AI-algorithm training and validation for identification of endometrial CD138+ cells in infertility-associated conditions; polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF).

Background: Endometrial CD138+ plasma cells serve as a diagnostic biomarker for endometrial inflammation, and their elevated occurrence correlates positively with adverse pregnancy outcomes. Infertility-related conditions like polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF) are closely associated with systemic and local chronic inflammatory status, wherein endometrial CD138+ plasma cell accumulation could also contribute to endometrial pathology. Current methods for quantifying CD138+ cells typically involve laborious and time-consuming microscopic assessments of only a few random areas from a slide. These methods have limitations in accurately representing the entire slide and are susceptible to significant biases arising from intra- and interobserver variations. Implementing artificial intelligence (AI) for CD138+ cell identification could enhance the accuracy, reproducibility, and reliability of analysis. Methods: Here, an AI algorithm was developed to identify CD138+ plasma cells within endometrial tissue. The AI model comprised two layers of convolutional neural networks (CNNs). CNN1 was trained to segment epithelium and stroma across 28,363 mm2 (2.56 mm2 of epithelium and 24.87 mm2 of stroma), while CNN2 was trained to distinguish stromal cells based on CD138 staining, encompassing 7345 cells in the object layers (6942 CD138- cells and 403 CD138+ cells). The training and performance of the AI model were validated by three experienced pathologists. We collected 193 endometrial tissues from healthy controls (n = 73), women with PCOS (n = 91), and RIF patients (n = 29) and compared the CD138+ cell percentages based on cycle phases, ovulation status, and endometrial receptivity utilizing the AI model. Results: The AI algorithm consistently and reliably distinguished CD138- and CD138+ cells, with total error rates of 6.32% and 3.23%, respectively. During the training validation, there was a complete agreement between the decisions made by the pathologists and the AI algorithm, while the performance validation demonstrated excellent accuracy between the AI and human evaluation methods (intraclass correlation; 0.76, 95% confidence intervals; 0.36-0.93, p = 0.002) and a positive correlation (Spearman's rank correlation coefficient: 0.79, p < 0.01). In the AI analysis, the AI model revealed higher CD138+ cell percentages in the proliferative phase (PE) endometrium compared to the secretory phase or anovulatory PCOS endometrium, irrespective of PCOS diagnosis. Interestingly, CD138+ percentages differed according to PCOS phenotype in the PE (p = 0.03). On the other hand, the receptivity status had no impact on the cell percentages in RIF samples. Conclusion: Our findings emphasize the potential and accuracy of the AI algorithm in detecting endometrial CD138+ plasma cells, offering distinct advantages over manual inspection, such as rapid analysis of whole slide images, reduction of intra- and interobserver variations, sparing the valuable time of trained specialists, and consistent productivity. This supports the application of AI technology to help clinical decision-making, for example, in understanding endometrial cycle phase-related dynamics, as well as different reproductive disorders.

Dynamic changes in AI-based analysis of endometrial cellular composition: Analysis of PCOS and RIF endometrium.

Background: The human endometrium undergoes a monthly cycle of tissue growth and degeneration. During the mid-secretory phase, the endometrium establishes an optimal niche for embryo implantation by regulating cellular composition (e.g., epithelial and stromal cells) and differentiation. Impaired endometrial development observed in conditions such as polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF) contributes to infertility. Surprisingly, despite the importance of the endometrial lining properly developing prior to pregnancy, precise measures of endometrial cellular composition in these two infertility-associated conditions are entirely lacking. Additionally, current methods for measuring the epithelial and stromal area have limitations, including intra- and inter-observer variability and efficiency. Methods: We utilized a deep-learning artificial intelligence (AI) model, created on a cloud-based platform and developed in our previous study. The AI model underwent training to segment both areas populated by epithelial and stromal endometrial cells. During the training step, a total of 28.36 mm2 areas were annotated, comprising 2.56 mm2 of epithelium and 24.87 mm2 of stroma. Two experienced pathologists validated the performance of the AI model. 73 endometrial samples from healthy control women were included in the sample set to establish cycle phase-dependent dynamics of the endometrial epithelial-to-stroma ratio from the proliferative (PE) to secretory (SE) phases. In addition, 91 samples from PCOS cases, accounting for the presence or absence of ovulation and representing all menstrual cycle phases, and 29 samples from RIF patients on day 5 after progesterone administration in the hormone replacement treatment cycle were also included and analyzed in terms of cellular composition. Results: Our AI model exhibited reliable and reproducible performance in delineating epithelial and stromal compartments, achieving an accuracy of 92.40% and 99.23%, respectively. Moreover, the performance of the AI model was comparable to the pathologists' assessment, with F1 scores exceeding 82% for the epithelium and >96% for the stroma. Next, we compared the endometrial epithelial-to-stromal ratio during the menstrual cycle in women with PCOS and in relation to endometrial receptivity status in RIF patients. The ovulatory PCOS endometrium exhibited epithelial cell proportions similar to those of control and healthy women's samples in every cycle phase, from the PE to the late SE, correlating with progesterone levels (control SE, r2 = 0.64, FDR < 0.001; PCOS SE, r2 = 0.52, FDR < 0.001). The mid-SE endometrium showed the highest epithelial percentage compared to both the early and late SE endometrium in both healthy women and PCOS patients. Anovulatory PCOS cases showed epithelial cellular fractions comparable to those of PCOS cases in the PE (Anovulatory, 14.54%; PCOS PE, 15.56%, p = 1.00). We did not observe significant differences in the epithelial-to-stroma ratio in the hormone-induced endometrium in RIF patients with different receptivity statuses. Conclusion: The AI model rapidly and accurately identifies endometrial histology features by calculating areas occupied by epithelial and stromal cells. The AI model demonstrates changes in epithelial cellular proportions according to the menstrual cycle phase and reveals no changes in epithelial cellular proportions based on PCOS and RIF conditions. In conclusion, the AI model can potentially improve endometrial histology assessment by accelerating the analysis of the cellular composition of the tissue and by ensuring maximal objectivity for research and clinical purposes.

Investigating the impact of vitrification on bovine ovarian tissue morphology, follicle survival, and transcriptomic signature.

PURPOSE: Ovarian tissue cryopreservation is vital for fertility preservation, yet its effect on ovarian tissue follicle survival and transcriptomic signature requires further investigation. This study delves into the effects of vitrification on tissue morphology, function, and transcriptomic changes, helping to find possibilities for vitrification protocol improvements. METHODS: Ovarian cortex from 19 bovine animals were used to conduct pre- and post-vitrification culture followed by histological assessment, immunohistochemistry, and TUNEL assay. Follicles' functionality was assessed for viability and growth within the tissue and in isolated cultures. RNA-sequencing of ovarian tissue was used to explore the transcriptomic alterations caused by vitrification. RESULTS: Follicle density, cell proliferation, and DNA damage in ovarian stroma were unaffected by vitrification. However, vitrified cultured tissue exhibited reduced follicle density of primordial/primary and antral follicles, while freshly cultured tissue manifested reduction of antral follicles. Increased stromal cell proliferation and DNA damage occurred in both groups post-culture. Isolated follicles from vitrified tissue exhibited similar viability to fresh follicles until day 4, after which the survival dropped. RNA-sequencing revealed minor effects of vitrification on transcriptomic signatures, while culture induced significant gene expression changes in both groups. The altered expression of WNT and hormonal regulation pathway genes post-vitrification suggests the molecular targets for vitrification protocol refinement. CONCLUSION: Vitrification minimally affects tissue morphology, follicle density, and transcriptomic signature post-thawing. However, culture revealed notable changes in vitrified tissue samples, including reduced follicle density, decreased isolated follicle survival, and alteration in WNT signalling and ovarian hormonal regulation pathways, highlighted them as possible limitations of the current vitrification protocol.

Machine Learning Approaches to Classify Primary and Metastatic Cancers Using Tissue of Origin-Based DNA Methylation Profiles.

Metastatic cancers account for up to 90% of cancer-related deaths. The clear differentiation of metastatic cancers from primary cancers is crucial for cancer type identification and developing targeted treatment for each cancer type. DNA methylation patterns are suggested to be an intriguing target for cancer prediction and are also considered to be an important mediator for the transition to metastatic cancer. In the present study, we used 24 cancer types and 9303 methylome samples downloaded from publicly available data repositories, including The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO). We constructed machine learning classifiers to discriminate metastatic, primary, and non-cancerous methylome samples. We applied support vector machines (SVM), Naive Bayes (NB), extreme gradient boosting (XGBoost), and random forest (RF) machine learning models to classify the cancer types based on their tissue of origin. RF outperformed the other classifiers, with an average accuracy of 99%. Moreover, we applied local interpretable model-agnostic explanations (LIME) to explain important methylation biomarkers to classify cancer types.

Decidualized endometrial stromal cells present with altered androgen response in PCOS.

Hyperandrogenic women with PCOS show disrupted decidualization (DE) and placentation. Dihydrotestosterone (DHT) is reported to enhance DE in non-PCOS endometrial stromal cells (eSCCtrl); however, this has not been assessed in PCOS cells (eSCPCOS). Therefore, we studied the transcriptome profile of non-decidualized (non-DE) and DE eSCs from women with PCOS and Ctrl in response to short-term estradiol (E2) and/or progesterone (P4) exposure with/without (±) DHT. The non-DE eSCs were subjected to E2 ± DHT treatment, whereas the DE (0.5 mM 8-Br-cAMP, 96 h) eSCs were post-treated with E2 and P4 ± DHT, and RNA-sequenced. Validation was performed by immunofluorescence and immunohistochemistry. The results showed that, regardless of treatment, the PCOS and Ctrl samples clustered separately. The comparison of DE vs. non-DE eSCPCOS without DHT revealed PCOS-specific differentially expressed genes (DEGs) involved in mitochondrial function and progesterone signaling. When further adding DHT, we detected altered responses for lysophosphatidic acid (LPA), inflammation, and androgen signaling. Overall, the results highlight an underlying defect in decidualized eSCPCOS, present with or without DHT exposure, and possibly linked to the altered pregnancy outcomes. We also report novel factors which elucidate the mechanisms of endometrial dysfunction in PCOS.

A case report and follow-up of the first live birth after heterotopic transplantation of cryopreserved ovarian tissue in Eastern Europe.

BACKGROUND: Ovarian insufficiency is a major concern for long-term cancer survivors. Although semen freezing is well established to preserve male fertility, the possibilities to secure post-cancer female fertility are mostly limited to oocyte or embryo freezing. These methods require time-consuming ovarian stimulation with or without in vitro fertilization (IVF) that evidently delays cancer therapy. Ovarian tissue cryopreservation and subsequent thawed tissue autotransplantation are considered the most promising alternative strategy for restoring the fertility of oncology patients, which has not yet received the full clinical acceptance. Therefore, all successful cases are needed to prove its reliability and safety. CASE PRESENTATION: Here we report a single case in Estonia, where a 28-year-old woman with malignant breast neoplasm had ovarian cortex cryopreserved before commencing gonadotoxic chemo- and radiotherapy. Two years after cancer therapy, the patient underwent heterotopic ovarian tissue transplantation into the lateral pelvic wall. The folliculogenesis was stimulated in the transplanted tissue by exogenous follicle-stimulating hormone and oocytes were collected under ultrasound guidance for IVF and embryo transfer. The healthy boy was born after full-term gestation in 2014, first in Eastern Europe. CONCLUSION: Despite many countries have reported the first implementation of the ovarian tissue freezing and transplantation protocols, the data is still limited on the effectiveness of heterotopic ovarian transplant techniques. Thus, all case reports of heterotopic ovarian tissue transplantation and long-term follow-ups to describe the children's health are valuable source of clinical experience.

The role of integrin ß1 in the heterogeneity of human embryonic stem cells culture.

The maintenance of the pluripotency of human embryonic stem (hES) cells requires special conditions for culturing. These conditions include specific growth factors containing media and extracellular matrix (ECM) or an appropriate substrate for adhesion. Interactions between the cells and ECM are mediated by integrins, which interact with the components of ECM in active conformation. This study focused on the characterisation of the role of integrin ß1 in the adhesion, migration and differentiation of hES cells. Blocking integrin ß1 abolished the adhesion of hES cells, decreasing their survival and pluripotency. This effect was in part rescued by the inhibition of RhoA signalling with Y-27632. The presence of Y-27632 increased the migration of hES cells and supported their differentiation into embryoid bodies. The differences in integrin ß1 recycling in the phosphorylation of the myosin light chain and in the localisation of TSC2 were observed between the hES cells growing as a single-cell culture and in a colony. The hES cells at the centre and borders of the colony were found to have differences in their morphology, migration and signalling network activity. We concluded that the availability of integrin ß1 was essential for the contraction, migration and differentiation ability of hES cells.

Targeted deletion of RIC8A in mouse neural precursor cells interferes with the development of the brain, eyes, and muscles.

Autosomal recessive disorders such as Fukuyama congenital muscular dystrophy, Walker-Warburg syndrome, and the muscle-eye-brain disease are characterized by defects in the development of patient's brain, eyes, and skeletal muscles. These syndromes are accompanied by brain malformations like type II lissencephaly in the cerebral cortex with characteristic overmigrations of neurons through the breaches of the pial basement membrane. The signaling pathways activated by laminin receptors, dystroglycan and integrins, control the integrity of the basement membrane, and their malfunctioning may underlie the pathologies found in the rise of defects reminiscent of these syndromes. Similar defects in corticogenesis and neuromuscular disorders were found in mice when RIC8A was specifically removed from neural precursor cells. RIC8A regulates a subset of G-protein α subunits and in several model organisms, it has been reported to participate in the control of cell division, signaling, and migration. Here, we studied the role of RIC8A in the development of the brain, muscles, and eyes of the neural precursor-specific conditional Ric8a knockout mice. The absence of RIC8A severely affected the attachment and positioning of radial glial processes, Cajal-Retzius' cells, and the arachnoid trabeculae, and these mice displayed additional defects in the lens, skeletal muscles, and heart development. All the discovered defects might be linked to aberrancies in cell adhesion and migration, suggesting that RIC8A has a crucial role in the regulation of cell-extracellular matrix interactions and that its removal leads to the phenotype characteristic to type II lissencephaly-associated diseases. © 2018 Wiley Periodicals, Inc. Develop Neurobiol 78: 374-390, 2018.

RIC8A is essential for the organisation of actin cytoskeleton and cell-matrix interaction.

RIC8A functions as a chaperone and guanine nucleotide exchange factor for a subset of G protein α subunits. Multiple G protein subunits mediate various signalling events that regulate cell adhesion and migration and the involvement of RIC8A in some of these processes has been demonstrated. We have previously shown that the deficiency of RIC8A causes a failure in mouse gastrulation and neurogenesis - major events in embryogenesis that rely on proper association of cells with the extracellular matrix (ECM) and involve active cell migration. To elaborate on these findings, we used Ric8a-/- mouse embryonic stem cells and Ric8a-deficient mouse embryonic fibroblasts, and found that RIC8A plays an important role in the organisation and remodelling of actin cytoskeleton and cell-ECM association. Ric8a-deficient cells were able to attach to different ECM components, but were unable to spread correctly, and did not form stress fibres or focal adhesion complexes. We also found that the presence of RIC8A is necessary for the activation of ß1 integrins and integrin-mediated cell migration.

Expression Pattern and Localization Dynamics of Guanine Nucleotide Exchange Factor RIC8 during Mouse Oogenesis.

Targeting of G proteins to the cell cortex and their activation is one of the triggers of both asymmetric and symmetric cell division. Resistance to inhibitors of cholinesterase 8 (RIC8), a guanine nucleotide exchange factor, activates a certain subgroup of G protein α-subunits in a receptor independent manner. RIC8 controls the asymmetric cell division in Caenorhabditis elegans and Drosophila melanogaster, and symmetric cell division in cultured mammalian cells, where it regulates the mitotic spindle orientation. Although intensely studied in mitosis, the function of RIC8 in mammalian meiosis has remained unknown. Here we demonstrate that the expression and subcellular localization of RIC8 changes profoundly during mouse oogenesis. Immunofluorescence studies revealed that RIC8 expression is dependent on oocyte growth and cell cycle phase. During oocyte growth, RIC8 is abundantly present in cytoplasm of oocytes at primordial, primary and secondary preantral follicle stages. Later, upon oocyte maturation RIC8 also populates the germinal vesicle, its localization becomes cell cycle dependent, and it associates with chromatin and the meiotic spindle. After fertilization, RIC8 protein converges to the pronuclei and is also detectable at high levels in the nucleolus precursor bodies of both maternal and paternal pronucleus. During first cleavage of zygote RIC8 localizes in the mitotic spindle and cell cortex of forming blastomeres. In addition, we demonstrate that RIC8 co-localizes with its interaction partners Gαi1/2:GDP and LGN in meiotic/mitotic spindle, cell cortex and polar bodies of maturing oocytes and zygotes. Downregulation of Ric8 by siRNA leads to interferred translocation of Gαi1/2 to cortical region of maturing oocytes and reduction of its levels. RIC8 is also expressed at high level in female reproductive organs e.g. oviduct. Therefore we suggest a regulatory function for RIC8 in mammalian gametogenesis and fertility.

Deletion of RIC8A in neural precursor cells leads to altered neurogenesis and neonatal lethality of mouse.

RIC8A is a noncanonical guanine nucleotide exchange factor for a subset of Gα subunits. RIC8A has been reported in different model organisms to participate in the control of mitotic cell division, cell signalling, development and cell migration. Still, the function of RIC8A in the mammalian nervous system has not been sufficiently analysed yet. Adult mice express RIC8A in the brain regions involved in the regulation of memory and emotional behaviour. To elucidate the role of RIC8A in mammalian neurogenesis we have inactivated Ric8a in neural precursor cells using Cre/Lox system. As a result, the conditional knockout mice were born at expected Mendelian ratio, but died or were cannibalized by their mother within 12 h after birth. The cerebral cortex of the newborn Nes;Ric8a(CKO) mice was thinner compared to littermates and the basement membrane was discontinuous, enabling migrating neurons to invade to the marginal zone. In addition, the balance between the planar and oblique cell divisions was altered, influencing the neuron production. Taken together, RIC8A has an essential role in the development of mammalian nervous system by maintaining the integrity of pial basement membrane and modulating cell division.

Ablation of RIC8A function in mouse neurons leads to a severe neuromuscular phenotype and postnatal death.

Resistance to inhibitors of cholinesterase 8 (RIC8) is a guanine nucleotide exchange factor required for the intracellular regulation of G protein signalling. RIC8 activates different Gα subunits via non-canonical pathway, thereby amplifying and prolonging the G protein mediated signal. In order to circumvent the embryonic lethality associated with the absence of RIC8A and to study its role in the nervous system, we constructed Ric8a conditional knockout mice using Cre/loxP technology. Introduction of a synapsin I promoter driven Cre transgenic mouse strain (SynCre) into the floxed Ric8a (Ric8a (F/F) ) background ablated RIC8A function in most differentiated neuron populations. Mutant SynCre (+/-) Ric8 (lacZ/F) mice were born at expected Mendelian ratio, but they died in early postnatal age (P4-P6). The mutants exhibited major developmental defects, like growth retardation and muscular weakness, impaired coordination and balance, muscular spasms and abnormal heart beat. Histological analysis revealed that the deficiency of RIC8A in neurons caused skeletal muscle atrophy and heart muscle hypoplasia, in addition, the sinoatrial node was misplaced and its size reduced. However, we did not observe gross morphological changes in brains of SynCre (+/-) Ric8a (lacZ/F) mutants. Our results demonstrate that in mice the activity of RIC8A in neurons is essential for survival and its deficiency causes a severe neuromuscular phenotype.