Novel and conventional embryo parameters as input data for artificial neural networks: an artificial intelligence model applied for prediction of the implantation potential

[ES] Objetivo: Describir nuevas características de embriones capaces de predecir el potencial de implantación como datos de entrada para un modelo de red neuronal artificial (ANN). Diseño: Estudio de cohorte retrospectivo. Entorno: Centro de FIV privado afiliado a la universidad. Paciente (s): Este estudio incluyó a 637 pacientes del programa de donación de ovocitos que se sometieron a transferencia de un solo blastocisto durante dos años consecutivos. Intervención (es): Ninguna. Principales medidas de resultado: La investigación se dividió en dos fases. La fase 1 consistió en la descripción y análisis de las siguientes características embrionarias en embriones implantados y no implantados: distancia y velocidad de migración pronuclear, diámetro del blastocisto expandido, área de masa celular interna y duración del ciclo celular del trofoectodermo. La fase 2 consistió en el desarrollo de un algoritmo ANN para la predicción de la implantación. Se obtuvieron resultados para cuatro modelos alimentados con diferentes datos de entrada. El poder predictivo se midió con el uso del área bajo la curva característica operativa del receptor (AUC). Resultado (s): De los cinco nuevos parámetros descritos, el diámetro expandido del blastocisto y la duración del ciclo celular del trofoectodermo tenían valores estadísticamente diferentes en los embriones implantados y no implantados. Después de que los modelos ANN fueron entrenados y validados mediante validación cruzada cinco veces, estos fueron capaces de predecir la implantación en los datos de prueba con AUC de 0,64 para ANN1 (morfocinética convencional), 0,73 para ANN2 (morfodinámica novedosa), 0,77 para ANN3 (morfocinética convencional þ morfodinámica novedosa) y 0,68 para ANN4 (variables discriminatorias de prueba estadística). Conclusión (es): Las nuevas características embrionarias propuestas afectan al potencial de implantación y su combinación con parámetros morfocinéticos convencionales es eficaz como datos de entrada para un modelo predictivo basado en inteligencia artificial.[EN] Objective: To describe novel embryo features capable of predicting implantation potential as input data for an artificial neural network (ANN) model. Design: Retrospective cohort study. Setting: University-affiliated private IVF center. Patient(s): This study included 637 patients from the oocyte donation program who underwent single-blastocyst transfer during two consecutive years. Intervention(s): None. Main Outcome Measure(s): The research was divided into two phases. Phase 1 consisted of the description and analysis of the following embryo features in implanted and nonimplanted embryos: distance and speed of pronuclear migration, blastocyst expanded diameter, inner cell mass area, and trophectoderm cell cycle length. Phase 2 consisted of the development of an ANN algorithm for implantation prediction. Results were obtained for four models fed with different input data. The predictive power was measured with the use of the area under the receiver operating characteristic curve (AUC). Result(s): Out of the five novel described parameters, blastocyst expanded diameter and trophectoderm cell cycle length had statistically different values in implanted and nonimplanted embryos. After the ANN models were trained and validated using fivefold cross validation, they were capable of predicting implantation on testing data with AUCs of 0.64 for ANN1 (conventional morphokinetics), 0.73 for ANN2 (novel morphodynamics), 0.77 for ANN3 (conventional morphokinetics thorn novel morphodynamics), and 0.68 for ANN4 (discriminatory variables from statistical test). Conclusion(s): The novel proposed embryo features affect the implantation potential, and their combination with conventional morphokinetic parameters is effective as input data for a predictive model based on artificial intelligence. ((c) 2020 by American Society for Reproductive Medicine.)Supported by the Ministry of Science, Innovation, and Universities CDTI (IDI-20191102), an Industrial Ph.D. grant (DIN2018-009911), and Agencia Valenciana de Innovacio (INNCAD00-18-009) to E.P. and M.M.Bori, L.; Paya-Bosch, E.; Alegre, L.; Viloria, T.; Remohí, J.; Naranjo Ornedo, V.; Meseguer, M. (2020). Novel and conventional embryo parameters as input data for artificial neural networks: an artificial intelligence model applied for prediction of the implantation potential. Fertility and Sterility. 114(6):1232-1241. https://doi.org/10.1016/j.fertnstert.2020.08.023123212411146De Geyter, C., Calhaz-Jorge, C., Kupka, M. S., Wyns, C., Mocanu, E., Motrenko, T., … Goossens, V. (2018). ART in Europe, 2014: results generated from European registries by ESHRE†. Human Reproduction, 33(9), 1586-1601. doi:10.1093/humrep/dey242Edwards, R. G., Fishel, S. B., Cohen, J., Fehilly, C. B., Purdy, J. M., Slater, J. M., … Webster, J. M. (1984). Factors influencing the success of in vitro fertilization for alleviating human infertility. Journal of In Vitro Fertilization and Embryo Transfer, 1(1), 3-23. doi:10.1007/bf01129615Ferraretti, A. P., Goossens, V., de Mouzon, J., Bhattacharya, S., Castilla, J. A., … Korsak, V. (2012). Assisted reproductive technology in Europe, 2008: results generated from European registers by ESHRE†. Human Reproduction, 27(9), 2571-2584. doi:10.1093/humrep/des255Zhang, J. Q., Li, X. L., Peng, Y., Guo, X., Heng, B. C., & Tong, G. Q. (2010). Reduction in exposure of human embryos outside the incubator enhances embryo quality and blastulation rate. Reproductive BioMedicine Online, 20(4), 510-515. doi:10.1016/j.rbmo.2009.12.027Cruz, M., Garrido, N., Herrero, J., Pérez-Cano, I., Muñoz, M., & Meseguer, M. (2012). Timing of cell division in human cleavage-stage embryos is linked with blastocyst formation and quality. Reproductive BioMedicine Online, 25(4), 371-381. doi:10.1016/j.rbmo.2012.06.017Kirkegaard, K., Agerholm, I. E., & Ingerslev, H. J. (2012). Time-lapse monitoring as a tool for clinical embryo assessment. Human Reproduction, 27(5), 1277-1285. doi:10.1093/humrep/des079Montag, M., Liebenthron, J., & Köster, M. (2011). Which morphological scoring system is relevant in human embryo development? Placenta, 32, S252-S256. doi:10.1016/j.placenta.2011.07.009Aparicio, B., Cruz, M., & Meseguer, M. (2013). Is morphokinetic analysis the answer? Reproductive BioMedicine Online, 27(6), 654-663. doi:10.1016/j.rbmo.2013.07.017Gallego, R. D., Remohí, J., & Meseguer, M. (2019). Time-lapse imaging: the state of the art†. Biology of Reproduction, 101(6), 1146-1154. doi:10.1093/biolre/ioz035Zaninovic, N., Irani, M., & Meseguer, M. (2017). Assessment of embryo morphology and developmental dynamics by time-lapse microscopy: is there a relation to implantation and ploidy? Fertility and Sterility, 108(5), 722-729. doi:10.1016/j.fertnstert.2017.10.002Athayde Wirka, K., Chen, A. A., Conaghan, J., Ivani, K., Gvakharia, M., Behr, B., … Shen, S. (2014). Atypical embryo phenotypes identified by time-lapse microscopy: high prevalence and association with embryo development. Fertility and Sterility, 101(6), 1637-1648.e5. doi:10.1016/j.fertnstert.2014.02.050Zhan, Q., Ye, Z., Clarke, R., Rosenwaks, Z., & Zaninovic, N. (2016). Direct Unequal Cleavages: Embryo Developmental Competence, Genetic Constitution and Clinical Outcome. PLOS ONE, 11(12), e0166398. doi:10.1371/journal.pone.0166398Goodman, L. R., Goldberg, J., Falcone, T., Austin, C., & Desai, N. (2016). Does the addition of time-lapse morphokinetics in the selection of embryos for transfer improve pregnancy rates? A randomized controlled trial. Fertility and Sterility, 105(2), 275-285.e10. doi:10.1016/j.fertnstert.2015.10.013Desai, N., Ploskonka, S., Goodman, L., Attaran, M., Goldberg, J. M., Austin, C., & Falcone, T. (2016). Delayed blastulation, multinucleation, and expansion grade are independently associated with live-birth rates in frozen blastocyst transfer cycles. Fertility and Sterility, 106(6), 1370-1378. doi:10.1016/j.fertnstert.2016.07.1095Aguilar, J., Rubio, I., Muñoz, E., Pellicer, A., & Meseguer, M. (2016). Study of nucleation status in the second cell cycle of human embryo and its impact on implantation rate. Fertility and Sterility, 106(2), 291-299.e2. doi:10.1016/j.fertnstert.2016.03.036Rubio, I., Kuhlmann, R., Agerholm, I., Kirk, J., Herrero, J., Escribá, M.-J., … Meseguer, M. (2012). Limited implantation success of direct-cleaved human zygotes: a time-lapse study. Fertility and Sterility, 98(6), 1458-1463. doi:10.1016/j.fertnstert.2012.07.1135Desai, N., Ploskonka, S., Goodman, L. R., Austin, C., Goldberg, J., & Falcone, T. (2014). Analysis of embryo morphokinetics, multinucleation and cleavage anomalies using continuous time-lapse monitoring in blastocyst transfer cycles. Reproductive Biology and Endocrinology, 12(1), 54. doi:10.1186/1477-7827-12-54Ebner, T., Höggerl, A., Oppelt, P., Radler, E., Enzelsberger, S.-H., Mayer, R. B., … Shebl, O. (2017). Time-lapse imaging provides further evidence that planar arrangement of blastomeres is highly abnormal. Archives of Gynecology and Obstetrics, 296(6), 1199-1205. doi:10.1007/s00404-017-4531-5Azzarello, A., Hoest, T., Hay-Schmidt, A., & Mikkelsen, A. L. (2017). Live birth potential of good morphology and vitrified blastocysts presenting abnormal cell divisions. Reproductive Biology, 17(2), 144-150. doi:10.1016/j.repbio.2017.03.004Desch, L., Bruno, C., Luu, M., Barberet, J., Choux, C., Lamotte, M., … Fauque, P. (2017). Embryo multinucleation at the two-cell stage is an independent predictor of intracytoplasmic sperm injection outcomes. Fertility and Sterility, 107(1), 97-103.e4. doi:10.1016/j.fertnstert.2016.09.022Kirkegaard, K., Hindkjaer, J. J., Grøndahl, M. L., Kesmodel, U. S., & Ingerslev, H. J. (2012). A randomized clinical trial comparing embryo culture in a conventional incubator with a time-lapse incubator. Journal of Assisted Reproduction and Genetics, 29(6), 565-572. doi:10.1007/s10815-012-9750-xWong, C. C., Loewke, K. E., Bossert, N. L., Behr, B., De Jonge, C. J., Baer, T. M., & Pera, R. A. R. (2010). Non-invasive imaging of human embryos before embryonic genome activation predicts development to the blastocyst stage. Nature Biotechnology, 28(10), 1115-1121. doi:10.1038/nbt.1686Conaghan, J., Chen, A. A., Willman, S. P., Ivani, K., Chenette, P. E., Boostanfar, R., … Shen, S. (2013). Improving embryo selection using a computer-automated time-lapse image analysis test plus day 3 morphology: results from a prospective multicenter trial. Fertility and Sterility, 100(2), 412-419.e5. doi:10.1016/j.fertnstert.2013.04.021Milewski, R., Kuć, P., Kuczyńska, A., Stankiewicz, B., Łukaszuk, K., & Kuczyński, W. (2015). A predictive model for blastocyst formation based on morphokinetic parameters in time-lapse monitoring of embryo development. Journal of Assisted Reproduction and Genetics, 32(4), 571-579. doi:10.1007/s10815-015-0440-3Chamayou, S., Patrizio, P., Storaci, G., Tomaselli, V., Alecci, C., Ragolia, C., … Guglielmino, A. (2013). The use of morphokinetic parameters to select all embryos with full capacity to implant. Journal of Assisted Reproduction and Genetics, 30(5), 703-710. doi:10.1007/s10815-013-9992-2Milewski, R., Czerniecki, J., Kuczyńska, A., Stankiewicz, B., & Kuczyński, W. (2016). Morphokinetic parameters as a source of information concerning embryo developmental and implantation potential. Ginekologia Polska, 87(10), 677-684. doi:10.5603/gp.2016.0067Motato, Y., de los Santos, M. J., Escriba, M. J., Ruiz, B. A., Remohí, J., & Meseguer, M. (2016). Morphokinetic analysis and embryonic prediction for blastocyst formation through an integrated time-lapse system. Fertility and Sterility, 105(2), 376-384.e9. doi:10.1016/j.fertnstert.2015.11.001Petersen, B. M., Boel, M., Montag, M., & Gardner, D. K. (2016). Development of a generally applicable morphokinetic algorithm capable of predicting the implantation potential of embryos transferred on Day 3. Human Reproduction, 31(10), 2231-2244. doi:10.1093/humrep/dew188Meseguer, M., Herrero, J., Tejera, A., Hilligsoe, K. M., Ramsing, N. B., & Remohi, J. (2011). The use of morphokinetics as a predictor of embryo implantation. Human Reproduction, 26(10), 2658-2671. doi:10.1093/humrep/der256Liu, Y., Chapple, V., Feenan, K., Roberts, P., & Matson, P. (2016). Time-lapse deselection model for human day 3 in vitro fertilization embryos: the combination of qualitative and quantitative measures of embryo growth. Fertility and Sterility, 105(3), 656-662.e1. doi:10.1016/j.fertnstert.2015.11.003VerMilyea, M. D., Tan, L., Anthony, J. T., Conaghan, J., Ivani, K., Gvakharia, M., … Shen, S. (2014). Computer-automated time-lapse analysis results correlate with embryo implantation and clinical pregnancy: A blinded, multi-centre study. Reproductive BioMedicine Online, 29(6), 729-736. doi:10.1016/j.rbmo.2014.09.005Basile, N., Vime, P., Florensa, M., Aparicio Ruiz, B., García Velasco, J. A., Remohí, J., & Meseguer, M. (2014). The use of morphokinetics as a predictor of implantation: a multicentric study to define and validate an algorithm for embryo selection. Human Reproduction, 30(2), 276-283. doi:10.1093/humrep/deu331Aparicio-Ruiz, B., Romany, L., & Meseguer, M. (2018). Selection of preimplantation embryos using time-lapse microscopy in in vitro fertilization: State of the technology and future directions. Birth Defects Research, 110(8), 648-653. doi:10.1002/bdr2.1226Barrie, A., Homburg, R., McDowell, G., Brown, J., Kingsland, C., & Troup, S. (2017). Preliminary investigation of the prevalence and implantation potential of abnormal embryonic phenotypes assessed using time-lapse imaging. Reproductive BioMedicine Online, 34(5), 455-462. doi:10.1016/j.rbmo.2017.02.011Campbell, A., Fishel, S., Bowman, N., Duffy, S., Sedler, M., & Hickman, C. F. L. (2013). Modelling a risk classification of aneuploidy in human embryos using non-invasive morphokinetics. Reproductive BioMedicine Online, 26(5), 477-485. doi:10.1016/j.rbmo.2013.02.006Desai, N., Goldberg, J. M., Austin, C., & Falcone, T. (2018). Are cleavage anomalies, multinucleation, or specific cell cycle kinetics observed with time-lapse imaging predictive of embryo developmental capacity or ploidy? Fertility and Sterility, 109(4), 665-674. doi:10.1016/j.fertnstert.2017.12.025Amir, H., Barbash-Hazan, S., Kalma, Y., Frumkin, T., Malcov, M., Samara, N., … Ben-Yosef, D. (2018). Time-lapse imaging reveals delayed development of embryos carrying unbalanced chromosomal translocations. Journal of Assisted Reproduction and Genetics, 36(2), 315-324. doi:10.1007/s10815-018-1361-8Del Carmen Nogales, M., Bronet, F., Basile, N., Martínez, E. M., Liñán, A., Rodrigo, L., & Meseguer, M. (2017). Type of chromosome abnormality affects embryo morphology dynamics. Fertility and Sterility, 107(1), 229-235.e2. doi:10.1016/j.fertnstert.2016.09.019Dyer, S., Chambers, G. M., de Mouzon, J., Nygren, K. G., Zegers-Hochschild, F., Mansour, R., … Adamson, G. D. (2016). International Committee for Monitoring Assisted Reproductive Technologies world report: Assisted Reproductive Technology 2008, 2009 and 2010. Human Reproduction, 31(7), 1588-1609. doi:10.1093/humrep/dew082Simopoulou, M., Sfakianoudis, K., Maziotis, E., Antoniou, N., Rapani, A., Anifandis, G., … Koutsilieris, M. (2018). Are computational applications the «crystal ball» in the IVF laboratory? The evolution from mathematics to artificial intelligence. Journal of Assisted Reproduction and Genetics, 35(9), 1545-1557. doi:10.1007/s10815-018-1266-6Milewski, R., Kuczyńska, A., Stankiewicz, B., & Kuczyński, W. (2017). How much information about embryo implantation potential is included in morphokinetic data? A prediction model based on artificial neural networks and principal component analysis. Advances in Medical Sciences, 62(1), 202-206. doi:10.1016/j.advms.2017.02.001Curchoe, C. L., & Bormann, C. L. (2019). Artificial intelligence and machine learning for human reproduction and embryology presented at ASRM and ESHRE 2018. Journal of Assisted Reproduction and Genetics, 36(4), 591-600. doi:10.1007/s10815-019-01408-xTran, D., Cooke, S., Illingworth, P. J., & Gardner, D. K. (2019). Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer. Human Reproduction, 34(6), 1011-1018. doi:10.1093/humrep/dez064Khosravi, P., Kazemi, E., Zhan, Q., Malmsten, J. E., Toschi, M., Zisimopoulos, P., … Hajirasouliha, I. (2019). Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization. npj Digital Medicine, 2(1). doi:10.1038/s41746-019-0096-yCerrillo, M., Herrero, L., Guillén, A., Mayoral, M., & García-Velasco, J. A. (2017). Impact of Endometrial Preparation Protocols for Frozen Embryo Transfer on Live Birth Rates. Rambam Maimonides Medical Journal, 8(2), e0020. doi:10.5041/rmmj.10297Panchal, G., Ganatra, A., Kosta, Y. P., & Panchal, D. (2011). Behaviour Analysis of Multilayer Perceptronswith Multiple Hidden Neurons and Hidden Layers. International Journal of Computer Theory and Engineering, 332-337. doi:10.7763/ijcte.2011.v3.328Azzarello, A., Hoest, T., & Mikkelsen, A. L. (2012). The impact of pronuclei morphology and dynamicity on live birth outcome after time-lapse culture. Human Reproduction, 27(9), 2649-2657. doi:10.1093/humrep/des210Dal Canto, M., Coticchio, G., Mignini Renzini, M., De Ponti, E., Novara, P. V., Brambillasca, F., … Fadini, R. (2012). Cleavage kinetics analysis of human embryos predicts development to blastocyst and implantation. Reproductive BioMedicine Online, 25(5), 474-480. doi:10.1016/j.rbmo.2012.07.016Barrie, A., Homburg, R., McDowell, G., Brown, J., Kingsland, C., & Troup, S. (2017). Examining the efficacy of six published time-lapse imaging embryo selection algorithms to predict implantation to demonstrate the need for the development of specific, in-house morphokinetic selection algorithms. Fertility and Sterility, 107(3), 613-621. doi:10.1016/j.fertnstert.2016.11.014Coticchio, G., Mignini Renzini, M., Novara, P. V., Lain, M., De Ponti, E., Turchi, D., … Dal Canto, M. (2017). Focused time-lapse analysis reveals novel aspects of human fertilization and suggests new parameters of embryo viability. Human Reproduction, 33(1), 23-31. doi:10.1093/humrep/dex344Aguilar, J., Motato, Y., Escribá, M. J., Ojeda, M., Muñoz, E., & Meseguer, M. (2014). The human first cell cycle: impact on implantation. Reproductive BioMedicine Online, 28(4), 475-484. doi:10.1016/j.rbmo.2013.11.014Barberet, J., Bruno, C., Valot, E., Antunes-Nunes, C., Jonval, L., Chammas, J., … Fauque, P. (2019). Can novel early non-invasive biomarkers of embryo quality be identified with time-lapse imaging to predict live birth? Human Reproduction, 34(8), 1439-1449. doi:10.1093/humrep/dez085Richter, K. S., Harris, D. C., Daneshmand, S. T., & Shapiro, B. S. (2001). Quantitative grading of a human blastocyst: optimal inner cell mass size and shape. Fertility and Sterility, 76(6), 1157-1167. doi:10.1016/s0015-0282(01)02870-9Shapiro, B. S., Daneshmand, S. T., Garner, F. C., Aguirre, M., & Thomas, S. (2008). Large blastocyst diameter, early blastulation, and low preovulatory serum progesterone are dominant predictors of clinical pregnancy in fresh autologous cycles. Fertility and Sterility, 90(2), 302-309. doi:10.1016/j.fertnstert.2007.06.062Almagor, M., Harir, Y., Fieldust, S., Or, Y., & Shoham, Z. (2016). Ratio between inner cell mass diameter and blastocyst diameter is correlated with successful pregnancy outcomes of single blastocyst transfers. Fertility and Sterility, 106(6), 1386-1391. doi:10.1016/j.fertnstert.2016.08.009Shapiro, B. S., Harris, D. C., & Richter, K. S. (2000). Predictive value of 72-hour blastomere cell number on blastocyst development and success of subsequent transfer based on the degree of blastocyst development. Fertility and Sterility, 73(3), 582-586. doi:10.1016/s0015-0282(99)00586-5Coello, A., Meseguer, M., Galán, A., Alegre, L., Remohí, J., & Cobo, A. (2017). Analysis of the morphological dynamics of blastocysts after vitrification/warming: defining new predictive variables of implantation. Fertility and Sterility, 108(4), 659-666.e4. doi:10.1016/j.fertnstert.2017.07.1157Huang, T. T., Huang, D. H., Ahn, H. J., Arnett, C., & Huang, C. T. (2019). Early blastocyst expansion in euploid and aneuploid human embryos: evidence for a non-invasive and quantitative marker for embryo selection. Reproductive BioMedicine Online, 39(1), 27-39. doi:10.1016/j.rbmo.2019.01.010Sundvall, L., Ingerslev, H. J., Breth Knudsen, U., & Kirkegaard, K. (2013). Inter- and intra-observer variability of time-lapse annotations. Human Reproduction, 28(12), 3215-3221. doi:10.1093/humrep/det36