深度学习在体外受精胚胎优选中的应用

doi:10.12280/gjszjk.20220553

摘要/Abstract

摘要：

挑选移植胚胎对提高体外受精-胚胎移植周期成功率至关重要。当前最常用的挑选胚胎方法是胚胎形态学评估，其高度依赖于实验室技术人员的主观视觉印象和个人经验，影响胚胎优选的准确性和一致性。近年有学者尝试将深度学习算法引入移植胚胎的选择，基于大量人工标记的胚胎图像/视频建立质量评估和结局预测模型，发现深度学习模型具备客观、准确、高效及稳定等优点。综述深度学习模型优选胚胎研究现状，并与人工胚胎形态学评估和经典机器学习算法的性能进行比较，进一步探讨其在辅助生殖中的应用价值。

关键词: 体外受精, 胚胎移植, 深度学习, 胚胎选择, 胚胎质量, 妊娠结局

Abstract:

The selection of transferred embryo is one of the most important factors in achieving successful pregnancy of in vitro fertilization-embryo transfer. At present, the most common method of embryo selection is visual evaluation of embryo morphology, which is highly dependent on subjective vision and personal experience of lab technicians. This method may affect the accuracy and consistency of optimal embryo selection. Recently, some studies have tried to introduce the deep learning algorithm into embryo selection. The deep learning model is developed to assess quality, and to predict outcome based on a large number of manually labeled embryo images and vedios. It has been found that the deep learning algorithm was objective, accurate, efficient and stable. This paper reviews the application of deep learning, as well as its research progress, in embryo selection, and compares deep learning with manual evaluation or classic machine learning algorithms, so as to provide a glimpse into the application value of deep learning in assisted reproduction.

Key words: Fertilization in vitro, Embryo transfer, Deep learning, Embryo selection, Embryo quality, Pregnancy outcome

霍文杰, 王晓聪, 彭飞, 全松. 深度学习在体外受精胚胎优选中的应用[J]. 国际生殖健康/计划生育杂志, 2023, 42(2): 135-139.

HUO Wen-jie, WANG Xiao-cong, PENG Fei, QUAN Song. Application of Deep Learning in Optimal Embryo Selection of In Vitro Fertilization[J]. Journal of International Reproductive Health/Family Planning, 2023, 42(2): 135-139.

参考文献 33

[1]	Gardner DK, Lane M, Stevens J, et al. Reprint of: Blastocyst score affects implantation and pregnancy outcome: towards a single blastocyst transfer[J]. Fertil Steril, 2019, 112(4 Suppl 1):e81-e84. doi: 10.1016/j.fertnstert.2019.08.077. doi: 10.1016/j.fertnstert.2019.08.077 pmid: 31623746
[2]	Baxter Bendus AE, Mayer JF, Shipley SK, et al. Interobserver and intraobserver variation in day 3 embryo grading[J]. Fertil Steril, 2006, 86(6):1608-1615. doi: 10.1016/j.fertnstert.2006.05.037. doi: 10.1016/j.fertnstert.2006.05.037 pmid: 17074349
[3]	Bormann CL, Kanakasabapathy MK, Thirumalaraju P, et al. Performance of a deep learning based neural network in the selection of human blastocysts for implantation[J]. Elife, 2020, 9:e55301. doi: 10.7554/eLife.55301. doi: 10.7554/eLife.55301 URL
[4]	Lundin K, Park H. Time-lapse technology for embryo culture and selection[J]. Ups J Med Sci, 2020, 125(2):77-84. doi: 10.1080/03009734.2020.1728444. doi: 10.1080/03009734.2020.1728444 URL
[5]	LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553):436-444. doi: 10.1038/nature14539. doi: 10.1038/nature14539
[6]	Chan HP, Samala RK, Hadjiiski LM, et al. Deep Learning in Medical Image Analysis[J]. Adv Exp Med Biol, 2020, 1213:3-21. doi: 10.1007/978-3-030-33128-3_1. doi: 10.1007/978-3-030-33128-3_1
[7]	Khosravi P, Kazemi E, Zhan Q, et al. Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization[J]. NPJ Digit Med, 2019, 2:21. doi: 10.1038/s41746-019-0096-y. doi: 10.1038/s41746-019-0096-y pmid: 31304368
[8]	Liao Q, Zhang Q, Feng X, et al. Development of deep learning algorithms for predicting blastocyst formation and quality by time-lapse monitoring[J]. Commun Biol, 2021, 4(1):415. doi: 10.1038/s42003-021-01937-1. doi: 10.1038/s42003-021-01937-1 pmid: 33772211
[9]	Tran D, Cooke S, Illingworth PJ, et al. Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer[J]. Hum Reprod, 2019, 34(6):1011-1018. doi: 10.1093/humrep/dez064. doi: 10.1093/humrep/dez064
[10]	Huang B, Zheng S, Ma B, et al. Using deep learning to predict the outcome of live birth from more than 10,000 embryo data[J]. BMC Pregnancy Childbirth, 2022, 22(1):36. doi: 10.1186/s12884-021-04373-5. doi: 10.1186/s12884-021-04373-5
[11]	Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017, 542(7639):115-118. doi: 10.1038/nature21056. doi: 10.1038/nature21056
[12]	Louis CM, Erwin A, Handayani N, et al. Review of computer vision application in in vitro fertilization: the application of deep learning-based computer vision technology in the world of IVF[J]. J Assist Reprod Genet, 2021, 38(7):1627-1639. doi: 10.1007/s10815-021-02123-2. doi: 10.1007/s10815-021-02123-2
[13]	Wang D, Lu Z, Xu Y, et al. Cellular structure image classification with small targeted training samples[J]. IEEE Access, 2019, 7:148967-148974. doi: 10.1109/access.2019.2940161. doi: 10.1109/access.2019.2940161 URL
[14]	Rad RM, Saeedi P, Au J, et al. Trophectoderm segmentation in human embryo images via inceptioned U-Net[J]. Med Image Anal, 2020, 62:101612. doi: 10.1016/j.media.2019.101612. doi: 10.1016/j.media.2019.101612 URL
[15]	Hu J, Wang H, Wang J, et al. SA-Net: A scale-attention network for medical image segmentation[J]. PLoS One, 2021, 16(4):e0247388. doi: 10.1371/journal.pone.0247388. doi: 10.1371/journal.pone.0247388 URL
[16]	Kragh MF, Rimestad J, Berntsen J, et al. Automatic grading of human blastocysts from time-lapse imaging[J]. Comput Biol Med, 2019, 115:103494. doi: 10.1016/j.compbiomed.2019.103494. doi: 10.1016/j.compbiomed.2019.103494 URL
[17]	Loewke K, Cho JH, Brumar CD, et al. Characterization of an artificial intelligence model for ranking static images of blastocyst stage embryos[J]. Fertil Steril, 2022, 117(3):528-535. doi: 10.1016/j.fertnstert.2021.11.022. doi: 10.1016/j.fertnstert.2021.11.022 pmid: 34998577
[18]	VerMilyea M, Hall J, Diakiw SM, et al. Development of an artificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy during IVF[J]. Hum Reprod, 2020, 35(4):770-784. doi: 10.1093/humrep/deaa013. doi: 10.1093/humrep/deaa013 URL
[19]	Pribenszky C, Nilselid AM, Montag M. Time-lapse culture with morphokinetic embryo selection improves pregnancy and live birth chances and reduces early pregnancy loss: a meta-analysis[J]. Reprod Biomed Online, 2017, 35(5):511-520. doi: 10.1016/j.rbmo.2017.06.022. doi: S1472-6483(17)30307-3 pmid: 28736152
[20]	Thompson SM, Onwubalili N, Brown K, et al. Blastocyst expansion score and trophectoderm morphology strongly predict successful clinical pregnancy and live birth following elective single embryo blastocyst transfer (eSET): a national study[J]. J Assist Reprod Genet, 2013, 30(12):1577-1581. doi: 10.1007/s10815-013-0100-4. doi: 10.1007/s10815-013-0100-4 URL
[21]	Raudonis V, Paulauskaite-Taraseviciene A, Sutiene K, et al. Towards the automation of early-stage human embryo development detection[J]. Biomed Eng Online, 2019, 18(1):120. doi: 10.1186/s12938-019-0738-y. doi: 10.1186/s12938-019-0738-y pmid: 31830988
[22]	Dirvanauskas D, Maskeliunas R, Raudonis V, et al. Embryo development stage prediction algorithm for automated time lapse incubators[J]. Comput Methods Programs Biomed, 2019, 177:161-174. doi: 10.1016/j.cmpb.2019.05.027. doi: 10.1016/j.cmpb.2019.05.027 URL
[23]	Leahy BD, Jang WD, Yang HY, et al. Automated Measurements of Key Morphological Features of Human Embryos for IVF[J]. Med Image Comput Comput Assist Interv, 2020, 12265:25-35. doi: 10.1007/978-3-030-59722-1_3. doi: 10.1007/978-3-030-59722-1_3 pmid: 33313603
[24]	Huang T, Kosasa T, Walker B, et al. Deep learning neural network analysis of human blastocyst expansion from time-lapse image files[J]. Reprod Biomed Online, 2021, 42(6):1075-1085. doi: 10.1016/j.rbmo.2021.02.015. doi: 10.1016/j.rbmo.2021.02.015 pmid: 33820741
[25]	Berntsen J, Rimestad J, Lassen JT, et al. Robust and generalizable embryo selection based on artificial intelligence and time-lapse image sequences[J]. PLoS One, 2022, 17(2):e0262661. doi: 10.1371/journal.pone.0262661. doi: 10.1371/journal.pone.0262661 URL
[26]	Chavez-Badiola A, Mendizabal-Ruiz G, Flores-Saiffe Farias A, et al. Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer[J]. Hum Reprod, 2020, 35(2):482. doi: 10.1093/humrep/dez263. doi: 10.1093/humrep/dez263 URL
[27]	Miyagi Y, Habara T, Hirata R, et al. Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age[J]. Reprod Med Biol, 2019, 18(2):190-203. doi: 10.1002/rmb2.12266. doi: 10.1002/rmb2.12266 pmid: 30996683
[28]	Sawada Y, Sato T, Nagaya M, et al. Evaluation of artificial intelligence using time-lapse images of IVF embryos to predict live birth[J]. Reprod Biomed Online, 2021, 43(5):843-852. doi: 10.1016/j.rbmo.2021.05.002. doi: 10.1016/j.rbmo.2021.05.002 pmid: 34521598
[29]	Miyagi Y, Habara T, Hirata R, et al. Feasibility of predicting live birth by combining conventional embryo evaluation with artificial intelligence applied to a blastocyst image in patients classified by age[J]. Reprod Med Biol, 2019, 18(4):344-356. doi: 10.1002/rmb2.12284. doi: 10.1002/rmb2.12284 pmid: 31607794
[30]	Thirumalaraju P, Kanakasabapathy MK, Bormann CL, et al. Evaluation of deep convolutional neural networks in classifying human embryo images based on their morphological quality[J]. Heliyon, 2021, 7(2):e06298. doi: 10.1016/j.heliyon.2021.e06298. doi: 10.1016/j.heliyon.2021.e06298 URL
[31]	Fitz VW, Kanakasabapathy MK, Thirumalaraju P, et al. Should there be an "AI" in TEAM? Embryologists selection of high implantation potential embryos improves with the aid of an artificial intelligence algorithm[J]. J Assist Reprod Genet, 2021, 38(10):2663-2670. doi: 10.1007/s10815-021-02318-7. doi: 10.1007/s10815-021-02318-7
[32]	Ueno S, Berntsen J, Ito M, et al. Pregnancy prediction performance of an annotation-free embryo scoring system on the basis of deep learning after single vitrified-warmed blastocyst transfer: a single-center large cohort retrospective study[J]. Fertil Steril, 2021, 116(4):1172-1180. doi: 10.1016/j.fertnstert.2021.06.001. doi: 10.1016/j.fertnstert.2021.06.001 pmid: 34246469
[33]	Zheng W, Zhang S, Gu Y, et al. Non-invasive Metabolomic Profiling of Embryo Culture Medium Using Raman Spectroscopy With Deep Learning Model Predicts the Blastocyst Development Potential of Embryos[J]. Front Physiol, 2021, 12:777259. doi: 10.3389/fphys.2021.777259. doi: 10.3389/fphys.2021.777259 URL