Erratum: Relationship between morphology, euploidy and implantation potential of cleavage and blastocyst stage embryos

Development of an artificial intelligence based model for predicting the euploidy of blastocysts in PGT-A treatments

The euploidy of embryos is unpredictable before transfer in in vitro fertilisation (IVF) treatments without pre-implantation genetic testing (PGT). Previous studies have suggested that morphokinetic characteristics using an artificial intelligence (AI)-based model in the time-lapse monitoring (TLM) system were correlated with the outcomes of frozen embryo transfer (FET), but the predictive effectiveness of the model for euploidy remains to be perfected. In this study, we combined morphokinetic characteristics, morphological characteristics of blastocysts, and clinical parameters of patients to build a model to predict the euploidy of blastocysts and live births in PGT for aneuploidy treatments. The model was effective in predicting euploidy (AUC = 0.879) but was ineffective in predicting live birth after FET. These results provide a potential method for the selection of embryos for IVF treatments with non-PGT.

Evaluation of artificial intelligence using time-lapse images of IVF embryos to predict live birth

RESEARCH QUESTION

Can artificial intelligence (AI) improve the prediction of live births based on embryo images?

DESIGN

The AI system was created by using the Attention Branch Network associated with deep learning to predict the probability of live birth from 141,444 images recorded by time-lapse imaging of 470 transferred embryos, of which 91 resulted in live birth and 379 resulted in non-live birth that included implantation failure, biochemical pregnancy and clinical miscarriage. The possibility that the calculated confidence scores of each embryo and the focused areas visualized in each embryo image can help predict subsequent live birth was examined.

RESULTS

The AI system for the first time successfully visualized embryo features in focused areas that had potential to distinguish between live and non-live births. No visual feature of embryos were visualized that were associated with live or non-live births, although there were many images in which high-focused areas existed around the zona pellucida. When a cut-off level for the confidence score was set at 0.341, the live birth rate was significantly greater for embryos with a score higher than the cut-off level than for those with a score lower than the cut-off level (P < 0.001). In addition, the live birth rate of embryos with good morphological quality and confidence scores higher than 0.341 was 41.1%.

CONCLUSIONS

The authors have created an AI system with a confidence score that is useful for non-invasive selection of embryos that could result in live birth. Further study is necessary to improve selection accuracy.

Miscarriage Rate Is High With Frozen-Thawed Blastocysts Arising From Poor-Quality Cleavage Stage Embryos

Embryos with low morphological scores can still develop to the blastocyst stage and result in good clinical outcomes. However, no studies have reported the possible effects of transferring cryopreserved blastocysts developed from poor-quality cleavage stage embryos on pregnancy and perinatal outcomes. In this retrospective study, the clinical value of transferring blastocysts derived from day 3 poor-quality cleavage stage embryos during in vitro fertilization and embryo transfer procedures was evaluated. According to the quality of embryos on day 3 from which the transferred blastocyst originated, patients were divided into three groups: poor-quality (111 cycles, group A), good-quality (235 cycles, group B), and top-quality (119 cycles, group C). Group A experienced the highest miscarriage rate (30.2%) which was increased when compared to group C (12.5%) (P = 0.03). The clinical pregnancy rates and live birth rates were not significantly different among the three groups. However, good blastocyst originating from top day 3 embryos resulted in higher live birth rate. Of the 218 live births, no differences in obstetric and perinatal outcomes were noted among the three groups. The results showed that extended culture of poor-quality cleavage stage embryos could resulted in favorable clinical pregnancy rates but at a higher incidence of miscarriages. Meanwhile, the risk of adverse perinatal outcomes was not increased.