Automatic Ploidy Prediction and Quality Assessment of Human Blastocyst Using Time-Lapse Imaging.

Assessing fertilized human embryos is crucial for in vitro-fertilization (IVF), a task being revolutionized by artificial intelligence and deep learning. Existing models used for embryo quality assessment and chromosomal abnormality (ploidy) detection could be significantly improved by effectively utilizing time-lapse imaging to identify critical developmental time points for maximizing prediction accuracy. Addressing this, we developed and compared various embryo ploidy status prediction models across distinct embryo development stages. We present BELA (Blastocyst Evaluation Learning Algorithm), a state-of-the-art ploidy prediction model surpassing previous image- and video-based models, without necessitating subjective input from embryologists. BELA uses multitask learning to predict quality scores that are used downstream to predict ploidy status. By achieving an AUC of 0.76 for discriminating between euploidy and aneuploidy embryos on the Weill Cornell dataset, BELA matches the performance of models trained on embryologists' manual scores. While not a replacement for preimplantation genetic testing for aneuploidy (PGT-A), BELA exemplifies how such models can streamline the embryo evaluation process, reducing time and effort required by embryologists.

Characterization of an artificial intelligence model for ranking static images of blastocyst stage embryos.

OBJECTIVE: To perform a series of analyses characterizing an artificial intelligence (AI) model for ranking blastocyst-stage embryos. The primary objective was to evaluate the benefit of the model for predicting clinical pregnancy, whereas the secondary objective was to identify limitations that may impact clinical use. DESIGN: Retrospective study. SETTING: Consortium of 11 assisted reproductive technology centers in the United States. PATIENT(S): Static images of 5,923 transferred blastocysts and 2,614 nontransferred aneuploid blastocysts. INTERVENTION(S): None. MAIN OUTCOME MEASURE(S): Prediction of clinical pregnancy (fetal heartbeat). RESULT(S): The area under the curve of the AI model ranged from 0.6 to 0.7 and outperformed manual morphology grading overall and on a per-site basis. A bootstrapped study predicted improved pregnancy rates between +5% and +12% per site using AI compared with manual grading using an inverted microscope. One site that used a low-magnification stereo zoom microscope did not show predicted improvement with the AI. Visualization techniques and attribution algorithms revealed that the features learned by the AI model largely overlap with the features of manual grading systems. Two sources of bias relating to the type of microscope and presence of embryo holding micropipettes were identified and mitigated. The analysis of AI scores in relation to pregnancy rates showed that score differences of ≥0.1 (10%) correspond with improved pregnancy rates, whereas score differences of <0.1 may not be clinically meaningful. CONCLUSION(S): This study demonstrates the potential of AI for ranking blastocyst stage embryos and highlights potential limitations related to image quality, bias, and granularity of scores.

In vitro fertilization and andrology laboratories in 2030.

The in vitro fertilization and andrology laboratories are at the center of assisted reproductive technologies and the place where technicians and embryologists manipulate gametes and preimplantation-stage embryos with the goal of achieving the best embryo for transfer. Through the years, these laboratories have seen developments in technique, technology, and testing. The goal of this Views and Interviews series is to bring together the thought leaders in the field and envision what the laboratories will look like in the next 10 years.

In vitro fertilization and andrology laboratory in 2030: expert visions.

The aim of this article is to gather 9 thought leaders and their team members to present their ideas about the future of in vitro fertilization and the andrology laboratory. Although we have seen much progress and innovation in the laboratory over the years, there is still much to come, and this article looks at what these leaders think will be important in the future development of technology and processes in the laboratory.

The global impact of COVID-19 on infertility services.

The COVID-19 pandemic has posed unique concerns and potential risks to women now pregnant or considering childbearing. Although no professional societies have issued recommendations that women avoid conception at this time, several professional organizations recommended a moratorium on infertility services including both medically assisted reproduction and assisted reproductive technology shortly after the World Health Organization declared COVID-19 infection to be a pandemic. Reasons cited for undertaking these extraordinary measures included prevention of possible complications of assisted reproductive technology and medically assisted reproduction and virus induced complications of pregnancy including potential vertical transmission to the fetus and optimization use of critical health care resources. A survey of reproductive health providers in 97 countries was undertaken to assess their response to the pandemic and recently issued guidance. Although different countries reacted differently with diverse responses and variable resources, the results suggest that the reproductive health community has largely been responsive to public health and individual patient concerns.

A novel single-cell DNA fingerprinting method successfully distinguishes sibling human embryos.

OBJECTIVE: To validate a novel system for embryonic DNA fingerprinting which can reliably distinguish sibling embryos from each other. DESIGN: Prospective, randomized, and blinded study. SETTING: Academic center for reproductive medicine. PATIENT(S): Blastomeres were obtained from discarded and transferred embryos from six patients undergoing IVF treatment. INTERVENTION(S): None. MAIN OUTCOME MEASURE(S): Single lymphocytes from sibling cell lines and blastomeres from sibling day 3 human embryos were evaluated for accurate assignment of relationship using whole genome amplification and single-nucleotide polymorphism microarrays. RESULT(S): Assignment of single-cell relationships was accomplished with 100% accuracy. We also observed complete agreement between the molecular karyotype and DNA fingerprint-based identification of embryos implanted in three clinical IVF cases after multiple embryo transfer. CONCLUSION(S): These data demonstrate the first single-blastomere DNA fingerprinting technology capable of unequivocal discrimination of sibling human embryos.

Robust embryo identification using first polar body single nucleotide polymorphism microarray-based DNA fingerprinting.

This study sought to validate a novel, minimally invasive system for embryo tracking by single nucleotide polymorphism microarray-based DNA fingerprinting of the first polar body. First polar body-based assignments of which embryos implanted and were delivered after multiple ET were 100% consistent with previously validated embryo DNA fingerprinting-based assignments.

A GnRH agonist and exogenous hormone stimulation protocol has a higher live-birth rate than a natural endogenous hormone protocol for frozen-thawed blastocyst-stage embryo transfer cycles: an analysis of 1391 cycles.

OBJECTIVE: To compare embryo and birth data in cryopreserved-thawed blastocyst-stage ET cycles between natural endogenous hormone cycles and exogenous hormone stimulation cycles. DESIGN: Retrospective cohort analysis. SETTING: Large academic assisted reproductive technology center. PATIENT(S): One thousand three hundred ninety-one patient cycles undergoing frozen-thawed blastocyst-stage ET cycles. MAIN OUTCOME MEASURE(S): Live-birth rate. INTERVENTION(S): The synthetic protocol used GnRH agonist followed by estrogen and P. The natural protocol used monitoring and post-transfer P. RESULT(S): The patients in the two protocols had similar baseline characteristics. Multiple linear regression showed the synthetic protocol to have a higher live-birth rate (odds ratio [OR], 1.46; 95% confidence interval [CI], 1.02-2.09). In patients having two embryos transferred, the synthetic stimulation protocol resulted in a higher live-birth rate per cycle start (32.3% vs. 20.4%; relative risk [RR], 1.58; 95% CI, 1.22-2.06). Similarly, patients with one or two embryos transferred who had additional cryopreserved blastocysts available also had a higher live-birth rate per cycle start (36.1% vs. 12.1; RR, 2.98; 95% CI, 1.16-7.63). CONCLUSION(S): The synthetic hormone protocol was associated with a higher live-birth rate when compared with a natural cycle protocol for frozen-thawed blastocyst-stage ET cycles. This improvement persisted when analysis was controlled for cycle cancellation. The synthetic stimulation protocol for frozen-thawed embryo cycles offers improved outcome results for patients.

Live birth sex ratios are not influenced by blastocyst-stage embryo transfer.

OBJECTIVE: To analyze the sex ratio of infants born after blastocyst-stage transfer of embryos with normal preimplantation FISH genetic screening. DESIGN: Retrospective cohort analysis. SETTING: Large academic assisted reproductive technology center. PATIENT(S): Two hundred twenty-eight patients undergoing fresh IVF cycle with blastocyst transfer. INTERVENTION(S): Preimplantation genetic screening for sex complement. MAIN OUTCOME MEASURE(S): Sex ratio in liveborn infants following blastocyst transfer. RESULT(S): One thousand thirteen embryos were normal by preimplantation genetic screening of chromosomes 13, 15, 16, 17, 18, 21, 22, X, and Y. Four hundred ninety-eight normal embryos were transferred to 228 patients with an overall live birth rate of 41.7%. Transferred blastocysts were selected based upon morphologic assessment. When controlling for the sex of the blastocyst embryo, there was no difference in the male-to-female delivery rate per embryo transferred (27.3% vs. 21.4%) (relative risk =1.28, confidence interval 0.93-1.74). Of the live births 51.7% were male and 48.3% were female (P=.61). Subanalysis revealed no difference in male-to-female delivery rates in groups with a 1:1 ratio of male:female embryos transferred, a non 1:1 ratio transferred, or single-sex transfers. CONCLUSION(S): Blastocyst-stage embryo transfer does not influence the live birth sex ratio of embryos with normal preimplantation FISH genetic screening.

A luteal estradiol protocol for anticipated poor-responder patients may improve delivery rates.

OBJECTIVE: To compare IVF data and outcomes between a standard protocol and a luteal phase E(2) protocol. DESIGN: Retrospective cohort analysis. SETTING(S): Large academic assisted reproduction technologies center. PATIENT(S): Fifty-seven infertile patients with a history of poor response to IVF stimulation and 228 matched control patients. INTERVENTION(S): IVF with a standard protocol or a luteal phase E(2) protocol. MAIN OUTCOME MEASURE(S): Live-birth rates. RESULT(S): Patients in the luteal E(2) protocol required more days of stimulation and total gonadotropins and had higher peak E(2) levels when compared with the control group. The luteal E(2) protocol showed a greater percentage of embryos with >or=7 cells on day 3. A trend toward improved delivery rates was seen in the luteal E(2) protocol (28.1% vs. 22.4%; relative risk, 1.25, 0.78-2.03). CONCLUSION(S): A luteal E(2) protocol results in improved day 3 embryo development as demonstrated by the percent of embryos at the >or=7-cell stage. Likewise, the luteal E(2) protocol may ultimately improve pregnancy outcomes for patients with poor response to IVF stimulation.

A luteal estradiol protocol for expected poor-responders improves embryo number and quality.

OBJECTIVE: To compare embryo and oocyte data between a standard protocol and a luteal phase estradiol protocol. DESIGN: Retrospective paired cohort analysis. SETTING: Private in vitro fertilization (IVF) center. PATIENT(S): 60 poor-responder patients undergoing 120 IVF cycles. INTERVENTION(S): Addition of luteal estradiol to the standard IVF protocol. MAIN OUTCOME MEASURE(S): Number of embryos with > or = 7 cells on day 3 of development. RESULT(S): The luteal phase estradiol protocol showed a statistically significantly greater number of embryos with > or = 7 cells, oocytes retrieved, mature oocytes, and embryos than did the standard protocol. There was no difference between the two protocols with respect to basal antral follicle count, days of stimulation, number of follicles > or = 14 mm on day of surge, or endometrial thickness on day of surge. A trend toward improved pregnancy outcomes was found with the luteal estradiol protocol. CONCLUSION(S): Giving estradiol in the luteal phase preceding IVF hyperstimulation increases the number and the quality of embryos achieved in patients deemed to have a poor response to IVF. Ultimately, this may translate into improved pregnancy outcomes in these patients.

The predictive value for in vitro fertility delivery rates is greatly impacted by the method used to select the threshold between normal and elevated basal follicle-stimulating hormone.

OBJECTIVE: To evaluate the predictive accuracy of different methodologies for selecting a basal FSH threshold level that prognosticates live birth after IVF. DESIGN: Retrospective. SETTING: Academic private practice. PATIENT(S): Eight thousand nineteen patients who had their basal FSH levels determined by the program's endocrinology laboratory. INTERVENTION(S): Thresholds between normal and elevated basal FSH levels were calculated by using six different methodologies. MAIN OUTCOME MEASURE(S): Live birth rate per initiated IVF cycle. RESULT(S): The thresholds selected by using the manufacturer's normal range or using 95% confidence intervals of a fertile population, the infertile population, or distinct age groups within the infertile population all proved unsatisfactory. The live birth rates for patients in whom there had been a previously elevated FSH level were

Low-dose aspirin use does not improve in vitro fertilization outcomes in poor responders.

OBJECTIVE: To assess if aspirin improves pregnancy outcome in patients undergoing in vitro fertilization (IVF) with a diagnosis of poor response. DESIGN: Retrospective cohort analysis. SETTING: Academic private practice. PATIENT(S): 1250 poor-responder patients undergoing IVF. INTERVENTION(S): Low-dose (81 mg) aspirin before and during an IVF cycle. MAIN OUTCOME MEASURE(S): Live-birth rate. RESULT(S): Patients taking 81 mg of aspirin had statistically significantly higher basal antral follicle counts, more days of stimulation, more ampules of gonadotropins used, higher peak estradiol levels, and more follicles that were > or = 14 mm in diameter on the day of human chorionic gonadotropin administration. There was a decrease in the overall fertilization rate for the patients taking aspirin. There was no difference in IVF outcome rates (implantation, pregnancy, loss, or live birth). CONCLUSION(S): Patients with a diagnosis of poor response who were taking a regimen of 81 of mg aspirin showed an increase in many IVF stimulation parameters and a decrease in fertilization rates. No improvement secondary to 81-mg aspirin intake was found in IVF outcome rates.

Male age negatively impacts embryo development and reproductive outcome in donor oocyte assisted reproductive technology cycles.

OBJECTIVE: To determine whether male age influences embryo development and reproductive potential in assisted reproductive technology cycles. DESIGN: Retrospective cohort analysis. SETTING: Private IVF center. PATIENT(S): One thousand twenty-three male partners participating in anonymous oocyte donation cycles. INTERVENTION(S): Infertile couples undergoing 1,023 anonymous oocyte donation cycles. MAIN OUTCOME MEASURE(S): Live birth rate. RESULT(S): A significant increase in pregnancy loss, decrease in live birth rate, and decrease in blastocyst formation rate were noted in men >50 years of age. There was no significant difference in implantation rate, pregnancy rate, or early embryo development through the cleavage stage (demonstrated by fertilization rate, embryo cleavage rate, percentage of nonfertilized or polyspermic embryos, rate of embryo arrest, or seven or more cell embryo development on day 3). Men < or =45 years of age had significantly more semen volume and more motile sperm than men >45 years of age. There was no significant change in sperm morphology or concentration. CONCLUSION(S): After controlling for female age with use of the donor oocyte model, male age >50 years significantly affected pregnancy outcomes and blastocyst formation rates. Semen volume and total motility decreased with increasing male age. Initial embryo morphology through the cleavage stage was not affected.

Pregnancy after cryopreservation of donor oocytes and preimplantation genetic diagnosis of embryos in a patient with ovarian failure.

OBJECTIVE: To describe the successful use of preimplantation genetic diagnosis to assess the prevalence of meiotic errors after oocyte cryopreservation in an oocyte donation cycle. DESIGN: Case report. SETTING: Private IVF center. PATIENT(S): A 42.6-year-old patient with ovarian failure. INTERVENTION(S): A donor oocyte IVF cycle with cryopreservation of oocytes followed by thaw, fertilization of oocytes, preimplantation genetic diagnosis for selective aneuploidy, and ET. MAIN OUTCOME MEASURE(S): Preimplantation genetic analysis of chromosomes 13,16,18, 21,22, X, and Y with fluorescence in-situ hybridization. RESULT(S): The recipient's initial serum beta-hCG level was 196 mIU/mL 15 days after oocyte retrieval. An initial ultrasound at the sixth week of gestation revealed two gestational sacs. A second ultrasound 1 week later showed a monochorionic twin in sac A and a singleton pregnancy in sac B. Fetal cardiac activity was visualized for all gestations. CONCLUSION(S): This case illustrates the feasibility of cryopreservation of donor oocytes combined with preimplantation genetic diagnosis for clinical use in those settings where there may be an increased risk of spindle-related abnormalities.

A new follicle aspiration needle set is equally effective and as well tolerated as the standard needle when used in a prospective randomized trial in a large in vitro fertilization program.

OBJECTIVE: To compare the effectiveness and tolerability of two different 17-gauge follicle aspiration needles used in a large in vitro fertilization (IVF) program. DESIGN: Prospective, randomized single blinded study. SETTING: Private IVF center. PATIENT(S): Three hundred women undergoing IVF were randomly allocated at the time of oocyte retrieval to either the study needle (n = 151; follicle aspiration set [FAS] set) or the standard needle (n = 149; Echotip) used in the practice. Patients were blinded to the needle used. INTERVENTION(S): Transvaginal ultrasound-guided oocyte aspiration. MAIN OUTCOME MEASURE(S): Number of eggs retrieved/follicles visualized, retrieval time, mean amount of blood in the aspirate, egg damage, patient tolerance, physician acceptability, implantation, and pregnancy rate. RESULT(S): No differences were found in the number of eggs retrieved normalized to follicles visualized. Egg damage (4% vs. 4.2%), average blood in the aspirate (2.2 vs. 2.2), and retrieval time per egg (38 vs. 36 seconds) were similar with both needles. There were also no differences in pain or cramping scores (at 30 minutes and 24 hours after retrieval) or in the physicians' ratings of the two needles. The percentage of patients receiving an embryo transfer (ET), the implantation rate per embryo transfer, and the clinical pregnancy rate per embryo transfer were comparable for both needles. CONCLUSION(S): The FASs are equivalent.