Blastocyst Prediction of Day-3 Cleavage-Stage Embryos Using Machine Learning

Background:Embryo selection plays an important role in the success of in vitro fertilization (IVF). However, morphological embryo assessment has a number of limitations, including the time required, lack of accuracy, and inconsistency. This study determined whether a machine learning-based model could predict blastocyst formation using day-3 embryo images. Methods:Day-3 embryo images from IVF/intracytoplasmic sperm injection (ICSI) cycles performed at My Duc Phu Nhuan Hospital between August 2018 and June 2019 were retrospectively analyzed to inform model development. Day-3 embryo images derived from two-pronuclear (2PN) zygotes with known blastocyst formation data were extracted from the CCM-iBIS time-lapse incubator (Astec, Japan) at 67 hours post ICSI, and labeled as blastocyst/non-blastocyst based on results at 116 hours post ICSI. Images were used as the input dataset to train (85%) and validate (15%) the convolutional neural network (CNN) model, then model accuracy was determined using the training and validation dataset. The performance of 13 experienced embryologists for predicting blastocyst formation based on 100 day-3 embryo images was also evaluated. Results:A total of 1,135 images were allocated into training ([Formula: see text] = 967) and validation ([Formula: see text] = 168) sets, with an even distribution for blastocyst formation outcome. The accuracy of the final model for blastocyst formation was 97.72% in the training dataset and 76.19% in the validation dataset. The final model predicted blastocyst formation from day-3 embryo images in the validation dataset with an area under the curve of 0.75 (95% confidence interval [CI] 0.69–0.81). Embryologists predicted blastocyst formation with the accuracy of 70.07% (95% CI 68.12%–72.03%), sensitivity of 87.04% (95% CI 82.56%–91.52%), and specificity of 30.93% (95% CI 29.35%–32.51%). Conclusions:The CNN-based machine learning model using day-3 embryo images predicted blastocyst formation more accurately than experienced embryologists. The CNN-based model is a potential tool to predict additional IVF outcomes.

Blastocyst Transfer: A risk Factor for Gestational Diabetes Mellitus in Women undergoing in vitro Fertilization

Background The risk of developing gestational diabetes mellitus (GDM) is higher in women undergoing assisted reproductive treatment than in women conceiving spontaneously. Objectives To determine whether the GDM risk after day-3 embryo transfer differs from the GDM risk after day-5 blastocyst transfer. Methods Prospective observational study in women becoming pregnant after first fresh embryo or blastocyst transfer. Results 1579 women got pregnant and had life birth. 1300 women got day three embryo transfer only, whereas 279 women received at least one blastocyst. 252 out of the 1579 women developed GDM. Age, body mass index, baseline estradiol, baseline high-density lipoprotein, and progesterone on the day of hCG injection were not different in women receiving day three embryos only versus women receiving at least one blastocyst. The number and quality of retrieved oocytes were not different in women receiving day 3 embryo transfer (ET) from those receiving blastocysts. Our study confirmed already established GDM risk factors such as age and body mass index, baseline estradiol and high-density lipoprotein, as well as progesterone after ovarian stimulation. We could furthermore demonstrate that the GDM incidence in women receiving day five blastocyst transfer was significantly higher than those who received day three embryo transfer (21.15% vs. 14.85%, P=.009). Considering confounding factors, we likewise saw that blastocyst transfer was an independent procedure-related GDM risk factor (P = 0.009, Exp (B): 1.56, 95% CI: 1.12-2.18). Conclusion Blastocyst transfer after IVF/ICSI increases the risk of developing GDM.

The influence of oxygen concentration during embryo culture on obstetric and neonatal outcomes: a secondary analysis of a randomized controlled trial

STUDY QUESTION Does oxygen concentration during 3-day embryo culture affect obstetric and neonatal outcomes? SUMMARY ANSWER Oxygen concentration during 3-day embryo culture does not seem to affect the obstetric and neonatal outcomes measured. WHAT IS KNOWN ALREADY Atmospheric oxygen appears to be harmful during extended embryo culture. Embryo culture conditions might therefore be a potential risk factor for subsequent fetal development and the health of future children. No data are available concerning the obstetrics and neonatal outcomes after Day 3 transfer of embryos cultured under reduced and atmospheric oxygen tensions. STUDY DESIGN, SIZE, DURATION A secondary analysis of a previous randomized controlled trial assessing clinical pregnancy outcomes was carried out. This analysis included 1125 consecutive oocyte donation cycles utilizing ICSI or IVF and Day 3 embryo transfers between November 2009 and April 2012. The whole cohort of donated oocytes from patients who agreed to participate in the study were randomly allocated (1:1 ratio) to a reduced O2 tension group (6% O2) or an air-exposed group (20% O2) based on a computer-generated randomization list. Fresh and vitrified oocytes were used for oocyte donation. Only those pregnancies with a live birth at or beyond 24 weeks of gestation were included. PARTICIPANTS/MATERIALS, SETTING, METHODS Day 3 embryos were cultured in an atmosphere of 5.5% CO2, 6% O2, 88.5% N2 versus a dual gas system in air. MAIN RESULTS AND THE ROLE OF CHANCE From the eligible 1125 cycles, 564 were allocated to the 6% O2 group and 561 cycles to the 20% O2 group. However, 50 and 62 cycles did not reach embryo transfer in the 6% and 20% O2 groups, respectively. No differences were found between 6% O2 and atmospheric O2 tension in the number of livebirths per embryo transfer (mean ± SD, 0.5 ± 0.7 versus 0.5 ± 0.7), pregnancy complications or neonatal outcomes. Both groups (6% and atmospheric O2) had similar single and twin delivery rates (40.8% versus 38.1% and 10.7% versus 12.3%, respectively). Preterm delivery rates and very preterm delivery rates (10.80% versus 13.24% and 1.25% versus 2.94%, respectively), birthweight (3229 ± 561 g versus 3154 ± 731 g), low birthweight (2.92% versus 2.45%), birth height (50.18 ± 2.41 cm versus 49.7 ± 3.59 cm), head circumference (34.16 ± 1.87 cm versus 33.09 ± 1.85 cm) and 1 min Apgar scores (8.96 ± 0.87 versus 8.89 ± 0.96) were also similar between 6% and atmospheric O2 groups, respectively. LIMITATIONS, REASONS FOR CAUTION The number of liveborns finally analyzed is still small and not all obstetric and neonatal variables could be evaluated. Furthermore, a small proportion of the obstetric and neonatal data was obtained through a questionnaire filled out by the patients themselves. One reason for the lack of effect of oxygen concentration on pregnancy outcome could be the absence of trophectoderm cells at cleavage stage, which may make Day 3 embryos less susceptible to hypoxic conditions. WIDER IMPLICATIONS OF THE FINDINGS Nowadays many IVF laboratories use a more physiological oxygen concentration for embryo culture. However, the benefits of using low oxygen concentration on both laboratory and clinical outcomes during embryo culture are still under debate. Furthermore, long-term studies investigating the effect of using atmospheric O2 are also needed. Gathering these type of clinical data is indeed, quite relevant from the safety perspective. The present data show that, at least in egg donation cycles undergoing Day 3 embryo transfers, culturing embryos under atmospheric oxygen concentration seems not to affect perinatal outcomes. STUDY FUNDING/COMPETING INTEREST(S) The present project was supported by the R + D program of the Regional Valencian Government, Spain (IMPIVA IMDTF/2011/214). The authors declare that they have no conflict of interest with respect to the content of this manuscript. TRIAL REGISTRATION NUMBER NCT 01532193.

Pregnancy Outcomes of Patients with Low Serum β-hCG Level 14 Days After Fresh Embryo Transfer

Background: Although previous studies had successfully illustrated different pregnancy outcomes by different serum β-hCG levels after embryo transfer, prognosis of pregnancy outcomes remains elusive when the serum β-hCG level is extremely low (e.g., < 100 mIU/ml 14 days after embryo transfer). Therefore, the purpose of our study is to investigate the pregnancy outcomes of patients with low serum β-hCG level 14 days after day 3 embryo transfer. Methods: A retrospective study was performed with 723 patients with a serum β-hCG level between 5 and 100 mIU/ml 14 days after day 3 fresh embryo transfer. Pregnancy outcomes (ongoing pregnancy, early miscarriage, biochemical pregnancy loss, and ectopic pregnancy) were analyzed according to the female patients’ age. Receiver operating characteristic (ROC) curves were plotted to indicate the threshold for prediction of clinical pregnancy and ongoing pregnancy. Sensitivity and specificity were calculated according the ROC curves as well. Results: Of the 723 patients with serum β-hCG level <100 mIU/mL 14 days after day 3 embryo transfer, 85.6% (619) had biochemical pregnancy, and only 14.4% (104) had clinical pregnancy (including 4.7% with ongoing pregnancy, 3.7% with ectopic pregnancy, and 5.9% with early miscarriage). The rate of ongoing pregnancy was significantly lower in ≥ 38-year group compared with < 38-year group (1.3% vs. 5.6%, P =0.029). The serum β-hCG level to predict clinical pregnancy was 44.7 mIU/ml (sensitivity, 91.3%; specificity, 82.1%; area under the ROC curve (AUROC), 0.908). For ongoing pregnancy, the serum β-hCG level was 53.7 mIU/ml (sensitivity, 94.1%; specificity, 81.4%; AUROC, 0.902). Conclusions: Initially low serum β-hCG level 14 days after day 3 embryo transfer indicated poor prognosis with minimal likelihood of ongoing pregnancy. Keywords: assisted reproductive technology; human chorionic gonadotropin; pregnancy; live birth; embryo transfer

Cleavage Stage versus Blastocyst Stage Embryo Transfer in Oocyte Donation Cycles

Background and Objective: During the last few years, a trend has been noted towards embryos being transferred at the blastocyst stage, which has been associated with improved rates regarding implantation and clinical pregnancy in comparison to cleavage stage embryo transfers. There is a limited number of studies investigating this notion in oocyte donation cycles employing cryopreserved embryos. The aim of this study is to evaluate the implantation potential and clinical pregnancy rates between the day 3 cleavage stage and blastocyst stage embryo transfers in oocyte donation cycles employing vitrified embryos. Methods: This is a retrospective evaluation of oocyte donation frozen–thawed transfers completed in our clinic from January 2017 to December 2017. Intracytoplasmic sperm injection was conducted for all oocytes. Following fertilization, all embryos were cryopreserved either at the cleavage or blastocyst stage. Embryo transfer of two embryos was performed under direct sonographic guidance in all cases. Results: Our results confirmed a 55.6% clinical pregnancy (CP) resulting from day 3 embryo transfers, a 68.8% CP from day 5, and 71.4% CP from day 6. Significantly improved pregnancy rates were related to embryo transfers at the blastocyst stage when compared to cleavage stage transfers (68.9% and 55.6% respectively, p = 0.016). The risk with regards to multiple pregnancies was similar. Conclusion: Our findings indicate that in oocyte donation cycles employing vitrified embryos, embryo transfer at the blastocyst stage is accompanied with a significant improvement in pregnancy rates and merits further investigation.

Is leptin receptor expression triggered in case of embryo transfer to endometrium co-culture?

Background/aim: A synchronized dialogue between maternal and embryonic tissues is required for a successful implantation. Low uterine receptivity is responsible for two-thirds of implantation failures and leptin is effective in physiology of reproduction by binding to specific receptors. In this study, we investigate leptin receptor expression in cases of embryo transfer to endometrial co - culture. Material and methods: Biopsy materials were taken from 20 females with indication for co - culture application and were cultured in appropriate medium, after the epithelial cells were isolated. The grown cells were cultured in chamber slides as the first group. For the second group, day 3 embryo was added to chamber slides and the development was observed. 1 - 2 days later, the embryo was transferred and other cells (after the transfer process) were used to form the second group. After fixation, immunohistochemical staining with anti-leptin primary antibody was done. Results: Regarding the co-culture without the embryo transfer, moderate leptin receptor immunoreactivity was seen in perinuclear region and in cell membrane. And regarding co-culture with the embryo transfer, moderate leptin receptor immunreactivity was seen in cytoplasm and strong leptin receptor immunoreactivity was seen in cell membrane. Conclusion: Embryo transfer to the endometrium co-culture triggers leptin receptor expression.