Embryo Ranking Intelligent Classification Algorithm (ERICA): Artificial Intelligence Clinical Assistant Predicting Embryo Ploidy and Implantation

Chavez-Badiola et al., 2020

---

Abstract

Research question 

Can a deep machine learning artificial intelligence algorithm predict ploidy and implantation in a known data set of static blastocyst images, and how does its performance compare against chance and experienced embryologists?

Design

A database of blastocyst images with known outcome was applied with an algorithm dubbed ERICA (Embryo Ranking Intelligent Classification Algorithm). It was evaluated against its ability to predict euploidy, compare ploidy prediction against randomly assigned prognosis labels and against senior embryologists, and if it could rank an euploid embryo highly.

Results

A total of 1231 embryo images were classed as good prognosis if euploid and implanted or poor prognosis if aneuploid and failed to implant. An accuracy of 0.70 was obtained with ERICA, with positive predictive value of 0.79 for predicting euploidy. ERICA had greater normalized discontinued cumulative gain (ranking metric) than random selection (P = 0.0007), and both embryologists (P = 0.0014 and 0.0242, respectively). ERICA ranked an euploid blastocyst first in 78.9% and at least one euploid embryo within the top two blastocysts in 94.7% of cases, better than random classification and the two senior embryologists. Average embryo ranking time for four blastocysts was under 25 s.

Conclusion

Artificial intelligence lends itself well to image pattern recognition. We have trained ERICA to rank embryos based on ploidy and implantation potential using single static embryo image. This tool represents a potentially significant advantage to assist embryologists to choose the best embryo, saving time spent annotating and does not require time lapse or invasive biopsy. Future work should be directed to evaluate reproducibility in different data sets.

KEY WORDS

Artificial intelligence • Deep machine-learning • Embryo ranking • Embryo selection • ERICA • Noninvasive embryo assessment

• References

  1. Adolfsson, E. ∙ Andershed, A.N. Morphology vs morphokinetics: a retrospective comparison of interobserver and intra-observer agreement between embryologists on blastocysts with known implantation outcome. JBRA Assist. Reprod. 2018;

  2. Armstrong, S. ∙ Bhide, P. ∙ Jordan, V. ... Time-lapse systems for embryo incubation and assessment in assisted reproduction. Cochrane Database Syst. Rev. 2019;

  3. Bormann, C.L. ∙ Thirumalaraju, P. ∙ Kanakasabapathy, M.K. ... Consistency and objectivity of automated embryo assessments using deep neural networks. Fertil. Steril. 2020; 113(4):781-787.e1.

  4. Chavez-Badiola, A. ∙ Flores-Saiffe Farias, A. ∙ Mendizabal-Ruiz, G. ... Predicting pregnancy test results after embryo transfer by image feature extraction and analysis using machine learning. Sci. Rep. 2020; 10:4394.

  5. Gardner, D.K. ∙ Schoolcraft, W.B. In vitro culture of human blastocysts. In: Jansen, R. ∙ Mortimer, D. (Editors). Toward Reproductive Certainty: Fertility and Genetics Beyond. Parthenon Publishing, Carnforth, UK, 1999; 378-388.

  6. Green, K.A. ∙ Patounakis, G. ∙ DeCherney, A. ... Day 3 embryo transfer (ET) versus pushing to day 5 in patients with few embryos. Fertil. Steril. 2016; 106:e165.

  7. Hatırnaz, Ş. ∙ Kanat Pektaş, M. Day 3 embryo transfer versus day 5 blastocyst transfers: A prospective randomized controlled trial. J. Turkish Soc. Obstet. Gynecol. 2017; 14:82-88.

  8. Huang, L. ∙ Bogale, B. ∙ Tang, Y. ... Noninvasive preimplantation genetic testing for aneuploidy in spent medium may be more reliable than trophectoderm biopsy. Proc. Natl. Acad. Sci. 2019; 116(28):14105-14112.

  9. Järvelin, K. ∙ Kekäläinen, J. Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst. 2002; 20:422-446.

  10. Khosravi, P. ∙ Kazemi, E. ∙ Zhan, Q. ... Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization. npj Digit. Med. 2019; 2:21.

  11. Kieslinger, D.C. ∙ De Gheselle, S. ∙ Lambalk, C.B. ... Embryo selection using time-lapse analysis (Early Embryo Viability Assessment) in conjunction with standard morphology: a prospective two-center pilot study. Hum. Reprod. 2016; 31:2450-2457.

  12. Liang, B. ∙ Gao, Y. ∙ Xu, J. ... Raman profiling of embryo culture medium to identify aneuploid and euploid embryos. Fertil. Steril. 2019; 111:753-762.e1.

  13. Liu, Y. ∙ Chen, P.-H.C. ∙ Krause, J. ... How to Read Articles That Use Machine Learning. JAMA. 2019; 322(18):1806.

  14. Lobo, J.M. ∙ Jiménez-Valverde, A. ∙ Real, R. AUC: a misleading measure of the performance of predictive distribution models. Glob. Ecol. Biogeogr. 2008; 17:145-151.

  15. Munné, S. ∙ Kaplan, B. ∙ Frattarelli, J.L. ... Preimplantation genetic testing for aneuploidy versus morphology as selection criteria for single frozen-thawed embryo transfer in good-prognosis patients: a multicenter randomized clinical trial. Fertil. Steril. 2019;

  16. Munne, S. ∙ Kaplan, B. ∙ Frattarelli, J.L. ... Global multicenter randomized controlled trial comparing single embryo transfer with embryo selected by preimplantation genetic screening using next-generation sequencing versus morphologic assessment. Fertil. Steril. 2017; 108:e19.

  17. Patounakis, G. ∙ Hill, M.J. The preimplantation genetic testing debate continues: first the hype, then the tension, now the hypertension. Fertil. Steril. 2019; 112:233-234.

  18. Pool, T.B. ∙ Schoolfield, J. ∙ Han, D. Human embryo culture media comparisons. Methods Mol. Biol. 2012; 912:367-386.

  19. Popescu, F. ∙ Jaslow, C.R. ∙ Kutteh, W.H. Recurrent pregnancy loss evaluation combined with 24-chromosome microarray of miscarriage tissue provides a probable or definite cause of pregnancy loss in over 90% of patients. Hum. Reprod. 2018; 33:579-587.

  20. Saito, T. ∙ Rehmsmeier, M. The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. Brock G (ed). PLoS One. 2015; 10, e0118432.

  21. Tran, D. ∙ Cooke, S. ∙ Illingworth, P.J. ... Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer. Hum. Reprod. 2019; 34:1011-1018.

  22. Verpoest, W. ∙ Staessen, C. ∙ Bossuyt, P.M. ... Preimplantation genetic testing for aneuploidy by microarray analysis of polar bodies in advanced maternal age: a randomized clinical trial. Hum. Reprod. 2018; 33:1767-1776.

  23. Weissman, A. ∙ Shoham, G. ∙ Shoham, Z. ... Preimplantation genetic screening: results of a worldwide web-based survey. Reprod. Biomed. Online. 2017; 35:693-700.

  24. Zhang, W.Y. ∙ von Versen-Höynck, F. ∙ Kapphahn, K.I. ... Maternal and neonatal outcomes associated with trophectoderm biopsy. Fertil. Steril. 2019; 112:283-290.e2.

Key Message

An artificial intelligence model, ERICA, was tested on its ability to predict euploidy. ERICA can assist embryologists in the embryo selection process by successfully ranking blastocysts based on its accuracy to predict ploidy and pregnancy results, without the need for time-lapse incubators or invasive preimplantation genetic testing for aneuploidy.