An interpretable and versatile machine learning approach for oocyte phenotyping

Automated detection and recognition of oocyte toxicity by fusion of latent and observable features

Oocyte quality is essential for successful pregnancy, yet no discriminant criterion exists to assess the effects of environmental pollutants on oocyte abnormalities. We developed a stepwise framework integrating deep learning-extracted latent features with observable human-concept features focused on toxicity detection, subtype and strength classification. Based on 2126 murine oocyte images, this method achieves performance surpassing human capabilities with ROC-AUC of 0.9087 for toxicity detection, 0.7956-0.9034 for subtype classification with Perfluorohexanesulfonic Acid(PFHxS) achieving highest score of 0.9034 and 0.6434-0.9062 for toxicity strength classification with PFHxS achieving highest score of 0.9062. Notably, Ablation studies confirmed feature fusion improved performance by 18.7-23.4 % over single-domain models, highlighting their complementary relationship. Personalized heatmaps and feature importance revealed biomarker regions such as polar body and cortical areas aligning with clinical knowledge. AI-driven oocyte selection predicts embryo competence under pollutants, bridging computational toxicology to mitigate infertility.

Noninvasive characterization of oocyte deformability in microconstrictions

Oocytes naturally present mechanical defects that hinder their development after fertilization. Thus, in the context of assisted reproduction, oocyte selection based on their mechanical properties has great potential to improve the quality of the resulting embryos and the success rate of these procedures. However, using mechanical properties as a quantifiable selective criterion requires robust and nondestructive measurement tools. This study developed a constriction-based microfluidic device that monitors the deformation of mouse oocytes under controlled pressure. The device can distinguish mechanically aberrant oocyte groups from healthy control ones. On the basis of a mathematical model, we propose that deformability measurements infer both oocyte tension and elasticity, elasticity being the most discriminating factor in our geometry. Despite force transmission during oocyte deformation, no long-term damage was observed. This noninvasive characterization of mouse oocyte deformability in microconstrictions allows for a substantial advance in assessing the mechanical properties of mammalian oocytes and has potential application as a quantifiable selective criterion in medically assisted reproduction.

Fluo-Cast-Bright: a deep learning pipeline for the non-invasive prediction of chromatin structure and developmental potential in live oocytes

In mammalian oocytes, large-scale chromatin organization regulates transcription, nuclear architecture, and maintenance of chromosome stability in preparation for meiosis onset. Pre-ovulatory oocytes with distinct chromatin configurations exhibit profound differences in metabolic and transcriptional profiles that ultimately determine meiotic competence and developmental potential. Here, we developed a deep learning pipeline for the non-invasive prediction of chromatin structure and developmental potential in live mouse oocytes. Our Fluorescence prediction and Classification on Bright-field (Fluo-Cast-Bright) pipeline achieved 91.3% accuracy in the classification of chromatin state in fixed oocytes and 85.7% accuracy in live oocytes. Importantly, transcriptome analysis following non-invasive selection revealed that meiotically competent oocytes exhibit a higher expression of transcripts associated with RNA and protein nuclear export, maternal mRNA deadenylation, histone modifications, chromatin remodeling and signaling pathways regulating microtubule dynamics during the metaphase-I to metaphase-II transition. Fluo-Cast-Bright provides fast and non-invasive selection of meiotically competent oocytes for downstream research and clinical applications.

Exploring the maternal inheritance transmitted by the oocyte to its progeny

Fertility is declining worldwide and many couples are turning towards assisted reproductive technologies (ART) to conceive babies. Organisms that propagate via sexual reproduction often come from the fusion between two gametes, an oocyte and a sperm, whose qualities seem to be decreasing in the human species. Interestingly, while the sperm mostly transmits its haploid genome, the oocyte transmits not only its haploid set of chromosomes but also its huge cytoplasm to its progeny. This is what can be defined as the maternal inheritance composed of chromosomes, organelles, lipids, metabolites, proteins and RNAs. To decipher the decline in oocyte quality, it is essential to explore the nature of the maternal inheritance, and therefore study the last stages of murine oogenesis, namely the end of oocyte growth followed by the two meiotic divisions. These divisions are extremely asymmetric in terms of the size of the daughter cells, allowing to preserve the maternal inheritance accumulated during oocyte growth within these huge cells to support early embryo development. Studies performed in Marie-Hélène Verlhac's lab have allowed to discover the unprecedented impact of original acto-myosin based mechanisms in the constitution as well as the preservation of this maternal inheritance and the consequences when these processes go awry.

Segmentation of mature human oocytes provides interpretable and improved blastocyst outcome predictions by a machine learning model

Within the medical field of human assisted reproductive technology, a method for interpretable, non-invasive, and objective oocyte evaluation is lacking. To address this clinical gap, a workflow utilizing machine learning techniques has been developed involving automatic multi-class segmentation of two-dimensional images, morphometric analysis, and prediction of developmental outcomes of mature denuded oocytes based on feature extraction and clinical variables. Two separate models have been developed for this purpose-a model to perform multiclass segmentation, and a classifier model to classify oocytes as likely or unlikely to develop into a blastocyst (Day 5-7 embryo). The segmentation model is highly accurate at segmenting the oocyte, ensuring high-quality segmented images (masks) are utilized as inputs for the classifier model (mask model). The mask model displayed an area under the curve (AUC) of 0.63, a sensitivity of 0.51, and a specificity of 0.66 on the test set. The AUC underwent a reduction to 0.57 when features extracted from the ooplasm were removed, suggesting the ooplasm holds the information most pertinent to oocyte developmental competence. The mask model was further compared to a deep learning model, which also utilized the segmented images as inputs. The performance of both models combined in an ensemble model was evaluated, showing an improvement (AUC 0.67) compared to either model alone. The results of this study indicate that direct assessments of the oocyte are warranted, providing the first objective insights into key features for developmental competence, a step above the current standard of care-solely utilizing oocyte age as a proxy for quality.

Aberrant cortex contractions impact mammalian oocyte quality

The cortex controls cell shape. In mouse oocytes, the cortex thickens in an Arp2/3-complex-dependent manner, ensuring chromosome positioning and segregation. Surprisingly, we identify that mouse oocytes lacking the Arp2/3 complex undergo cortical actin remodeling upon division, followed by cortical contractions that are unprecedented in mammalian oocytes. Using genetics, imaging, and machine learning, we show that these contractions stir the cytoplasm, resulting in impaired organelle organization and activity. Oocyte capacity to avoid polyspermy is impacted, leading to a reduced female fertility. We could diminish contractions and rescue cytoplasmic anomalies. Similar contractions were observed in human oocytes collected as byproducts during IVF (in vitro fertilization) procedures. These contractions correlate with increased cytoplasmic motion, but not with defects in spindle assembly or aneuploidy in mice or humans. Our study highlights a multiscale effect connecting cortical F-actin, contractions, and cytoplasmic organization and affecting oocyte quality, with implications for female fertility.

Oocyte vitrification for fertility preservation is an evolving practice requiring a new mindset: societal, technical, clinical, and basic science-driven evolutions

Infertility is a condition with profound social implications. Indeed, it is not surprising that evolutions in both medicine and society affect the way in vitro fertilization is practiced. The keywords in modern medicine are the four principles, which implicitly involve a constant update of our knowledge and our technologies to fulfill the "prediction" and "personalization" tasks, and a continuous reshaping of our mindset in view of all relevant societal changes to fulfill the "prevention" and "participation" tasks. A worldwide aging population whose life priorities are changing requires that we invest in fertility education, spreading actionable information to allow women and men to make meaningful reproductive choices. Fertility preservation for both medical and nonmedical reasons is still very much overlooked in many countries worldwide, demanding a comprehensive update of our approach, starting from academia and in vitro fertilization laboratories, passing through medical offices, and reaching out to social media. Reproduction medicine should evolve from being a clinical practice to treat a condition to being a holistic approach to guarantee patients' reproductive health and well-being. Oocyte vitrification for fertility preservation is the perfect use case for this transition. This tool is acquiring a new identity to comply with novel indications and social needs, persisting technical challenges, brand-new clinical technologies, and novel revolutions coming from academia. This "views and reviews" piece aims at outlining the advancement of oocyte vitrification from all these tightly connected perspectives.

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.

Filopodia-like protrusions of adjacent somatic cells shape the developmental potential of oocytes

The oocyte must grow and mature before fertilization, thanks to a close dialogue with the somatic cells that surround it. Part of this communication is through filopodia-like protrusions, called transzonal projections (TZPs), sent by the somatic cells to the oocyte membrane. To investigate the contribution of TZPs to oocyte quality, we impaired their structure by generating a full knockout mouse of the TZP structural component myosin-X (MYO10). Using spinning disk and super-resolution microscopy combined with a machine-learning approach to phenotype oocyte morphology, we show that the lack of Myo10 decreases TZP density during oocyte growth. Reduction in TZPs does not prevent oocyte growth but impairs oocyte-matrix integrity. Importantly, we reveal by transcriptomic analysis that gene expression is altered in TZP-deprived oocytes and that oocyte maturation and subsequent early embryonic development are partially affected, effectively reducing mouse fertility. We propose that TZPs play a role in the structural integrity of the germline-somatic complex, which is essential for regulating gene expression in the oocyte and thus its developmental potential.

Identification of significant imaging features for sensing oocyte viability

The evaluation of oocyte viability in the laboratory is limited to the morphological assessment by naked eyes, but the realization that most normal-appearing oocytes may conceal abnormalities prompts the search for automated approaches that can detect the abnormalities imperceptible to naked eyes. In this study, we developed an image processing pipeline applicable to bright-field microscope images to quantify the causal relationship between the quantitative imaging features and the developmental potential of oocytes. We acquired 19 imaging features of approximately 700 oocytes and determined two imaging subtypes, namely viable and nonviable subtypes that correlated closely with a viability fluorescence indicator and cleavage rates. The causal relationship between these imaging features and oocyte viability was derived from a viability-oriented Bayesian network that was developed based on the Bayesian information criterion and Tabu search. Our experimental results revealed that entropy with mean Gray Level Co-Occurrence Matrix energy describing the uniformity and texture roughness of cytoplasm were salient features for the automated selection of promising oocytes that exhibited excellent developmental potential.

Looking with new eyes: advanced microscopy and artificial intelligence in reproductive medicine

Microscopy has long played a pivotal role in the field of assisted reproductive technology (ART). The advent of artificial intelligence (AI) has opened the door for new approaches to sperm and oocyte assessment and selection, with the potential for improved ART outcomes.

First person – Gaëlle Letort

First Person is a series of interviews with the first authors of a selection of papers published in Journal of Cell Science, helping early-career researchers promote themselves alongside their papers. Gaëlle Letort is first author on ‘ An interpretable and versatile machine learning approach for oocyte phenotyping’, published in JCS. Gaëlle conducted the research described in this article while a post-doc in Marie-Emilie Terret and Marie-Hélène Verlhac’s lab at Collège de France, Paris. She is now a Research Engineer (CNRS) in the lab of Department of Developmental and Stem Cell Biology at Institut Pasteur, Paris, investigating mathematical modelling and image analysis applied to biology.

An interpretable and versatile machine learning approach for oocyte phenotyping

Meiotic maturation is a crucial step of oocyte formation, allowing its potential fertilization and embryo development. Elucidating this process is important for both fundamental research and assisted reproductive technology. However, few computational tools based on non-invasive measurements are available to characterize oocyte meiotic maturation. Here, we develop a computational framework to phenotype oocytes based on images acquired in transmitted light. We trained neural networks to segment the contour of oocytes and their zona pellucida using oocytes from diverse species. We defined a comprehensive set of morphological features to describe an oocyte. These steps were implemented in an open-source Fiji plugin. We present a feature-based machine learning pipeline to recognize oocyte populations and determine morphological differences between them. We first demonstrate its potential to screen oocytes from different strains and automatically identify their morphological characteristics. Its second application is to predict and characterize the maturation potential of oocytes. We identify the texture of the zona pellucida and cytoplasmic particle size as features to assess mouse oocyte maturation potential and tested whether these features were applicable to the developmental potential of human oocytes. This article has an associated First Person interview with the first author of the paper.