Development of a generally applicable morphokinetic algorithm capable of predicting the implantation potential of embryos transferred on Day 3.

Can a generally applicable morphokinetic algorithm suitable for Day 3 transfers of time-lapse monitored embryos originating from different culture conditions and fertilization methods be developed for the purpose of supporting the embryologist's decision on which embryo to transfer back to the patient in assisted reproduction? The algorithm presented here can be used independently of culture conditions and fertilization method and provides predictive power not surpassed by other published algorithms for ranking embryos according to their blastocyst formation potential. Generally applicable algorithms have so far been developed only for predicting blastocyst formation. A number of clinics have reported validated implantation prediction algorithms, which have been developed based on clinic-specific culture conditions and clinical environment. However, a generally applicable embryo evaluation algorithm based on actual implantation outcome has not yet been reported. Retrospective evaluation of data extracted from a database of known implantation data (KID) originating from 3275 embryos transferred on Day 3 conducted in 24 clinics between 2009 and 2014. The data represented different culture conditions (reduced and ambient oxygen with various culture medium strategies) and fertilization methods (IVF, ICSI). The capability to predict blastocyst formation was evaluated on an independent set of morphokinetic data from 11 218 embryos which had been cultured to Day 5. PARTICIPANTS/MATERIALS, SETTING, The algorithm was developed by applying automated recursive partitioning to a large number of annotation types and derived equations, progressing to a five-fold cross-validation test of the complete data set and a validation test of different incubation conditions and fertilization methods. The results were expressed as receiver operating characteristics curves using the area under the curve (AUC) to establish the predictive strength of the algorithm. By applying the here developed algorithm (KIDScore), which was based on six annotations (the number of pronuclei equals 2 at the 1-cell stage, time from insemination to pronuclei fading at the 1-cell stage, time from insemination to the 2-cell stage, time from insemination to the 3-cell stage, time from insemination to the 5-cell stage and time from insemination to the 8-cell stage) and ranking the embryos in five groups, the implantation potential of the embryos was predicted with an AUC of 0.650. On Day 3 the KIDScore algorithm was capable of predicting blastocyst development with an AUC of 0.745 and blastocyst quality with an AUC of 0.679. In a comparison of blastocyst prediction including six other published algorithms and KIDScore, only KIDScore and one more algorithm surpassed an algorithm constructed on conventional Alpha/ESHRE consensus timings in terms of predictive power. Some morphological assessments were not available and consequently three of the algorithms in the comparison were not used in full and may therefore have been put at a disadvantage. Algorithms based on implantation data from Day 3 embryo transfers require adjustments to be capable of predicting the implantation potential of Day 5 embryo transfers. The current study is restricted by its retrospective nature and absence of live birth information. Prospective Randomized Controlled Trials should be used in future studies to establish the value of time-lapse technology and morphokinetic evaluation. Algorithms applicable to different culture conditions can be developed if based on large data sets of heterogeneous origin. This study was funded by Vitrolife A/S, Denmark and Vitrolife AB, Sweden. B.M.P.'s company BMP Analytics is performing consultancy for Vitrolife A/S. M.B. is employed at Vitrolife A/S. M.M.'s company ilabcomm GmbH received honorarium for consultancy from Vitrolife AB. D.K.G. received research support from Vitrolife AB.

Petersen BM ，Boel M ，Montag M ，Gardner DK ... -  《-》

Clinical validation of an automatic classification algorithm applied on cleavage stage embryos: analysis for blastulation, euploidy, implantation, and live-birth potential.

Is a commercially available embryo assessment algorithm for early embryo evaluation based on the automatic annotation of morphokinetic timings a useful tool for embryo selection in IVF cycles? The classification provided by the algorithm was shown to be significantly predictive, especially when combined with conventional morphological evaluation, for development to blastocyst, implantation, and live birth, but not for euploidy. The gold standard for embryo selection is still morphological evaluation conducted by embryologists. Since the introduction of time-lapse technology to embryo culture, many algorithms for embryo selection have been developed based on embryo morphokinetics, providing complementary information to morphological evaluation. However, manual annotations of developmental events and application of algorithms can be time-consuming and subjective processes. The introduction of automation to morphokinetic annotations is a promising approach that can potentially reduce subjectivity in the embryo selection process and improve the workflow in IVF laboratories. This observational, retrospective cohort study was performed in a single IVF clinic between 2018 and 2021 and included 3736 embryos from oocyte donation cycles (423 cycles) and 1291 embryos from autologous cycles with preimplantation genetic testing for aneuploidies (PGT-A, 185 cycles). Embryos were classified on Day 3 with a score from 1 (best) to 5 (worst) by the automatic embryo assessment algorithm. The performance of the embryo classification model for blastocyst development, implantation, live birth, and euploidy prediction was assessed. All embryos were monitored by a time-lapse system with an automatic cell-tracking and embryo assessment software during culture. The embryo assessment algorithm was applied on Day 3, resulting in embryo classification from 1 to 5 (from highest to lowest developmental potential) depending on four parameters: P2 (t3-t2), P3 (t4-t3), oocyte age, and number of cells. There were 959 embryos selected for transfer on Day 5 or 6 based on conventional morphological evaluation. The blastocyst development, implantation, live birth, and euploidy rates (for embryos subjected to PGT-A) were compared between the different scores. The correlation of the algorithm scoring with the occurrence of those outcomes was quantified by generalized estimating equations (GEEs). Finally, the performance of the GEE model using the embryo assessment algorithm as the predictor was compared to that using conventional morphological evaluation, as well as to a model using a combination of both classification systems. The blastocyst rate was higher with lower the scores generated by the embryo assessment algorithm. A GEE model confirmed the positive association between lower embryo score and higher odds of blastulation (odds ratio (OR) (1 vs 5 score) = 15.849; P < 0.001). This association was consistent in both oocyte donation and autologous embryos subjected to PGT-A. The automatic embryo classification results were also statistically associated with implantation and live birth. The OR of Score 1 vs 5 was 2.920 (95% CI 1.440-5.925; P = 0.003; E = 2.81) for implantation and 3.317 (95% CI 1.615-6.814; P = 0.001; E = 3.04) for live birth. However, this association was not found in embryos subjected to PGT-A. The highest performance was achieved when combining the automatic embryo scoring and traditional morphological classification (AUC for implantation potential = 0.629; AUC for live-birth potential = 0.636). Again, no association was found between the embryo classification and euploidy status in embryos subjected to PGT-A (OR (1 vs 5) = 0.755 (95% CI 0.255-0.981); P = 0.489; E = 1.57). The retrospective nature of this study may be a reason for caution, although the large sample size reinforced the ability of the model for embryo selection. Time-lapse technology with automated embryo assessment can be used together with conventional morphological evaluation to increase the accuracy of embryo selection process and improve the success rates of assisted reproduction cycles. To our knowledge, this is the largest embryo dataset analysed with this embryo assessment algorithm. This research was supported by Agencia Valenciana de Innovació and European Social Fund (ACIF/2019/264 and CIBEFP/2021/13). In the last 5 years, M.M. received speaker fees from Vitrolife, Merck, Ferring, Gideon Richter, Angelini, and Theramex, and B.A.-R. received speaker fees from Merck. The remaining authors have no competing interests to declare. N/A.

Valera MA ，Aparicio-Ruiz B ，Pérez-Albalá S ，Romany L ，Remohí J ，Meseguer M ... -  《-》

Correlation between aneuploidy, standard morphology evaluation and morphokinetic development in 1730 biopsied blastocysts: a consecutive case series study.

Are there correlations among human blastocyst ploidy status, standard morphology evaluation and time-lapse kinetics? Correlations were observed, in that euploid human blastocysts showed a higher percentage with top quality inner cell mass (ICM) and trophectoderm (TE), higher expansion grades and shorter time to start of blastulation, expansion and hatching, compared to aneuploid ones. Embryo quality has always been considered an important predictor of successful implantation and pregnancy. Nevertheless, knowledge of the relative impact of each morphological parameter at the blastocyst stage needs to be increased. Recently, with the introduction of time-lapse technology, morphokinetic parameters can also be evaluated. However, a large number of studies has reported conflicting outcomes. This was a consecutive case series study. The morphology of 1730 blastocysts obtained in 530 PGS cycles performed from September 2012 to April 2014 that underwent TE biopsy and array comparative genomic hybridization was analyzed retrospectively. A total of 928 blastocysts were cultured in a time-lapse incubator allowing morphokinetic parameters to be analyzed. Mean female age was 36.8 ± 4.24 years. Four hunderd fifty-four couples were enrolled in the study: 384, 64 and 6 of them performed single, double or triple PGS cycles, respectively. In standard morphology evaluation, the expansion grade, and quality of the ICM and TE were analyzed. The morphokinetic parameters observed were second polar body extrusion, appearance of two pronuclei, pronuclear fading, onset of two- to eight-cell divisions, time between the two- and three-cell (cc2) and three- and four-cell (s2) stages, morulae formation time, starting blastulation, full blastocyst stage, expansion and hatching timing. Of the 1730 biopsied blastocysts, 603 were euploid and 1127 aneuploid. We observed that 47.2% of euploid and 32.8% of aneuploid blastocysts showed top quality ICM (P < 0.001), and 17.1% of euploid and 28.5% of aneuploid blastocysts showed poor quality ICM (P < 0.001). Top quality TE was present in 46.5% of euploid and 31.1% of aneuploid blastocysts (P < 0.001), while 26.6% of euploid and 38.1% of aneuploid blastocysts showed poor quality TE (P < 0.001). Regarding expansion grade, 81.1% of euploid and 72.4% of aneuploid blastocysts were fully expanded (Grade 5-6; P < 0.001). The timing of cleavage from the three- to four-cell stage, of reaching four-cell stage, of starting blastulation, reaching full blastocyst stage, blastocyst expansion and hatching were 2.6 (95% confidence interval (CI): 1.7-3.5), 40.0 (95% CI: 39.3-40.6), 103.4 (95% CI: 102.2-104.6), 110.2 (95% CI: 108.8-111.5), 118.7 (95% CI: 117.0-120.5) and 133.2 (95% CI: 131.2-135.2) hours in euploid blastocysts, and 4.2 (95% CI: 3.6-4.8), 41.1 (95% CI: 40.6-41.6), 105.0 (95% CI: 104.0-106.0), 112.8 (95% CI: 111.7-113.9), 122.1 (95% CI: 120.7-123.4) and 137.4 (95% CI: 135.7-139.1) hours in aneuploid blastocysts (P < 0.05 for early and P < 0.0001 for later stages of development), respectively. No statistically significant differences were found between euploid and aneuploid blastocysts for the remaining morphokinetic parameters.A total of 407 embryo transfers were performed (155 fresh, 252 frozen-thawed blastocysts). Higher clinical pregnancy, implantation and live birth rates were obtained in frozen-thawed compared to fresh embryo transfers (P = 0.0104, 0.0091 and 0.0148, respectively). The miscarriage rate was 16.1% and 19.6% in cryopreserved and fresh embryo transfer, respectively. The mean female age was lower in the euploid compared to aneuploid groups (35.0 ± 3.78 versus 36.7 ± 4.13 years, respectively), We found an increasing probability for aneuploidy with female age of 10% per year (odds ratio (OR) = 1.1, 95% CI: 1.1-1.2, P < 0.001). The main limitation of morphology assessment is that it is a static system and can be operator-dependent. In this study, eight embryologists performed morphology assessments. The main limitation of the time-lapse technology is that it is impossible to rotate the embryos making it very difficult to observe them in case of blastomere overlapping or increased cytoplasmic fragmentation. Although there seems to be a relationship between the ploidy status and blastocyst morphology/development dynamics, the evaluation of morphological and morphokinetic parameters cannot currently be improved upon, and therefore replace, PGS. Our results on ongoing pregnancy and miscarriage rates suggest that embryo evaluation by PGS or time-lapse imaging may not improve IVF outcome. However, time-lapse monitoring could be used in conjunction with PGS to choose, within a cohort, the blastocysts to analyze or, when more than one euploid blastocyst is available, to select which one should be transferred. No specific funding was obtained for this study. None of the authors have any competing interests to declare.

Minasi MG ，Colasante A ，Riccio T ，Ruberti A ，Casciani V ，Scarselli F ，Spinella F ，Fiorentino F ，Varricchio MT ，Greco E ... -  《-》

Time-lapse deselection model for human day 3 in vitro fertilization embryos: the combination of qualitative and quantitative measures of embryo growth.

To present a time-lapse deselection model involving both qualitative and quantitative parameters for assessing embryos on day 3. Retrospective cohort study and prospective validation. Private IVF center. A total of 270 embryos with known implantation data (KID) after day 3 transfer from 212 IVF/intracytoplasmic sperm injection (ICSI) cycles were retrospectively analyzed for building the proposed deselection model, followed by prospective validation using an additional 66 KID embryos. None. Morphological score on day 3, embryo morphokinetic parameters, abnormal cleavage patterns, and known implantation results. All included embryos were categorized either retrospectively or prospectively into 7 grades (A+, A, B, C, D, E, F). Qualitative deselection parameters included poor conventional day 3 morphology, abnormal cleavage patterns identified via time-lapse monitoring, and <8 cells at 68 hours postinsemination. Quantitative parameters included time from pronuclear fading (PNF) to 5-cell stage and duration of 3-cell stage. KID implantation rates of embryos graded from A+ to F were 52.9%, 36.1%, 25.0%, 13.8%, 15.6%, 3.1%, and 0 respectively (area under the curve [AUC] = 0.762; 95% confidence interval [CI], 0.701-0.824), and a similar pattern was seen in either IVF (AUC = 0.721; 95% CI, 0.622-0.821) or ICSI embryos (AUC = 0.790; 95% CI, 0.711-0.868). Preliminary prospective validation using 66 KID embryos also showed statistically significant prediction in Medicult (AUC = 0.750; 95% CI, 0.588-0.912) and Vitrolife G-Series (AUC = 0.820; 95% CI, 0.671-0.969) suites of culture media. The proposed model involving both qualitative and quantitative deselection effectively predicts day 3 embryo implantation potential and is applicable to all IVF embryos regardless of insemination method by using PNF as the reference starting time point.

Liu Y ，Chapple V ，Feenan K ，Roberts P ，Matson P ... -  《-》

Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer.

Can a deep learning model predict the probability of pregnancy with fetal heart (FH) from time-lapse videos? We created a deep learning model named IVY, which was an objective and fully automated system that predicts the probability of FH pregnancy directly from raw time-lapse videos without the need for any manual morphokinetic annotation or blastocyst morphology assessment. The contribution of time-lapse imaging in effective embryo selection is promising. Existing algorithms for the analysis of time-lapse imaging are based on morphology and morphokinetic parameters that require subjective human annotation and thus have intrinsic inter-reader and intra-reader variability. Deep learning offers promise for the automation and standardization of embryo selection. A retrospective analysis of time-lapse videos and clinical outcomes of 10 638 embryos from eight different IVF clinics, across four different countries, between January 2014 and December 2018. The deep learning model was trained using time-lapse videos with known FH pregnancy outcome to perform a binary classification task of predicting the probability of pregnancy with FH given time-lapse video sequence. The predictive power of the model was measured using the average area under the curve (AUC) of the receiver operating characteristic curve over 5-fold stratified cross-validation. The deep learning model was able to predict FH pregnancy from time-lapse videos with an AUC of 0.93 [95% CI 0.92-0.94] in 5-fold stratified cross-validation. A hold-out validation test across eight laboratories showed that the AUC was reproducible, ranging from 0.95 to 0.90 across different laboratories with different culture and laboratory processes. This study is a retrospective analysis demonstrating that the deep learning model has a high level of predictability of the likelihood that an embryo will implant. The clinical impacts of these findings are still uncertain. Further studies, including prospective randomized controlled trials, are required to evaluate the clinical significance of this deep learning model. The time-lapse videos collected for training and validation are Day 5 embryos; hence, additional adjustment would need to be made for the model to be used in the context of Day 3 transfer. The high predictive value for embryo implantation obtained by the deep learning model may improve the effectiveness of previous approaches used for time-lapse imaging in embryo selection. This may improve the prioritization of the most viable embryo for a single embryo transfer. The deep learning model may also prove to be useful in providing the optimal order for subsequent transfers of cryopreserved embryos. D.T. is the co-owner of Harrison AI that has patented this methodology in association with Virtus Health. P.I. is a shareholder in Virtus Health. S.C., P.I. and D.G. are all either employees or contracted with Virtus Health. D.G. has received grant support from Vitrolife, the manufacturer of the Embryoscope time-lapse imaging used in this study. The equipment and time for this study have been jointly provided by Harrison AI and Virtus Health.

Tran D ，Cooke S ，Illingworth PJ ，Gardner DK ... -  《-》