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.

Intrauterine Infusion and Hysteroscopic Injection of Autologous Platelet-Rich Plasma for Patients with a Persistent Thin Endometrium: A Prospective Case-Control Study.

Objectives: To evaluate the effect of intrauterine infusion and hysteroscopic injection of autologous platelet-rich plasma (PRP) in patients with a persistent thin endometrium (EM) undergoing euploid frozen embryo transfer (EFET) cycles. Methods: This prospective case-control study enrolled 116 infertile women with thin EM (<7 mm) who underwent hormone replacement therapy (HRT) for EFET. These women had experienced at least one previous unsuccessful EFET cycle, which either resulted in the cancellation of the cycle or failure of pregnancy. A total of 55 women received an intrauterine infusion of PRP before FET, 38 received a hysteroscopic injection of PRP, and 23 received standard HRT treatment without PRP (control group). Only euploid embryos were transferred in these cycles. The primary outcomes were the implantation rate (IR) and clinical pregnancy rate (CPR) after EFET. Results: After receiving intrauterine infusion and hysteroscopic injection of PRP, 78.2% and 55.3% of patients, respectively, showed an EM thickness exceeding 7 mm, followed by embryo transfer. The hysteroscopic injection group demonstrated significantly higher IR (52%), a higher trend of CPR (52%), and a higher live birth rate (38%) than the control group (18%, 22%, and 4%). Conclusions: Intrauterine infusion and hysteroscopic injection of autologous PRP may be effective methods to increase EM thickness in HRT cycles. According to our results, both methods could increase EM thickness, while hysteroscopic injection appeared to provide more significant assistance in increasing IR, CPR, and live birth rate after EFET in patients with persistent thin EM.

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.

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.

Innovative technology for evaluation of sperm DNA double-strand breaks diagnoses male factor infertility and prevents reproductive failures.

Neutral comet assay has been available for two decades to evaluate sperm double-strand breaks (DSBs). However, its clinical usability is limited due to its complex and time-consuming procedure, as well as the lack of a standardized scoring system. The aim of this study was to: develop a rapid diagnostic method for DSBs, Sperm DNA Fragmentation Releasing Assay (SDFR), and explore the association between DSBs and reproductive outcomes. We pioneered the use of polyacrylamide (PA) for embedding sperm chromatin and optimized the porosity of PA to be between 10 and 13%. The refined PA network allowed the trapping of DSBs, which dispersed halo on an immunological slide; in contrast, intact chromatin failed to develop a halo. A strong correlation was showed between reproducible values obtained from SDFR and neutral comet assay. SDFR were responsive to dose-/time-dependent simulated DSBs, indicating high sensitivity and specificity. Furthermore, we conducted a retrospective study of couples with embryonic aneuploidy screening, and recording DSB profiles of the male partners. Our findings revealed that DSB enabled to predict embryonic aneuploidy whereas basic semen parameters did not. In conclusion, SDFR offers a rapid and user-friendly approach for evaluating DSBs, with potential implications for predictive healthcare in reproductive medicine.

Factors Affecting the Potential Efficacy of Intrauterine Platelet-Rich Plasma Infusion on Thin Endometrium in Women with Recurrent Implantation Failure.

Optimizing endometrial thickness (EMT) is crucial for successful embryo implantation, but enhancing thin endometrium remains a significant challenge. Platelet-rich plasma (PRP)-derived therapies have emerged as a promising approach in reproductive medicine due to their capacity to facilitate tissue repair and regeneration. This study aims to identify the risk factors associated with the failure of intrauterine PRP infusion for thin endometrium in women with recurrent implantation failure (RIF). We retrospectively reviewed data from 77 women with RIF, all exhibiting an EMT of <7 mm. These women underwent programmed hormone therapy for frozen embryo transfer (FET) and received two autologous intrauterine PRP infusions. Following intrauterine PRP-lysate (PL) infusions, the mean increase in EMT was 1.9 ± 1.2 mm, with EMT reaching 7 mm in 86% of the cases (66/77; average EMT, 8.3 mm). We identified an exceedingly thin EMT as a risk factor impacting the therapeutic efficacy in increasing EMT (p = 0.04, OR: 3.16; 95% CI: 1.03-9.67). Additionally, the number of previous uterine surgeries emerged as a prognostic factor for pregnancy failure following PL infusion (p = 0.02, OR: 2.02; 95% CI: 1.12-3.64). Our findings suggest that an extremely thin EMT and a history of numerous uterine surgeries can impede successful pregnancy, even when an optimal EMT is achieved following PRP infusion.

SUMO1 and Defective Spermatozoa Correlate with Endogenous Hydrogen Peroxide and Live Birth Outcome in Intrauterine Insemination Cycles for Unexplained Infertility.

This study aimed to investigate the correlation between hydrogen peroxide (H2O2), small ubiquitin-like modifier molecules (SUMO), and pregnancy outcomes in couples with unexplained infertility (UI) undergoing intrauterine insemination (IUI) treatment. We prospectively collected semen samples from 56 couples with UI and divided the spermatozoa into motile and immotile fractions by density gradient centrifugation (DSC). Immunofluorescence staining was used to examine the immunostaining and localization of nuclear pore complex (NPC), SUMO1, and SUMO2/3 in spermatozoa. We detected H2O2 levels by chemiluminescence methods. We found that H2O2 levels correlated with NPC (neck) (r = 0.400) and NPC (tail) (r = 0.473) in motile sperm fractions. In immotile fractions, H2O2 positively correlated with NPC (tail) (r = 0.431) and SUMO1 (neck) (r = 0.282). Furthermore, the positive NPC (tail) group had a significantly lower live birth rate than the negative NPC group (17.9% = 5/28 vs. 42.9% = 12/28). In conclusion, H2O2 positively correlated with SUMO1 (neck) and NPC (tail) in human spermatozoa. The DSC may partially eliminate defective spermatozoa (positive NPC staining); however, if defective spermatozoa remain in the motile fraction, this scenario is associated with a low live birth rate following IUI treatment.

Increased incidence of live births in implanted day 5 versus day 6 blastocysts following single embryo transfers with PGT-A.

Elective single-embryo transfers of euploid or low-level mosaic blastocysts were analyzed in this retrospective study to determine the correlations of live birth (LB) probability with embryonic developmental features of implanted day 5 (D5, n = 245) or day 6 (D6, n = 73) blastocysts using time-lapse (TL) monitoring. According to the logistic regression analyses (adjusted odds ratio [OR] = 0.341, 95% confidence interval [CI] = 0.169-0.685, P < 0.05), the LB probability was negatively associated with the D6 group. The LB rate of the D5 group was higher than the D6 group (88.2% vs. 75.3%; P < 0.05). Compared with the D5 blastocysts, the D6 blastocysts exhibited comparable dysmorphisms except for the multinucleation at the 4-cell stage (10.9% vs. 2.9%, P < 0.05). Moreover, D6 blastocysts had considerably slower developmental kinetics and poorer blastocyst morphologies. Further analysis confirmed that the LB rate was not associated with developmental kinetics or dysmorphisms but rather with blastocyst morphology (inner cell mass [ICM] grade ≤ C vs. ICM grade A, adjusted OR = 0.155, 95% CI = 0.04-0.596, P < 0.05; trophectoderm [TE] grade ≤ C vs. TE grade A, adjusted OR = 0.157, 95% CI = 0.032-0.760, P < 0.05). In conclusion, D6 implanted blastocysts have a considerably lower LB rate than D5 implanted blastocysts. As determined by TL monitoring, the diminished blastocyst morphology can be one of the primary reasons underlying the decreased likelihood of LB.

Live motile sperm sorting device for enhanced sperm-fertilization competency: comparative analysis with density-gradient centrifugation and microfluidic sperm sorting.

PURPOSE: A live motile sperm sorting device (LensHooke® CA0) developed to prevent the deleterious effects of centrifugation was evaluated comparatively with conventional density-gradient centrifugation (DGC) and microfluidic-based device (Zymot) in sperm selection. METHODS: Semen samples from 239 men were collected. CA0 under different incubation intervals (5, 10, 30, and 60 min) and temperatures (20, 25, and 37℃) was conducted. The sperm quality in CA0-, DGC-, and Zymot-processed samples was then comparatively evaluated. Semen parameters included concentration, motility, morphology, motion kinematics, DNA fragmentation index (DFI), and the rate of acrosome-reacted sperm (AR). RESULTS: Total motility and motile sperm concentration increased in a time- and temperature-dependent manner and the total motility peaked for 30 min at 37℃. In paired analysis, CA0 showed significantly higher total motility (94.0%), progressive motility (90.8%), rapid progressive motility (83.6%), normal morphology (10.3%), and lower DFI (2.4%) and AR (4.7%) than the other two methods in normozoospermic samples (all p < 0.05). For non-normozoospermic samples, CA0 had significantly better results than the other two methods (total motility 89.2%, progressive motility 80.4%, rapid progressive motility 74.2%, normal morphology 8.5%, DFI 4.0%, and AR 4.0%; all p < 0.05). CONCLUSION: CA0 yielded spermatozoa with enhanced sperm fertilization potentials; DFI was minimized in samples processed by CA0. CA0 was effective for both normal and abnormal semen samples due to its consistent selection efficiency.

Development and integration of LensHooke® R10 for automatic and standardized diagnosis for sperm DNA fragmentation.

BACKGROUND: The sperm chromatin dispersion assay is commonly used to assess sperm DNA integrity. This approach is time-consuming, demonstrates poor chromatin preservation, and provides an ambiguous and unstandardized evaluation of fragmented chromatin. OBJECTIVES: We aimed to (i) develop an optimized sperm chromatin dispersion assay with reduced operation time, (ii) validate R10 test accuracy by comparing it to a conventional sperm chromatin dispersion assay, and (iii) standardize the sperm DNA fragmentation analysis procedure by integrating artificial intelligence optical microscopic technology. MATERIALS AND METHODS: This cross-section study included 620 semen samples. Aliquots were analyzed by a conventional Halosperm® G2 assay (G2) and LensHooke® R10 assay (R10). The DNA fragmentation index was scored manually, and R10 slides were automatically determined by a LensHooke® X12 PRO semen analysis system (X12). RESULTS: We demonstrated significant improvements in total assay time (40 vs. 72 min, p < 0.001) and in the halo-cytological resolution using R10 compared to G2. Comparing the G2 and R10, DNA fragmentation index results demonstrated good agreement between the two methods (Spearman's rank correlation, rho = 0.8517, p < 0.0001). We introduced the integration of an auto-calculation system to diagnose sperm DNA fragmentation. X12 interpretation showed excellent agreement with manual interpretation (Spearman's rank correlation, rho = 0.9323, p < 0.0001), but had a low coefficient of variation compared to manual interpretation (4% for R10 by X12 vs. 19% for R10 by manual scoring vs. 25% for G2 by manual scoring). DNA fragmentation index was more correlated with total motility (coefficients = -0.3607, p < 0.0001) than sperm morphology and was positively associated with asthenozoospermic semen samples (p = 0.0001). CONCLUSION: The R10 sperm chromatin dispersion assay combined with the X12 semen analysis system is faster, more objective, and provides standardization for sperm DNA fragmentation.

Biphasic oxygen tension promotes the formation of transferable blastocysts in patients without euploid embryos in previous monophasic oxygen cycles.

This study evaluated whether the concentration of biphasic O2 (5-2%) promotes the formation of qualified blastocysts (QBs) and euploid blastocysts and the probability of cycles with transferable blastocysts. The paired experimental design included a total 90 patients (180 cycles) without euploid blastocysts in previous monophasic O2 (5%) cycles were enrolled for an additional cycle of biphasic O2 (5-2%). In the biphasic O2 (5-2%) group, the QB rate (35.8%, 225/628) was significantly higher than that in the monophasic O2 (5%) group (23.5%, 137/582; p < 0.001). In addition, the euploid blastocyst number (0.5 ± 0.8) and the percentage of cycles with transferable blastocysts were significantly higher in the biphasic O2 (5-2%) group (57.8%, 52/90) than those in the monophasic O2 (5%) group (0 and 35.6%, 32/90, respectively; p < 0.01). Multivariable regression analysis also indicated that the QB rate and the probability of cycles with transferable blastocysts correlated with O2 tension (OR 1.535, 95% CI 1.325-1.777, and OR 3.191, 95% CI 1.638-5.679, respectively; p < 0.001). Biphasic O2 culture can be used as an alternative strategy to increase the euploid QBs and the probability of cycles with transferable blastocysts in patients with a poor prognosis.

Association between Leukemia Inhibitory Factor Gene Polymorphism and Clinical Outcomes among Young Women with Poor Ovarian Response to Assisted Reproductive Technology.

BACKGROUND: Does the presence of single-nucleotide polymorphisms (SNPs) in the leukemia inhibitory factor (LIF) gene affect ovarian response in infertile young women? METHODS: This was a case-control study recruiting 1744 infertile women between January 2014 to December 2015. The 1084 eligible patients were stratified into four groups using the POSEIDON criteria. The gonadotropin-releasing hormone receptor (GnRHR), follicle-stimulating hormone receptor (FSHR), anti-Müllerian hormone (AMH), and LIF SNP genotypes were compared among the groups. The distributions of LIF and FSHR among younger and older patients were compared. Clinical outcomes were also compared. RESULTS: The four groups of poor responders had different distributions of SNP in LIF. The prevalence of LIF genotypes among young poor ovarian responders differed from those of normal responders. Genetic model analyses in infertile young women revealed that the TG or GG genotype in the LIF resulted in fewer oocytes retrieved and fewer mature oocytes relative to the TT genotypes. In older women, the FSHR SNP genotype contributed to fewer numbers of mature oocytes. CONCLUSIONS: LIF and FSHR SNP genotypes were associated with a statistically significant reduction in ovarian response to controlled ovarian hyperstimulation in younger and older women with an adequate ovarian reserve, respectively.

Investigation of the deformation behavior and mechanical characteristics of polycrystalline chromium-nickel alloys using molecular dynamics.

In this study, the mechanical properties and plastic deformation responses of nanocrystalline Cr-Ni alloy were investigated via tensile tests by molecular dynamics (MD) simulation. The effect of various compositions, various grain sizes (GSs) from 4.7 to 11.0 nm, and various temperatures from 300 to 1500 K is analyzed. The results indicate that the yield strength of the polycrystalline Cr-Ni alloy decreases as decreasing GS, which shows the inverse Hall-Petch relation in the metal softening as reducing GS.  Young's modulus (E) increases in the order of the increasing GSs and single crystalline. E rises as raising the percent of Ni from 5 to 15% and then decreases as increasing %Ni to 20%. Besides, E is the linear decrease function with increasing temperature. The maximum stress decreases as increasing temperature and increasing %Ni from 5 to 15%. But that decreases as increasing %Ni from 15 to 20%. The maximum stress value of single crystalline is smaller than that of polycrystalline. The high shear strain zones depend on the GS and alloy composition. The shear strain zones focus on the grain boundary at a low temperature and disperse over the entire specimen when the specimen works at a high temperature. The reason is that the grain boundary helps release stresses to prolong the plastic deformation period to prevent rapid specimen destruction.

Isolable fluorinated triphenylmethyl cation salts of [HCB11Cl11]-: demonstration of remarkable hydride affinity.

Significantly fluorinated triarylmethyl cations have long attracted attention as potentially accessible highly reactive carbocations, but their isolation in a convenient form has proved elusive. We show that abstraction of chloride with a cationic silylium reagent leads to the facile formation of di-, tetra-, and hexafluorinated trityl cations, which could be isolated as analytically pure salts with the [HCB11Cl11]- counterion and are compatible with (halo)arene solvents. The F6Tr+ cation carrying six meta-F substituents was computationally predicted to possess up to 20% higher hydride affinity than the parent triphenylmethyl cation Tr+. We report that indeed F6Tr+ displays reactivity unmatched by Tr+. F6Tr+ at ambient temperature abstracts hydrides from the C-H bonds in tetraethylsilane, mesitylene, methylcyclohexane, and catalyzes Friedel-Crafts alkylation of arenes with ethylene, while Tr+ does none of these.

Estimating the causal effect of embryo transfer day on clinical in vitro fertilization outcomes using propensity score matching.

BACKGROUND: For women undergoing in vitro fertilization (IVF), the clinical benefit of embryo transfer at the blastocyst stage (Day 5) versus cleavage stage (Day 3) remains controversial. The purpose of this study is to compare the implantation rate, clinical pregnancy rate and odds of live birth of Day 3 and Day 5 embryo transfer, and more importantly, to address the issue that patients were chosen to receive either transfer protocol due to their underlying clinical characteristics, i.e., confounding by indication. METHODS: We conducted a retrospective cohort study of 9,090 IVF cycles collected by Lee Women's Hospital in Taichung, Taiwan from 1998 to 2014. We utilized the method of propensity score matching to mimic a randomized controlled trial (RCT) where each patient with Day 5 transfer was matched by another patient with Day 3 transfer with respect to other clinical characteristics. Implantation rate, clinical pregnancy rate, and odds of live birth were compared for women underwent Day 5 transfer and Day 3 transfer to estimate the causal effects. We further investigated the causal effects in subgroups by stratifying age and anti-Mullerian hormone (AMH). RESULTS: Our analyses uncovered an evidence of a significant difference in implantation rate (p=0.04) favoring Day 5 transfer, and showed that Day 3 and Day 5 transfers made no difference in both odds of live birth (p=0.27) and clinical pregnancy rate (p=0.11). With the increase of gestational age, the trend toward non-significance of embryo transfer day in our result appeared to be consistent for subgroups stratified by age and AMH, while all analyses stratified by age and AMH were not statistically significant. CONCLUSIONS: We conclude that for women without strong indications for Day 3 or Day 5 transfer, there is a small significant difference in implantation rate in favor of Day 5 transfer. However, the two protocols have indistinguishable outcomes on odds of live birth and clinical pregnancy rate.

Association between GnRH Receptor Polymorphisms and Luteinizing Hormone Levels for Low Ovarian Reserve Infertile Women.

The choice of ovarian stimulation protocols in assisted reproduction technology (ART) cycles for low ovarian reserve patients is challenging. Our previous report indicated that the gonadotrophin-releasing (GnRH) agonist (GnRHa) protocol is better than the GnRH antagonist (GnRHant) protocol for young age poor responders. Here, we recruited 269 patients with anti-Müllerian hormone (AMH) < 1.2 ng/mL undergoing their first ART cycles for this nested case-control study. We investigated the genetic variants of the relevant genes, including follicular stimulating hormone receptor (FSHR; rs6166), AMH (rs10407022), GnRH (rs6185), and GnRH receptor (GnRHR; rs3756159) in patients <35 years (n = 86) and patients ≥35 years of age (n = 183). Only the genotype of GnRHR (rs3756159) is distributed differently in young (CC 39.5%, CT/TT 60.5%) versus advanced (CC 24.0%, CT/TT 76.0%) age groups (recessive model, p = 0.0091). Furthermore, the baseline luteinizing hormone (LH) levels (3.60 (2.45 to 5.40) vs. 4.40 (2.91 to 6.48)) are different between CC and CT/TT genotype of GnRHR (rs3756159). In conclusion, the genetic variants of GnRHR (rs3756159) could modulate the release of LH in the pituitary gland and might then affect the outcome of ovarian stimulation by GnRHant or GnRHa protocols for patients with low AMH levels.

End-to-end deep learning for recognition of ploidy status using time-lapse videos.

PURPOSE: Our retrospective study is to investigate an end-to-end deep learning model in identifying ploidy status through raw time-lapse video. METHODS: By randomly dividing the dataset of time-lapse videos with known outcome of preimplantation genetic testing for aneuploidy (PGT-A), a deep learning model on raw videos was trained by the 80% dataset, and used to test the remaining 20%, by feeding time-lapse videos as input and the PGT-A prediction as output. The performance was measured by an average area under the curve (AUC) of the receiver operating characteristic curve. RESULT(S): With 690 sets of time-lapse video image, combined with PGT-A results, our deep learning model has achieved an AUC of 0.74 from the test dataset (138 videos), in discriminating between aneuploid embryos (group 1) and others (group 2, including euploid and mosaic embryos). CONCLUSION: Our model demonstrated a proof of concept and potential in recognizing the ploidy status of tested embryos. A larger scale and further optimization on the exclusion criteria would be included in our future investigation, as well as prospective approach.

Anisotropic crack propagation and self-healing mechanism of freestanding black phosphorus nanosheets.

In this study, an indentation simulation is employed to study the anisotropic crack propagation and re-forming mechanism of freestanding black phosphorus (FBP) nanosheets by molecular dynamics simulation. The results indicate that the size of the FBP nanosheet decides the crack direction as well as the von Mises stress concentration. It is found that crack directions are not influenced by temperature. With increasing specimen size, the crack propagation rate is nearly the same as at the first stage of crack formation, while in the later stage, cracking develops very quickly in larger specimens. Especially, small FBP nanosheets almost re-form in a short time at ambient temperature. However, after being destroyed, the larger specimen has no possibility of recovery. Besides, when increasing the number of layers of FBP, the energy stored by the top layer and the system undergoing deformation increases. In addition, the specimen with two fixed edges is less stable, leading to increased stress and decreased Young's modulus compared with the specimen with four fixed edges.

Blastocyst Morphology Based on Uniform Time-Point Assessments is Correlated With Mosaic Levels in Embryos.

Avoiding aneuploid embryo transfers has been shown to improve pregnancy outcomes in patients with implantation failure and pregnancy loss. This retrospective cohort study aims to analyze the correlation of time-lapse (TL)-based variables and numeric blastocyst morphological scores (TLBMSs) with different mosaic levels. In total, 918 biopsied blastocysts with time-lapse assessments at a uniform time-point were subjected to next-generation sequencing-based preimplantation genetic testing for aneuploidy. In consideration of patient- and cycle-related confounding factors, all redefined blastocyst morphology components of low-grade blastocysts, that is, expansion levels (odds ratio [OR] = 0.388, 95% confidence interval [CI] = 0.217-0.695; OR = 0.328, 95% CI = 0.181-0.596; OR = 0.343, 95% CI = 0.179-0.657), inner cell mass grades (OR = 0.563, 95% CI = 0.333-0.962; OR = 0.35, 95% CI = 0.211-0.58; OR = 0.497, 95% CI = 0.274-0.9), and trophectoderm grades (OR = 0.29, 95% CI = 0.178-0.473; OR = 0.242, 95% CI = 0.143-0.411; OR = 0.3, 95% CI = 0.162-0.554), were less correlated with mosaic levels ≤20%, <50%, and ≤80% as compared with those of top-grade blastocysts (p < 0.05). After converting blastocyst morphology grades into scores, high TLBMSs were associated with greater probabilities of mosaic levels ≤20% (OR = 1.326, 95% CI = 1.187-1.481), <50% (OR = 1.425, 95% CI = 1.262-1.608), and ≤80% (OR = 1.351, 95% CI = 1.186-1.539) (p < 0.001). The prediction abilities of TLBMSs were similar for mosaic levels ≤20% (AUC = 0.604, 95% CI = 0.565-0.642), <50% (AUC = 0.634, 95% CI = 0.598-0.671), and ≤80% (AUC = 0.617, 95% CI = 0.576-0.658). In conclusion, detailed evaluation with TL monitoring at the specific time window reveals that redefined blastocyst morphology components and converted numeric TLBMSs are significantly correlated with all of the threshold levels of mosaicism. However, the performance of TLBMSs to differentiate blastocysts with aberrant ploidy risk remains perfectible.

Hypertension Risk in Young Women With Polycystic Ovary Syndrome: A Nationwide Population-Based Cohort Study.

Objective: A number of publications have assessed the prevalence of hypertension in polycystic ovary syndrome (PCOS) patients with inconclusive results. Since in general populations the occurrence of hypertension is related to age and comorbidities, we investigated the incidence rate and hazard ratios (HRs) of hypertension between healthy subjects and young women with PCOS as well as comorbidities. Methods: We conducted a population-based retrospective cohort study by using the National Health Insurance Research Database in Taiwan. The cohort included women with the diagnosis of PCOS between 2000 and 2012. Those without PCOS were selected as the control group at a ratio of 4:1 by an age-matched systematic random-sampling method. Cox proportional hazard regression analysis was used to determine the effects of PCOS on the risks of developing hypertension. Stratification analysis was performed to elucidate the interaction among PCOS and the comorbidities, which affect the incidence of hypertension. Results: The PCOS cohort consisted of 20,652 patients with PCOS and the comparison cohort consisted of 82,608 matched patients without PCOS. There was no difference in the distribution of age between the PCOS cohort and the comparison cohort (29.1 ± 6.8 vs. 29.0 ± 6.5, p = 0.32). The incidence rates of hypertension were 7.85 and 4.23 per 1,000 person-years in the PCOS and comparison groups, respectively. A statistically significant higher risk of hypertension was found in the PCOS cohort (adjusted HR = 1.62, 95% confidence interval = 1.48-1.76) than in the comparison cohort. After a joint analysis of comorbidities, the adjusted HR of hypertension was 9.44 (95% confidence interval = 7.27-12.24) for PCOS patients with comorbidities of diabetes mellitus (DM) and hyperlipidemia compared with women with neither PCOS nor DM and hyperlipidemia. Conclusion: The risk of developing hypertension in young women with PCOS was higher than in controls in this cohort study. The comorbidities of DM and hyperlipidemia could interact with PCOS patients and further increase the risk of hypertension. An earlier screening for hypertension and comorbidities in patients with PCOS may be warranted, even in young women.