Inferring simple but precise quantitative models of human oocyte and early embryo development

A new decision-support tool in a multi-center randomized trial for personalized, optimized, and simplified fertility treatment in non-PCOS patients

Graphical abstract

Abstract

This study aimed to evaluate the effectiveness of a clinical decision support tool, Opt-IVF, in achieving the following outcomes: reducing the total cumulative dosage of Gonadotropins (Gns) used during controlled ovarian stimulation cycles and reducing the repeated ultrasonograms (USG) for monitoring follicular growth without compromising the number of good quality blastocysts obtained. The study design employed a multi-center randomized trial. The study enrolled 115 women aged 25-45 years undergoing IVF. Among the participants, 55 were randomly assigned to the intervention group (Opt-IVF), and 60 were randomly assigned to the control group. The intervention involved using a clinical decision support tool, Opt-IVF, to guide Gn dosing and trigger dates. The participants in the intervention group required significantly lower cumulative Gn dosage. The intervention group had higher numbers of oocytes retrieved and M2 retrieved than the control group. The number of good-quality blastocysts, the good-quality blastocyst rate, the ovarian sensitivity index (OSI), and the pregnancy rate in the intervention group were significantly higher than in the control group. The utilization of the clinical decision support tool led to several positive outcomes, including eliminating the need for ultrasound exams after day 5, reducing the dosage of Gn required, and yielding significantly higher numbers of high-quality blastocysts and higher pregnancy rates. Thus, Opt-IVF can successfully provide a personalized, optimized, and simplified approach to superovulation. Opt-IVF consistently outperformed the clinical teams in most of the outcomes. Clinical trials registration: ClinicalTrials.gov (ID - NCT05811065). Date of Registration: 15 March 2023. Date of enrollment of the first subject: 20 March 2023.

Lay Summary

The high cost of IVF is a result of costly drugs, fixed prices for infrastructure, extensive testing required, and labor costs for physicians and other healthcare personnel. Superovulation, which involves the drug-induced release of multiple eggs needed for IVF, accounts for a significant share of these costs. Current approaches to superovulation involve almost daily monitoring of follicle development using ultrasound and/or blood tests. The daily dosage of stimulatory hormones is then prescribed by physicians based on empirical data and clinical experience. However, the dose is not optimized for each patient, and overstimulation complications can occur. The cost of testing and drugs makes this stage very expensive. To overcome the shortcomings of this system, we have developed a decision support tool (Opt-IVF) that can provide a personalized model-optimized dosage profile for each patient. The clinical results show that Opt-IVF optimizes and personalizes dosage, reduces testing, and provides better outcomes for patients.

Metabolic imaging of human cumulus cells reveals associations with pregnancy and live birth

STUDY QUESTION

Can fluorescence lifetime imaging microscopy (FLIM) detect associations between the metabolic state of cumulus cell (CC) samples and the clinical outcome of the corresponding embryos?

SUMMARY ANSWER

FLIM can detect significant variations in the metabolism of CC associated with the corresponding embryos that resulted in a clinical pregnancy versus those that did not.

WHAT IS KNOWN ALREADY

CC and oocyte metabolic cooperativity are known to be necessary for the acquisition of developmental competence. However, reliable CC biomarkers that reflect oocyte viability and embryo developmental competency have yet to be established. Quantitative measures of CC metabolism could be used to aid in the evaluation of oocyte and embryo quality in ART.

STUDY DESIGN, SIZE, DURATION

A prospective observational study was carried out. In total, 223 patients undergoing IVF with either conventional insemination or ICSI at a tertiary care center from February 2018 to May 2020 were included, with no exclusion criteria applied.

PARTICIPANTS/MATERIALS, SETTING, METHODS

This cohort had a mean maternal age of 36.5 ± 4.4 years and an average oocyte yield of 16.9 (range 1-50). One to four CC clusters from each patient were collected after oocyte retrieval and vitrified. CC metabolic state was assessed using FLIM to measure the autofluorescence of the molecules NAD(P)H and FAD+, which are essential for multiple metabolic pathways. CC clusters were tracked with their corresponding oocytes and associated embryos. Patient age, Day 3 and Day 5/6 embryo morphological grades, and clinical outcomes of embryos with traceable fate were recorded. Nine FLIM quantitative parameters were obtained for each CC cluster. We investigated associations between the FLIM parameters and patient maternal age, embryo morphological rank, ploidy, and clinical outcome, where false discovery rate P-values of <0.05 were considered statistically significant.

MAIN RESULTS AND THE ROLE OF CHANCE

A total of 851 CC clusters from 851 cumulus-oocyte complexes from 223 patients were collected. Of these CC clusters, 623 were imaged using FLIM. None of the measured CC FLIM parameters were correlated with Day 3 morphological rank or ploidy of the corresponding embryos, but FAD+ FLIM parameters were significantly associated with morphological rank of blastocysts. There were significant differences for FAD+ FLIM parameters (FAD+ fraction engaged and short lifetime) from CC clusters linked with embryos resulting in a clinical pregnancy compared with those that did not, as well as for CC clusters associated with embryos that resulted in a live birth compared those that did not.

LIMITATIONS, REASONS FOR CAUTION

Our data are based on a relatively low number of traceable embryos from an older patient population. Additionally, we only assessed CCs from 1 to 4 oocytes from each patient. Future work in a younger patient population with a larger number of traceable embryos, as well as measuring the metabolic state of CCs from all oocytes from each patient, would provide a better understanding of the potential utility of this technology for oocyte/embryo selection.

WIDER IMPLICATIONS OF THE FINDINGS

Metabolic imaging via FLIM is able to detect CC metabolic associations with maternal age and detects variations in the metabolism of CCs associated with oocytes leading to embryos that result in a clinical pregnancy and a live birth versus those that do not. Our findings suggest that FLIM of CCs may be used as a new approach to aid in the assessment of oocyte and embryo developmental competence in clinical ART.

STUDY FUNDING/COMPETING INTEREST(S)

National Institutes of Health grant NIH R01HD092550-03 (to C.R., and D.J.N.). Becker and Hickl GmbH and Boston Electronics sponsored research with the loaning of equipment for FLIM. D.J.N. and C.R. are inventors on patent US20170039415A1.

TRIAL REGISTRATION NUMBER

N/A.

BlastAssist: a deep learning pipeline to measure interpretable features of human embryos

STUDY QUESTION

Can the BlastAssist deep learning pipeline perform comparably to or outperform human experts and embryologists at measuring interpretable, clinically relevant features of human embryos in IVF?

SUMMARY ANSWER

The BlastAssist pipeline can measure a comprehensive set of interpretable features of human embryos and either outperform or perform comparably to embryologists and human experts in measuring these features.

WHAT IS KNOWN ALREADY

Some studies have applied deep learning and developed 'black-box' algorithms to predict embryo viability directly from microscope images and videos but these lack interpretability and generalizability. Other studies have developed deep learning networks to measure individual features of embryos but fail to conduct careful comparisons to embryologists' performance, which are fundamental to demonstrate the network's effectiveness.

STUDY DESIGN, SIZE, DURATION

We applied the BlastAssist pipeline to 67 043 973 images (32 939 embryos) recorded in the IVF lab from 2012 to 2017 in Tel Aviv Sourasky Medical Center. We first compared the pipeline measurements of individual images/embryos to manual measurements by human experts for sets of features, including: (i) fertilization status (n = 207 embryos), (ii) cell symmetry (n = 109 embryos), (iii) degree of fragmentation (n = 6664 images), and (iv) developmental timing (n = 21 036 images). We then conducted detailed comparisons between pipeline outputs and annotations made by embryologists during routine treatments for features, including: (i) fertilization status (n = 18 922 embryos), (ii) pronuclei (PN) fade time (n = 13 781 embryos), (iii) degree of fragmentation on Day 2 (n = 11 582 embryos), and (iv) time of blastulation (n = 3266 embryos). In addition, we compared the pipeline outputs to the implantation results of 723 single embryo transfer (SET) cycles, and to the live birth results of 3421 embryos transferred in 1801 cycles.

PARTICIPANTS/MATERIALS, SETTING, METHODS

In addition to EmbryoScope™ image data, manual embryo grading and annotations, and electronic health record (EHR) data on treatment outcomes were also included. We integrated the deep learning networks we developed for individual features to construct the BlastAssist pipeline. Pearson's χ2 test was used to evaluate the statistical independence of individual features and implantation success. Bayesian statistics was used to evaluate the association of the probability of an embryo resulting in live birth to BlastAssist inputs.

MAIN RESULTS AND THE ROLE OF CHANCE

The BlastAssist pipeline integrates five deep learning networks and measures comprehensive, interpretable, and quantitative features in clinical IVF. The pipeline performs similarly or better than manual measurements. For fertilization status, the network performs with very good parameters of specificity and sensitivity (area under the receiver operating characteristics (AUROC) 0.84-0.94). For symmetry score, the pipeline performs comparably to the human expert at both 2-cell (r = 0.71 ± 0.06) and 4-cell stages (r = 0.77 ± 0.07). For degree of fragmentation, the pipeline (acc = 69.4%) slightly under-performs compared to human experts (acc = 73.8%). For developmental timing, the pipeline (acc = 90.0%) performs similarly to human experts (acc = 91.4%). There is also strong agreement between pipeline outputs and annotations made by embryologists during routine treatments. For fertilization status, the pipeline and embryologists strongly agree (acc = 79.6%), and there is strong correlation between the two measurements (r = 0.683). For degree of fragmentation, the pipeline and embryologists mostly agree (acc = 55.4%), and there is also strong correlation between the two measurements (r = 0.648). For both PN fade time (r = 0.787) and time of blastulation (r = 0.887), there's strong correlation between the pipeline and embryologists. For SET cycles, 2-cell time (P < 0.01) and 2-cell symmetry (P < 0.03) are significantly correlated with implantation success rate, while other features showed correlations with implantation success without statistical significance. In addition, 2-cell time (P < 5 × 10-11), PN fade time (P < 5 × 10-10), degree of fragmentation on Day 3 (P < 5 × 10-4), and 2-cell symmetry (P < 5 × 10-3) showed statistically significant correlation with the probability of the transferred embryo resulting in live birth.

LIMITATIONS, REASONS FOR CAUTION

We have not tested the BlastAssist pipeline on data from other clinics or other time-lapse microscopy (TLM) systems. The association study we conducted with live birth results do not take into account confounding variables, which will be necessary to construct an embryo selection algorithm. Randomized controlled trials (RCT) will be necessary to determine whether the pipeline can improve success rates in clinical IVF.

WIDER IMPLICATIONS OF THE FINDINGS

BlastAssist provides a comprehensive and holistic means of evaluating human embryos. Instead of using a black-box algorithm, BlastAssist outputs meaningful measurements of embryos that can be interpreted and corroborated by embryologists, which is crucial in clinical decision making. Furthermore, the unprecedentedly large dataset generated by BlastAssist measurements can be used as a powerful resource for further research in human embryology and IVF.

STUDY FUNDING/COMPETING INTEREST(S)

This work was supported by Harvard Quantitative Biology Initiative, the NSF-Simons Center for Mathematical and Statistical Analysis of Biology at Harvard (award number 1764269), the National Institute of Heath (award number R01HD104969), the Perelson Fund, and the Sagol fund for embryos and stem cells as part of the Sagol Network. The authors declare no competing interests.

TRIAL REGISTRATION NUMBER

Not applicable.