Enhancing clinical utility: deep learning-based embryo scoring model for non-invasive aneuploidy prediction.

BACKGROUND: The best method for selecting embryos ploidy is preimplantation genetic testing for aneuploidies (PGT-A). However, it takes more labour, money, and experience. As such, more approachable, non- invasive techniques were still needed. Analyses driven by artificial intelligence have been presented recently to automate and objectify picture assessments. METHODS: In present retrospective study, a total of 3448 biopsied blastocysts from 979 Time-lapse (TL)-PGT cycles were retrospectively analyzed. The "intelligent data analysis (iDA) Score" as a deep learning algorithm was used in TL incubators and assigned each blastocyst with a score between 1.0 and 9.9. RESULTS: Significant differences were observed in iDAScore among blastocysts with different ploidy. Additionally, multivariate logistic regression analysis showed that higher scores were significantly correlated with euploidy (p < 0.001). The Area Under the Curve (AUC) of iDAScore alone for predicting euploidy embryo is 0.612, but rose to 0.688 by adding clinical and embryonic characteristics. CONCLUSIONS: This study provided additional information to strengthen the clinical applicability of iDAScore. This may provide a non-invasive and inexpensive alternative for patients who have no available blastocyst for biopsy or who are economically disadvantaged. However, the accuracy of embryo ploidy is still dependent on the results of next-generation sequencing technology (NGS) analysis.

Multiple collapses of blastocysts after full blastocyst formation is an independent risk factor for aneuploidy - a study based on AI and manual validation.

BACKGROUND: The occurrence of blastocyst collapse may become an indicator of preimplantation embryo quality assessment. It has been reported that collapsing blastocysts can lead to higher rates of aneuploidy and poorer clinical outcomes, but more large-scale studies are needed to explore this relationship. This study explored the characteristics of blastocyst collapse identified and quantified by artificial intelligence and explored the associations between blastocyst collapse and embryo ploidy, morphological quality, and clinical outcomes. METHODS: This observational study included data from 3288 biopsied blastocysts in 1071 time-lapse preimplantation genetic testing cycles performed between January 2019 and February 2023 at a single academic fertility center. All transferred blastocysts are euploid blastocysts. The artificial intelligence recognized blastocyst collapse in time-lapse microscopy videos and then registered the collapsing times, and the start time, the recovery duration, the shrinkage percentage of each collapse. The effects of blastocyst collapse and embryo ploidy, pregnancy, live birth, miscarriage, and embryo quality were studied using available data from 1196 euploid embryos and 1300 aneuploid embryos. RESULTS: 5.6% of blastocysts collapsed at least once only before the full blastocyst formation (tB), 19.4% collapsed at least once only after tB, and 3.1% collapsed both before and after tB. Multiple collapses of blastocysts after tB (times ≥ 2) are associated with higher aneuploid rates (54.6%, P > 0.05; 70.5%, P < 0.001; 72.5%, P = 0.004; and 71.4%, P = 0.049 in blastocysts collapsed 1, 2, 3 or ≥ 4 times), which remained significant after adjustment for confounders (OR = 2.597, 95% CI 1.464-4.607, P = 0.001). Analysis of the aneuploid embryos showed a higher ratio of collapses and multiple collapses after tB in monosomies and embryos with subchromosomal deletion of segmental nature (P < 0.001). Blastocyst collapse was associated with delayed embryonic development and declined blastocyst quality. There is no significant difference in pregnancy and live birth rates between collapsing and non-collapsing blastocysts. CONCLUSIONS: Blastocyst collapse is common during blastocyst development. This study underlined that multiple blastocyst collapses after tB may be an independent risk factor for aneuploidy which should be taken into account by clinicians and embryologists when selecting blastocysts for transfer.

How to identify patients who would benefit from delayed-matured oocytes insemination: a sibling oocyte and ploidy outcome study.

STUDY QUESTION: Which patients might benefit from insemination of delayed-matured oocytes? SUMMARY ANSWER: Delayed-matured oocytes had a ≥50% contribution to the available cohort of biopsied blastocysts in patients with advanced maternal age, low maturation, and/or low fertilization rates. WHAT IS KNOWN ALREADY: Retrieved immature oocytes that progress to the MII stage in vitro could increase the number of embryos available during ICSI cycles. However, these delayed-matured oocytes are associated with lower fertilization rates and compromised embryo quality. Data on the ploidy of these embryos are controversial, but studies failed to compare euploidy rates of embryos derived from delayed-matured oocytes to patients' own immediate mature sibling oocytes. This strategy efficiently allows to identify the patient population that would benefit from this approach. STUDY DESIGN, SIZE, DURATION: This observational study was performed between January 2019 and June 2021 including a total of 5449 cumulus oocytes complexes from 469 ovarian stimulation cycles, from which 3455 inseminated matured oocytes from ICSI (n = 2911) and IVF (n = 544) were considered as the sibling controls (MII-D0) to the delayed-matured oocytes (MII-D1) (n = 910). Euploidy rates were assessed between delayed-matured (MII-D1) and mature sibling oocytes (MII-D0) in relation to patients' clinical characteristics such as BMI, AMH, age, sperm origin, and the laboratory outcomes, maturation, fertilization, and blastocyst utilization rates. PARTICIPANTS/MATERIALS, SETTING, METHODS: A total of 390 patients undergoing IVF/ICSI, who had at least one metaphase I (MI) or germinal-vesicle (GV) oocyte on the day of oocyte collection (Day 0), which matured in 20-28 h after denudation were included. MI and GV oocytes that matured overnight were inseminated on the following day (Day 1, MII-D1) by ICSI. Only cycles planned for preimplantation genetic testing for aneuploidy using fresh own oocytes were included. MAIN RESULTS AND THE ROLE OF CHANCE: Fertilization (FR) and blastocyst utilization rates were significantly higher for MII-D0 compared to delayed-matured oocytes (MII-D1) (69.5% versus 55.9%, P < 0.001; and 59.5% versus 18.5%, P < 0.001, respectively). However, no significant difference was observed in the rate of euploid embryos between MII-D0 and MII-D1 (46.3% versus 39.0%, P = 0.163). For evaluation of the benefit of inseminating MI/GV oocytes on D1 per cycle in relation to the total number of biopsied embryos, cycles were split into three groups based on the proportion of MII-D1 embryos that were biopsied in that cycle (0%, 1-50%, and ≥50%). The results demonstrate that patients who had ≥50% contribution of delayed-matured oocytes to the available cohort of biopsied embryos were those of advanced maternal age (mean age 37.7 years), <10 oocytes retrieved presenting <34% maturation rate, and <60% fertilization rate. Every MII oocyte injected next day significantly increased the chances of obtaining a euploid embryo [odds ratio (OR) = 1.83, CI: 1.50-2.24, P < 0.001] among MII-D1. The odds of enhanced euploidy were slightly higher among the MII-D1-GV matured group (OR = 1.78, CI: 1.42-2.22, P < 0.001) than the MII-D1-MI matured group (OR = 1.54, CI: 1.25-1.89, P < 0.001). Inseminating at least eight MII-D1 would have >50% probability of getting a euploid embryo among the MII-D1 group. LIMITATIONS, REASONS FOR CAUTION: ICSI of MII-D1 was performed with the fresh or frozen ejaculates or testicular samples from the previous day. The exact timing of polar body extrusion of delayed-matured MI/GV was not identified. Furthermore, the time point of the final oocyte maturation to MII for the immature oocytes and for the oocytes inseminated by IVF could not be identified. WIDER IMPLICATIONS OF THE FINDINGS: The results of this study might provide guidance to the IVF laboratories for targeting the patient's population who would benefit from MII-D1 ICSI without adhering to unnecessary costs and workload. STUDY FUNDING/COMPETING INTEREST(S): No external funding was received for this study. There are no conflicts of interest to be declared for any of the authors. There are no patents, products in development, or marketed products to declare. TRIAL REGISTRATION NUMBER: N/A.

Conventional IVF is feasible in preimplantation genetic testing for aneuploidy.

PURPOSE: To investigate the feasibility of the application of conventional in vitro fertilization (cIVF) for couples undergoing preimplantation genetic testing for aneuploidies (PGT-A) with non-male factor infertility. METHODS: To evaluate the efficiency of sperm whole-genome amplification (WGA), spermatozoa were subjected to three WGA protocols: Picoplex, ChromInst, and multiple displacement amplification (MDA). In the clinical studies, 641 couples who underwent PGT-A treatment for frozen embryos between January 2016 and December 2021 were included to retrospectively compare the chromosomal and clinical outcomes of cIVF and intracytoplasmic sperm injection (ICSI). Twenty-six couples were prospectively recruited for cIVF and PGT-A treatment between April 2021 and April 2022; parental contamination was analyzed in biopsied samples; and 12 aneuploid embryos were donated to validate the PGT-A results. RESULTS: Sperm DNA failed to amplify under Picoplex and ChromInst conditions but could be amplified using MDA. In frozen PGT-A cycles, no significant differences in the average rates of euploid, mosaic, and aneuploid embryos per cycle between the cIVF-PGT-A and ICSI-PGT-A groups were observed. The results of the prospective study that recruited couples for cIVF-PGT-A treatment showed no paternal contamination and one case of maternal contamination in 150 biopsied trophectoderm samples. Among the 12 donated embryos with whole-chromosome aneuploidy, 11 (91.7%) presented uniform chromosomal aberrations, which were in agreement with the original biopsy results. CONCLUSIONS: Under the Picoplex and ChromInst WGA protocols, the risk of parental contamination in the cIVF-PGT-A cycles was low. Therefore, applying cIVF to couples with non-male factor infertility who are undergoing PGT-A is feasible.

Embryo ploidy in vitrified versus fresh oocytes: Is there a difference?

PURPOSE: To evaluate embryo ploidy in a cohort of patients who underwent preimplantation genetic testing for aneuploidy (PGT-A) with vitrified oocytes compared to fresh oocytes. METHODS: Patients who underwent their first autologous oocyte vitrification and warming followed by in vitro fertilization (IVF) and trophectoderm biopsy for PGT-A between 1/1/2017 and 12/31/2021 at a single academic institution were included. Patients were compared 1:3 to age-matched controls who underwent their first IVF cycle with fresh oocytes and subsequent trophectoderm biopsy for PGT-A. The primary outcome was the proportions of euploid, mosaic, and aneuploid embryos between those using vitrified versus fresh oocytes. RESULTS: 117 patients who cryopreserved a total of 1,272 mature oocytes were included in the study and were matched with 351 controls using fresh oocytes. The average age was 36.9 ± 2.6 years, and the median interval between oocyte vitrification and warming was 38 months. There were similar numbers of mature oocytes (10.9 ± 4.9 vs. 11.1 ± 6.3, P = .67), fertilized oocytes (7.8 ± 4.0 vs. 8.7 ± 5.5, P = .10), and blastocysts per patient (5.1 ± 3.1 vs. 5.8 ± 4.3, P = .10) between those using vitrified versus fresh oocytes. In terms of embryo ploidy results, there were no statistically significant differences in rates of euploidy (40.1% vs. 41.6%), mosaicism (15.7% vs. 12.0%), or aneuploidy (44.3% vs. 46.4%) (P = .06) between the two groups. CONCLUSIONS: Oocyte vitrification with subsequent warming, fertilization, and trophectoderm biopsy for PGT-A was not associated with adverse chromosomal competence when compared to age-matched controls utilizing fresh oocytes.

The use of voting ensembles to improve the accuracy of deep neural networks as a non-invasive method to predict embryo ploidy status.

PURPOSE: To determine if creating voting ensembles combining convolutional neural networks (CNN), support vector machine (SVM), and multi-layer neural networks (NN) alongside clinical parameters improves the accuracy of artificial intelligence (AI) as a non-invasive method for predicting aneuploidy. METHODS: A cohort of 699 day 5 PGT-A tested blastocysts was used to train, validate, and test a CNN to classify embryos as euploid/aneuploid. All embryos were analyzed using a modified FAST-SeqS next-generation sequencing method. Patient characteristics such as maternal age, AMH level, paternal sperm quality, and total number of normally fertilized (2PN) embryos were processed using SVM and NN. To improve model performance, we created voting ensembles using CNN, SVM, and NN to combine our imaging data with clinical parameter variations. Statistical significance was evaluated with a one-sample t-test with 2 degrees of freedom. RESULTS: When assessing blastocyst images alone, the CNN test accuracy was 61.2% (± 1.32% SEM, n = 3 models) in correctly classifying euploid/aneuploid embryos (n = 140 embryos). When the best CNN model was assessed as a voting ensemble, the test accuracy improved to 65.0% (AMH; p = 0.1), 66.4% (maternal age; p = 0.06), 65.7% (maternal age, AMH; p = 0.08), 66.4% (maternal age, AMH, number of 2PNs; p = 0.06), and 71.4% (maternal age, AMH, number of 2PNs, sperm quality; p = 0.02) (n = 140 embryos). CONCLUSIONS: By combining CNNs with patient characteristics, voting ensembles can be created to improve the accuracy of classifying embryos as euploid/aneuploid from CNN alone, allowing for AI to serve as a potential non-invasive method to aid in karyotype screening and selection of embryos.

Impact of inactivated SARS-CoV-2 vaccination on embryo ploidy: a retrospective cohort study of 133 PGT-A cycles in China.

BACKGROUND: Unsubstantiated concerns have been raised on the potential correlation between severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccination and infertility, leading to vaccine hesitancy in reproductive-aged population. Herein, we aim to evaluate the impact of inactivated SARS-CoV-2 vaccination on embryo ploidy, which is a critical indicator for embryo quality and pregnancy chance. METHODS: This was a retrospective cohort study of 133 patients who underwent preimplantation genetic testing for aneuploidy (PGT-A) cycles with next-generation sequencing technology from June 1st 2021 to March 17th 2022 at a tertiary-care medical center in China. Women fully vaccinated with two doses of Sinopharm or Sinovac inactivated vaccines (n = 66) were compared with unvaccinated women (n = 67). The primary outcome was the euploidy rate per cycle. Multivariate linear and logistic regression analyses were performed to adjust for potential confounders. RESULTS: The euploidy rate was similar between vaccinated and unvaccinated groups (23.2 ± 24.6% vs. 22.6 ± 25.9%, P = 0.768), with an adjusted ß of 0.01 (95% confidence interval [CI]: -0.08-0.10). After frozen-thawed single euploid blastocyst transfer, the two groups were also comparable in clinical pregnancy rate (75.0% vs. 60.0%, P = 0.289), with an adjusted odds ratio of 6.21 (95% CI: 0.76-50.88). No significant associations were observed between vaccination and cycle characteristics or other laboratory and pregnancy outcomes. CONCLUSIONS: Inactivated SARS-CoV-2 vaccination had no detrimental impact on embryo ploidy during in vitro fertilization treatment. Our finding provides further reassurance for vaccinated women who are planning to conceive. Future prospective cohort studies with larger datasets and longer follow-up are needed to confirm the conclusion.

Pronuclear and blastocyst morphology are associated age-dependently with embryo ploidy in in vitro fertilization cycles.

This retrospective study aimed to assess the relationship between standard markers of embryo morphology, maternal age and blastocyst ploidy determined by trophectoderm (TE) biopsy and Next-generation Sequencing (NGS). A total of 774 oocytes and embryos from 288 PGT-A cycles were scored for pronuclear, cleavage stage and blastocyst morphology. Pronuclear oocytes aligned between the nuclei and presenting equal number of nucleolus precursor bodies (NPBs) were designated Z1, oocytes showing equal number of NPBs, but not aligned, as Z2 while Z3 oocytes had an unequal number of NBPs between the nuclei or NPBs aligned in one nucleus and non-aligned in the other. Pronuclear oocytes with unequal-sized or non-aligned nuclei were designated Z4. Blastocysts were graded as BL1 (AA, AB or BA), BL2 (BB or CB) and BL3 (BC or CC) based on the combination of inner cell mass (ICM) and TE scores. Pronuclear and blastocyst morphology were correlated with aneuploidy in a < 40-year-old group (p < 0.01 and p < 0.05, respectively), but not in those ≥40 years. Interestingly, BL3 blastocysts classified as Z1 or Z3-Z4 on day-1 had different aneuploidy rates (BL3/Z1 = 46.7% vs. BL3/Z3-Z4 = 90.0%, p < 0.05). In summary, our data showed that pronuclear and blastocyst morphology are associated with blastocyst ploidy in younger patients. This may help embryo selection for embryo transfer and decision-making on which blastocysts should be biopsied in PGT-A cycles.

Impact of inactivated SARS-CoV-2 vaccination on embryo ploidy: a retrospective cohort study of 133 PGT-A cycles in China

BACKGROUND: Unsubstantiated concerns have been raised on the potential correlation between severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccination and infertility, leading to vaccine hesitancy in reproductive-aged population. Herein, we aim to evaluate the impact of inactivated SARS-CoV-2 vaccination on embryo ploidy, which is a critical indicator for embryo quality and pregnancy chance. METHODS: This was a retrospective cohort study of 133 patients who underwent preimplantation genetic testing for aneuploidy (PGT-A) cycles with next-generation sequencing technology from June 1st 2021 to March 17th 2022 at a tertiary-care medical center in China. Women fully vaccinated with two doses of Sinopharm or Sinovac inactivated vaccines (n = 66) were compared with unvaccinated women (n = 67). The primary outcome was the euploidy rate per cycle. Multivariate linear and logistic regression analyses were performed to adjust for potential confounders. RESULTS: The euploidy rate was similar between vaccinated and unvaccinated groups (23.2 ± 24.6% vs. 22.6 ± 25.9%, P = 0.768), with an adjusted ß of 0.01 (95% confidence interval [CI]: -0.08-0.10). After frozen-thawed single euploid blastocyst transfer, the two groups were also comparable in clinical pregnancy rate (75.0% vs. 60.0%, P = 0.289), with an adjusted odds ratio of 6.21 (95% CI: 0.76-50.88). No significant associations were observed between vaccination and cycle characteristics or other laboratory and pregnancy outcomes. CONCLUSIONS: Inactivated SARS-CoV-2 vaccination had no detrimental impact on embryo ploidy during in vitro fertilization treatment. Our finding provides further reassurance for vaccinated women who are planning to conceive. Future prospective cohort studies with larger datasets and longer follow-up are needed to confirm the conclusion.