Purpose: The purpose of the study was to invent and evaluate the novel artificial intelligence (AI) system named Fertility image Testing Through Embryo (FiTTE) for predicting blastocyst viability and visualizing the explanations via gradient‐based localization.Methods: The authors retrospectively analyzed 19 342 static blastocyst images with related inspection histories from 9961 infertile patients who underwent in vitro fertilization. Among these data, 17 984 cycles of single‐blastocyst transfer were used for training, and data from 1358 cycles were used for testing purposes.Results: The prediction accuracy for clinical pregnancy achieved by a control model using conventional Gardner scoring system was 59.8%, and area under the curve (AUC) was 0.62. FiTTE improved the prediction accuracy by using blastocyst images to 62.7% and AUC of 0.68. Additionally, the accuracy achieved by an ensemble model using image plus clinical data was 65.2% and AUC was 0.71, representing an improvement in prediction accuracy. The visualization algorithm showed brighter colors with blastocysts that resulted in clinical pregnancy.Conclusions: The authors invented the novel AI system, FiTTE, which could provide more precise prediction of the probability of clinical pregnancy using blastocyst images secondary to single embryo transfer than the conventional Gardner scoring assessments. FiTTE could also provide explanation of AI prediction using colored blastocyst images.

Purpose: This study aimed to evaluate the effectiveness of intrauterine infusion of platelet‐rich plasma (PRP) before embryo transfer (ET) in recurrent implantation failure (RIF) cases.Methods: The authors retrospectively analyzed 54 ET cycles involving frozen and thawed high‐quality blastocysts after intrauterine PRP infusion between September 2019 and November 2020. All patients had a history of at least two times of implantation failure on ET. A total of 54 patients were categorized into two groups: thin endometrium (39 patients) and unexplained implantation failure (15 patients). In the thin‐endometrium group, the endometrial thickness (EMT) was <8.0 mm at cycle days 12–14 in the prior ET cycle.Results: Among the 54 ET cycles after PRP infusion, 31 (57.4%) were positive for human chorionic gonadotropin (hCG) and 27 (50%) achieved clinical pregnancy, which was significantly better than that in prior ET cycles without PRP infusion (27.2% and 9.6%, respectively). The EMT was not increased at ET date on the PRP cycle compared with that in the prior ET cycle in both patient groups. Moreover, EMT was not different between the hCG‐positive and hCG‐negative groups.Conclusion: Although intrauterine PRP infusion had no superior effect on increasing the EMT than conventional therapeutic agents, it resulted in high pregnancy rates in patients experiencing RIF with or without thin endometrium.

Aim: To determine whether there are differences in size between the male and female pronuclei immediately before the pronuclear membrane breakdown (PNMBD) and to evaluate whether pronuclear size differences influence normal birth rates.Methods: Time‐lapse photography was used to measure the size of each pronucleus, while the outcome of 71 frozen‐thawed single blastocyst transfers in patients receiving hormone therapy was analyzed retrospectively. The pronuclear measurements were made 4 hours before the PNMBD, corresponding to 16‐20 hours after insemination or intracytoplasmic sperm injection, and immediately before the PNMBD. The differences in the areas between the pronuclei in the zygotes that were associated with the live births were compared with those that were associated with the failed pregnancies.Results: The average difference in the area between the pronuclei 4 hours before and immediately before the PNMBD in the patients with a live birth was significantly smaller than in the patients with a failed birth. In addition, the average area difference in the patients with a successful birth was significantly smaller when the measurements were made immediately before the PNMBD, compared with the measurements 4 hours before the PNMBD. Such differences were not detected among the patients who did not achieve a birth.Conclusion: The birth of healthy babies resulted from zygotes that contained pronuclei of similar size when the measurements were made immediately before the PNMBD. Evaluating the size of each pronucleus immediately before the PNMBD provides an effective indicator of the embryo's potential at an early stage of development.