity include lysis of red blood cells (hemolysis) in vitro and cytotoxicity of healthy cultured cells (e.g., fibroblasts). Here, as a non-conventional model of toxicity, the bovine oocytes were exposed to two standardized concentrations of RhoB-Ctn [1-9], and embryo viability and development at its first stage of cleavage (division of cells) and blastocyst formation were evaluated. Oocytes treated with peptide at 10 and 40 μM induced cleavage rates of 44.94% and 51.53%, resulting in the formation of blastocysts of 7.07% and 11.73%, respectively. Light sheet microscopy and in silico prediction analysis indicated that RhoB-Ctn [1-9] peptide interacts with zona pellucida and internalizes into bovine oocytes and developing embryos. The ADMET prediction estimated good bioavailability of RhoB-Ctn [1-9]. In conclusion, the peptide appeared harmless to bovine oocytes and, remarkably, activated the parthenogenesis in vitro.