Search

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Are the morphokinetics of euploid blastocysts evaluated by a generally applicable algorithm associated with the clinical outcomes of single-embryo transfer (SET)? Time-lapse microscopy was used to compare morphokinetic variables between expanded blastocysts derived from preimplantation genetic testing for aneuploidy cycles using high-resolution next-generation sequencing (hr-NGS). The clinical efficacy of the morphokinetic algorithm KIDScore D5 was evaluated after euploid SET. Compared with euploid blastocysts, low-level mosaic blastocysts presented comparable morphokinetic and morphological features. However, high-level mosaic blastocysts exhibited significant delays in t5 (median 51.9 h post insemination (hpi), P = 0.034) (where t is the time for the embryo to reach the specific stage in hours after ICSI or conventional IVF) and t8 (median 58.6 hpi, P = 0.032) accompanied by a prolonged time period for the third cell cycle (median 14.7 h, P = 0.012). A significantly higher incidence (P = 0.011) of multinucleation indicated a susceptibility of high-level mosaic blastocysts to mitotic errors. Only a delay in the time for the embryo to reach the full blastocyst stage (median 106.0 hpi, P = 0.039) was revealed in aneuploid blastocysts, reflecting the reduced formation of good-quality blastocysts (42.6% versus 65.7%, P < 0.001). Euploid blastocysts with specific morphokinetic characteristics were graded using the KIDScore D5 algorithm. Grade C embryos achieved significantly lower rates of clinical pregnancy, implantation and ongoing pregnancy (25%, 25% and 10%, respectively) compared with the grade A (76.2%, 79.4% and 68.3%, respectively) or grade B (62.5%, 66.7% and 62.5%, respectively) embryos (P = 0.0171 to <0.0001). Although morphokinetic features appear dissimilar in embryos with different diploid–aneuploid mosaic levels, predicting chromosomal abnormalities using morphokinetics alone is still insufficient. When combined with hr-NGS, use of the generally applicable KIDScore D5 algorithm has the potential to discriminate euploid blastocysts with different developmental competence. [ABSTRACT FROM AUTHOR]

This retrospective analysis compared the efficiency of the gonadotropin- releasing hormone (GnRH) antagonist (GnRH-ant) protocol and the GnRH agonist long (GnRH-a) protocol for patients with diminished ovarian reserve (DOR). A total of 1,233 patients with DOR (anti-Mullerian hormone <1.1 ng/mL) were recruited for this retrospective case-control study. They were divided into two groups according to female age. Younger patients were assigned to POSEIDON group3 (PG3: age ≤35 years); older patients were assigned to POSEIDON group 4 (PG4: age >35 years). All patients with DOR underwent controlled ovarian stimulation and fresh embryo transfer (ET) on day 3. We recruited 283 GnRH-a and 54 GnRH-ant cycles for PG3, and 663 GnRH-a and 233 GnRH-ant cycles for PG4. In PG3, the GnRH-a protocol was associated with a lower ET cancellation rate (30/283 = 10.2% vs. 12/54 = 22.2%, p = 0.018) and a higher live birth rate (7/54 = 13.0% vs. 78/283 = 27.6%, p = 0.024) than the GnRH-ant protocol for the initiated cycles. Furthermore, the GnRH-a protocol was correlated with a higher implantation rate than the GnRH-ant protocol for ET cycles (146/577 = 25.3% vs. 11/103 = 10.7%, P = 0.027). No differences in the ET cancellation rate, live birth rate and implantation rate between GnRH-a and GnRH-ant groups were observed among PG4 patients. In conclusion, the GnRH-a protocol was more effective than the GnRH-ant protocol for young patients with DOR. The low ET cancellation rate and high implantation rate may be related to embryo quality or endometrial receptivity, which warrant further investigation. [ABSTRACT FROM AUTHOR]

Recently, reports showed that embryos identified as mosaic after preimplantation genetic testing for aneuploid (PGT-A) could result in live birth with lower pregnancy and higher pregnancy loss rates compared with euploid embryos. However, the effects of mosaicism level on reproductive outcomes remain controversial. This study aimed to examine the level of mosaicism on pregnancy outcomes. Single mosaic embryo transfer was offered to 108 women who only had mosaic embryos. Mosaic embryos were labeled by utilizing next generation sequencing (NGS) based PGT-A for day 5/6 trophectoderm (TE) biopsies. TE biopsies containing < 50% abnormal cells were classified as low-level mosaicism and ≥ 50% as high-level mosaicism. To further confirm the concordance of chromosome constitution between TE and inner cell mass (ICM), 41 remaining embryos designated as mosaic blastocysts donated for research were also analyzed. Comparable live birth rate (LBR) but higher miscarriage rate (MR) was found in the high-level group. (LBR: low vs. high: 44.5% vs. 36%; p = 0.45, MR: low vs. high: 5.1% vs. 30.7%; p = 0.012). Analyses of TE and ICM from the remaining mosaic blastocysts show a poor concordance. This preliminary study demonstrated that high-level mosaic embryos could result in comparable LBR but higher MR. [ABSTRACT FROM AUTHOR]