Considerations for future modification of The Association for the Study of Reproductive Biology embryo grading system incorporating time-lapse observations

Application of a methodological framework for the development and multicenter validation of reliable artificial intelligence in embryo evaluation

BACKGROUND

Artificial intelligence (AI) models analyzing embryo time-lapse images have been developed to predict the likelihood of pregnancy following in vitro fertilization (IVF). However, limited research exists on methods ensuring AI consistency and reliability in clinical settings during its development and validation process. We present a methodology for developing and validating an AI model across multiple datasets to demonstrate reliable performance in evaluating blastocyst-stage embryos.

METHODS

This multicenter analysis utilizes time-lapse images, pregnancy outcomes, and morphologic annotations from embryos collected at 10 IVF clinics across 9 countries between 2018 and 2022. The four-step methodology for developing and evaluating the AI model include: (I) curating annotated datasets that represent the intended clinical use case; (II) developing and optimizing the AI model; (III) evaluating the AI's performance by assessing its discriminative power and associations with pregnancy probability across variable data; and (IV) ensuring interpretability and explainability by correlating AI scores with relevant morphologic features of embryo quality. Three datasets were used: the training and validation dataset (n = 16,935 embryos), the blind test dataset (n = 1,708 embryos; 3 clinics), and the independent dataset (n = 7,445 embryos; 7 clinics) derived from previously unseen clinic cohorts.

RESULTS

The AI was designed as a deep learning classifier ranking embryos by score according to their likelihood of clinical pregnancy. Higher AI score brackets were associated with increased fetal heartbeat (FH) likelihood across all evaluated datasets, showing a trend of increasing odds ratios (OR). The highest OR was observed in the top G4 bracket (test dataset G4 score ≥ 7.5: OR 3.84; independent dataset G4 score ≥ 7.5: OR 4.01), while the lowest was in the G1 bracket (test dataset G1 score < 4.0: OR 0.40; independent dataset G1 score < 4.0: OR 0.45). AI score brackets G2, G3, and G4 displayed OR values above 1.0 (P < 0.05), indicating linear associations with FH likelihood. Average AI scores were consistently higher for FH-positive than for FH-negative embryos within each age subgroup. Positive correlations were also observed between AI scores and key morphologic parameters used to predict embryo quality.

CONCLUSIONS

Strong AI performance across multiple datasets demonstrates the value of our four-step methodology in developing and validating the AI as a reliable adjunct to embryo evaluation.

Effect of 3D and 2D cell culture systems on trophoblast extracellular vesicle physico-chemical characteristics and potency

The growing understanding of the role of extracellular vesicles (EVs) in embryo-maternal communication has sparked considerable interest in their therapeutic potential within assisted reproductive technology, particularly in enhancing implantation success. However, the major obstacle remains the large-scale production of EVs, and there is still a gap in understanding how different culture systems affect the characteristics of the EVs. In the current study, trophoblast analogue human chorionic carcinoma cell line was cultivated in both conventional monolayer culture (2D) and as spheroids in suspension culture (3D) and how the cell growth environment affects the physical, biochemical and cellular signalling properties of EVs produced by them was studied. Interestingly, the 3D system was more active in secreting EVs compared to the 2D system, while no significant differences were observed in terms of morphology, size, and classical EV protein marker expression between EVs derived from the two culture systems. There were substantial differences in the proteomic cargo profile and cellular signalling potency of EVs derived from the two culture systems. Notably, 2D EVs were more potent in inducing a cellular response in endometrial epithelial cells (EECs) compared to 3D EVs. Therefore, it is essential to recognize that the biological activity of EVs depends not only on the cell of origin but also on the cellular microenvironment of the parent cell. In conclusion, caution is warranted when selecting an EV production platform, especially for assessing the functional and therapeutic potential of EVs through in vitro studies.

Trade-off between double cleavage-stage embryos transfer and single blastocyst-stage embryo transfer in patients with few good quality embryos in antagonist cycles: a retrospective study using a propensity score matching analysis

OBJECTIVE

This study aimed to compare the per OPU clinical outcomes for transfer of Day 3 double cleavage-stage embryos (DET) and Day 5 single blastocyst-stage (SBT) in patients with five or fewer good quality embryos on day 3 per occyte pick-up cycle (OPU) in antagonist cycles with consideration of blastocyst formation failure.

METHODS

This was a retrospective, observational cohort study of 2,116 cases of OPU treated with antagonist protocol in the affiliated Chenggong Hospital of Xiamen University between January 2013 and December 2020. DET was performed in 1,811cycles and SBT was performed in 305 cycles. The DET group was matched to the SBT group by propensity score (PS) matching according to multiple maternal baseline covariates. After PS matching, there were 303 ET cycles in each group. The primary outcomes were the cumulative live birth rate (CLBR), cumulative multiple pregnancy rate(CMPR)per OPU and the number of ET to achieve live birth per OPU. Secondary outcomes were the percentage of clinical pregnancy(CPR), live birth rate(LBR), multiple pregnancy rate(MPR).

RESULTS

Following PS mating, the CLBR was slightly higher (48.8% versus 40.3% ; P = 0.041) and the CMPR was significantly higher in the DET group compared to SBT group(44.2% versus 7.9%, P < 0.001). The CPR, LBR and MPR per fresh transfer were higher in DET group compared to SBT group(50.2% versus 28.7%; 41.3% versus 21.5%;29.6% versus 0%, P < 0.001). The number of ET to achieve live birth per OPU in SBT group was obiviously more than in DET group(1.48 ± 0.578 versus 1.22 ± 0.557 ,P < 0.001).

CONCLUSION

With a marginal difference cumulative live birth rate, the lower live birth rate per fresh transfer and higher number of ET per OPU in the SBT group suggested that it might take longer time to achieve a live birth with single blastocyst strategy. A trade-off decision should be made between efficiency and safety.

Sperm Selection Using Zona Pellucida-Binding Enhanced Embryo Morphokinetic and Clinical Outcomes in ICSI: A Sibling Oocytes Study

The objective was to investigate the embryo morphokinitics using a time-lapse monitoring (TLM) system and assessment of clinical outcomes following intracytoplasmic sperm injection (ICSI) with zona pellucida (ZP)-bound sperm selection and conventional methods. A total of 371 metaphase II (MII) oocytes from 50 ICSI cycles were studied. Sibling oocytes were randomly divided into control (n = 199) and ZP-bound group (n = 172). All resulting zygotes were cultured and monitored in the TLM system up to Day 3 after ICSI. Fertilization rate, early embryo development, and clinical outcomes were evaluated. No significant differences were found in fertilization rate, time-lapse qualitative and quantitative measures, pronuclear fading time (PNF) t2, t3, t4, t5, t6, and t7 (times of cleavage to 2, 3, 4, 5, 6, and 7 cells), respectively. However, the t8 (time of cleavage to eight cells) and cc3 (duration of third cell cycle) revealed a significant difference between control and ZP-bound groups (p < .05). A significant difference between the two groups (p < .05) in the rates of Grade A embryos (according to Basile algorithm), chemical pregnancy, clinical pregnancy, and implantation was observed. Sperm selection using biological materials, such as ZP, improved both embryo quality and pregnancy outcomes, despite not affecting the early embryo development and morphokinetic parameters up to t8. This prospective randomized sibling oocyte trial was registered in October 2020 to January 2022 (IRCT20200705048021N1).