Prediction of in-vitro fertilization outcome by ultrasound strain analysis and machine learning: A multi-center study
Keywords:
Infertility, Transvaginal ultrasound, Machine learning, Uterine contractility, Speckle trackingAbstract
Background: In-vitro-fertilization (IVF) failure rates remain above 65% with unknown causes. Uterine receptivity, largely determined by uterine peristalsis, is believed to play a key role in the IVF success. Accurate assessment of uterine peristalsis holds the potential for improving the success rate of embryo implantation.
Methods: This prospective study includes 62 IVF patients from multiple fertility centers under three different clinical settings. Four-minute B-mode transvaginal ultrasound (TVUS) scans were performed one hour before embryo transfer (ET). 25 features related to frequency, amplitude, power, velocity, and coordination were extracted using strain analysis from TVUS speckle tracking results. Three probabilistic classifiers, i.e., support vector machine (SVM), K-nearest neighbors (KNN), and adaptive boosting (AdaBoost), were employed to discriminate uterine activity as either favorable or adverse to clinical pregnancy rate. Prior to machine learning, feature selection was performed by categorized feature ranking and sequential forward selection. The proposed method was evaluated by a nested 8-fold cross validation.
Results: Our results suggest that features related to coordination and frequency of the uterine peristalsis are strongly associated with clinical pregnancy. SVM demonstrates the best classification performance between successful and unsuccessful pregnancies, with an average area under the ROC curve of 0.81.
Conclusions: We developed a machine learning framework to improve the prediction of IVF outcome based on multi-center TVUS recordings. Our SVM model identified significant uterine motion features and demonstrated reliable and generalizable classification performance. This work can provide useful means to support clinicians for clinical decision-making prior to ET and possibly enhance IVF success rates.
References
1. Fauser BC (2019) Towards the global coverage of a unified registry of IVF outcomes. Reprod Biomed Online 38:133-137. https://doi.org/10.1016/j.rbmo.2018.12.001
2. Andersen AN, Gianaroli L, Felberbaum R, De Mouzon J, Nygren KG (2006) Assisted reproductive technology in Europe, 2002. Results generated from European registers by ESHRE. Hum Reprod 21:1680-1697. https://doi.org/10.1093/humrep/del075
3. Raef B, Ferdousi R (2019) A review of machine learning approaches in assisted reproductive technologies. Acta Inform Med 27:205. https://doi.org/10.5455/aim.2019.27.205-211
4. Blank C, Wildeboer RR, DeCroo I, Tilleman K, Weyers B, De Sutter P, et al. (2019) Prediction of implantation after blastocyst transfer in in vitro fertilization: a machine-learning perspective. Fertil Steril 111:318-326. https://doi.org/10.1016/j.fertnstert.2018.10.030
5. Qiu J, Li P, Dong M, Xin X, Tan J (2019) Personalized prediction of live birth prior to the first in vitro fertilization treatment: a machine learning method. J Transl Med 17:1-8. https://doi.org/10.1186/s12967-019-2062-5
6. Zhang B, Cui Y, Wang M, Li J, Jin L, Wu D (2019) In vitro fertilization (IVF) cumulative pregnancy rate prediction from basic patient characteristics. IEEE Access 7:130460-130467. https://doi.org/10.1109/ACCESS.2019.2940588
7. Zhu L, Che HS, Xiao L, Li YP (2014) Uterine peristalsis before embryo transfer affects the chance of clinical pregnancy in fresh and frozen-thawed embryo transfer cycles. Hum Reprod 29:1238-1243. https://doi.org/10.1093/humrep/deu058
8. Kuijsters NP, Methorst WG, Kortenhorst MS, Rabotti C, Mischi M, Schoot BC (2017) Uterine peristalsis and fertility: current knowledge and future perspectives: a review and meta-analysis. Reprod Biomed Online 35:50-71. https://doi.org/10.1016/j.rbmo.2017.03.019
9. Blank C, Sammali F, Kuijsters N, Huang Y, Rabotti C, De Sutter P, et al. (2020) Assessment of uterine activity during IVF by quantitative ultrasound imaging: a pilot study. Reprod Biomed Online 41:1045-1053. https://doi.org/10.1016/j.rbmo.2020.08.006
10. Tu Z, Ran H, Zhang S, Xia G, Wang B, Wang H (2014) Molecular determinants of uterine receptivity. Int J Dev Biol 58:147-154. https://doi.org/10.1387/ijdb.130345wh
11. Pierzynski P, Reinheimer TM, Kuczynski W (2007) Oxytocin antagonists may improve infertility treatment. Fertil Steril 88:213.e19. https://doi.org/10.1016/j.fertnstert.2006.09.017
12. Pierzynski P (2011) Oxytocin and vasopressin V1A receptors as new therapeutic targets in assisted reproduction. Reprod Biomed Online 22:9-16. https://doi.org/10.1016/j.rbmo.2010.09.015
13. Moraloglu O, Tonguc E, Var T, Zeyrek T, Batıoglu S (2010) Treatment with oxytocin antagonists before embryo transfer may increase implantation rates after IVF. Reprod Biomed Online 21:338-343. https://doi.org/10.1016/j.rbmo.2010.04.009
14. Rees CO, Thomas S, de Boer A, Huang Y, Zizolfi B, Foreste V, et al. (2024) Quantitative ultrasound measurement of uterine contractility in adenomyotic versus normal uteri: a multicenter prospective study. Fertil Steril 121:864-872. https://doi.org/10.1016/j.fertnstert.2024.01.009
15. Kim SH, Kim HD, Song YS, Kang SB, Lee HP (1995) Detection of deep myometrial invasion in endometrial carcinoma: comparison of transvaginal ultrasound, CT, and MRI. J Comput Assist Tomogr 19:766-772. https://doi.org/10.1097/00004728-199509000-00013
16. Sammali F, Blank C, Xu L, Huang Y, Kuijsters NP, Schoot BC, et al. (2018) Experimental setup for objective evaluation of uterine motion analysis by ultrasound speckle tracking. Biomed Phys Eng Express 4:035012. https://doi.org/10.1088/2057-1976/aab053
17. Sammali F, Kuijsters NP, Huang Y, Blank C, Rabotti C, Schoot BC, et al. (2018) Dedicated ultrasound speckle tracking for quantitative analysis of uterine motion outside pregnancy. IEEE Trans Ultrason Ferroelectr Freq Control 66:581-590. https://doi.org/10.1109/TUFFC.2018.2867098
18. Sammali F, Blank C, Bakkes TG, Huang Y, Rabotti C, Schoot BC, et al. (2021) Multi-modal uterine-activity measurements for prediction of embryo implantation by machine learning. IEEE Access 9:47096-47111. https://doi.org/10.1109/ACCESS.2021.3067716
19. Huang Y, Rees C, Sammali F, Blank C, Schoot D, Mischi M (2022) Characterization of uterine peristaltic waves by ultrasound strain analysis. IEEE Trans Ultrason Ferroelectr Freq Control 69:2050-2060. https://doi.org/10.1109/TUFFC.2022.3165688
20. Zhou Y, Zheng YP (2010) A motion estimation refinement framework for real-time tissue axial strain estimation with freehand ultrasound. IEEE Trans Ultrason Ferroelectr Freq Control 57:1943-1951. https://doi.org/10.1109/TUFFC.2010.1642
21. Kim SH, Riaposova L, Ahmed H, Pohl O, Chollet A, Gotteland JP, et al. (2019) Oxytocin receptor antagonists, atosiban and nolasiban, inhibit prostaglandin F2α-induced contractions and inflammatory responses in human myometrium. Sci Rep 9:1-10. https://doi.org/10.1038/s41598-019-42181-2
22. Balaban B, Brison D, Calderon G, Catt J, Conaghan J, Cowan L, et al. (2011) Istanbul consensus workshop on embryo assessment: proceedings of an expert meeting. Reprod Biomed Online 22:632-646. http://doi.org/10.1016/j.rbmo.2011.02.001
23. Griesinger G, Blockeel C, Pierzynski P, Tournaye H, Višňová H, Humberstone A, et al. (2021) Effect of the oxytocin receptor antagonist nolasiban on pregnancy rates in women undergoing embryo transfer following IVF: analysis of three randomised clinical trials. Hum Reprod 36:1007-1020. https://doi.org/10.1093/humrep/deaa369
24. Lucas BD, Kanade T (1981) An iterative image registration technique with an application to stereo vision. In: IJCAI’81: 7th Int Joint Conf Artif Intell 2:674-679.
25. Lawrence I, Lin K (1989) A concordance correlation coefficient to evaluate reproducibility. Biometrics 45:255-268. https://doi.org/10.2307/2532051
26. Wilcoxon F (1992) Individual comparisons by ranking methods. In: Breakthroughs in Statistics: Methodology and Distribution. Springer, New York, pp 196-202. https://doi.org/10.1007/978-1-4612-4380-9_16
27. Marcano-Cedeño A, Quintanilla-Domínguez J, Cortina-Januchs MG, Andina D (2010) Feature selection using sequential forward selection and classification applying artificial metaplasticity neural network. In: IECON 2010 – 36th Annu Conf IEEE Ind Electron Soc. pp 2845-2850. https://doi.org/10.1109/IECON.2010.5675075
28. Kourou K, Exarchos TP, Exarchos KP, Karamouzis MV, Fotiadis DI (2015) Machine learning applications in cancer prognosis and prediction. Comput Struct Biotechnol J 13:8-17. https://doi.org/10.1016/j.csbj.2014.11.005
29. Hofmann T, Schölkopf B, Smola AJ (2006) A review of kernel methods in machine learning. Max Planck Inst Tech Rep 156.
30. Hsu CW, Chang CC, Lin CJ (2003) A practical guide to support vector classification. Dept Comput Sci, Natl Taiwan Univ.
31. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55:119-139. https://doi.org/10.1006/jcss.1997.1504
32. Li X, Wang L, Sung E (2005) A study of AdaBoost with SVM based weak learners. In: Proc 2005 IEEE Int Joint Conf Neural Netw 1:196-201. https://doi.org/10.1109/IJCNN.2005.1555829
33. Wang CW, Kuo CY, Chen CH, Hsieh YH, Su EC (2022) Predicting clinical pregnancy using clinical features and machine learning algorithms in in vitro fertilization. PLoS One 17(6):e0267554. https://doi.org/10.1371/journal.pone.0267554
34. Tsamardinos I, Rakhshani A, Lagani V (2015) Performance-estimation properties of cross-validation-based protocols with simultaneous hyper-parameter optimization. Int J Artif Intell Tools 24:1540023. https://doi.org/10.1142/S0218213015400230
35. de Boer A, Rees CO, Mischi M, Van Vliet H, Huirne J, Schoot BC (2023) The influence of uterine abnormalities on uterine peristalsis in the non-pregnant uterus: a systematic review. J Endometr Uterine Disord 100038. https://doi.org/10.1016/j.jeud.2023.100038
36. Shen D, Wu G, Suk HI (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221-248. https://doi.org/10.1146/annurev-bioeng-071516-044442
Issue
Section
License
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by-nc/4.0) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Transfer of Copyright and Permission to Reproduce Parts of Published Papers.
Authors retain the copyright for their published work. No formal permission will be required to reproduce parts (tables or illustrations) of published papers, provided the source is quoted appropriately and reproduction has no commercial intent. Reproductions with commercial intent will require written permission and payment of royalties.
How to Cite
