Non-invasively predicting euploidy in human blastocysts via quantitative 3D morphology measurement: a retrospective cohort study.
3D morphology measurement
Blastocyst
Euploidy prediction
Machine learning
Journal
Reproductive biology and endocrinology : RB&E
ISSN: 1477-7827
Titre abrégé: Reprod Biol Endocrinol
Pays: England
ID NLM: 101153627
Informations de publication
Date de publication:
28 Oct 2024
28 Oct 2024
Historique:
received:
01
08
2024
accepted:
17
10
2024
medline:
29
10
2024
pubmed:
29
10
2024
entrez:
29
10
2024
Statut:
epublish
Résumé
Blastocyst morphology has been demonstrated to be associated with ploidy status. Existing artificial intelligence models use manual grading or 2D images as the input for euploidy prediction, which suffer from subjectivity from observers and information loss due to incomplete features from 2D images. Here we aim to predict euploidy in human blastocysts using quantitative morphological parameters obtained by 3D morphology measurement. Multi-view images of 226 blastocysts on Day 6 were captured by manually rotating blastocysts during the preparation stage of trophectoderm biopsy. Quantitative morphological parameters were obtained by 3D morphology measurement. Six machine learning models were trained using 3D morphological parameters as the input and PGT-A results as the ground truth outcome. Model performance, including sensitivity, specificity, precision, accuracy and AUC, was evaluated on an additional test dataset. Model interpretation was conducted on the best-performing model. All the 3D morphological parameters were significantly different between euploid and non-euploid blastocysts. Multivariate analysis revealed that three of the five parameters including trophectoderm cell number, trophectoderm cell size variance and inner cell mass area maintained statistical significance (P < 0.001, aOR = 1.054, 95% CI 1.034-1.073; P = 0.003, aOR = 0.994, 95% CI 0.991-0.998; P = 0.010, aOR = 1.003, 95% CI 1.001-1.006). The accuracy of euploidy prediction by the six machine learning models ranged from 80 to 95.6%, and the AUCs ranged from 0.881 to 0.984. Particularly, the decision tree model achieved the highest accuracy of 95.6% (95% CI 84.9-99.5%) with the AUC of 0.978 (95% CI 0.882-0.999), and the extreme gradient boosting model achieved the highest AUC of 0.984 (95% CI 0.892-1.000) with the accuracy of 93.3% (95% CI 81.7-98.6%). No significant difference was found between different age groups using either decision tree or extreme gradient boosting to predict euploid blastocysts. The quantitative criteria extracted from the decision tree imply that euploid blastocysts have a higher number of trophectoderm cells, larger inner cell mass area, and smaller trophectoderm cell size variance compared to non-euploid blastocysts. Using quantitative morphological parameters obtained by 3D morphology measurement, the decision tree-based machine learning model achieved an accuracy of 95.6% and AUC of 0.978 for predicting euploidy in Day 6 human blastocysts. N/A.
Sections du résumé
BACKGROUND
BACKGROUND
Blastocyst morphology has been demonstrated to be associated with ploidy status. Existing artificial intelligence models use manual grading or 2D images as the input for euploidy prediction, which suffer from subjectivity from observers and information loss due to incomplete features from 2D images. Here we aim to predict euploidy in human blastocysts using quantitative morphological parameters obtained by 3D morphology measurement.
METHODS
METHODS
Multi-view images of 226 blastocysts on Day 6 were captured by manually rotating blastocysts during the preparation stage of trophectoderm biopsy. Quantitative morphological parameters were obtained by 3D morphology measurement. Six machine learning models were trained using 3D morphological parameters as the input and PGT-A results as the ground truth outcome. Model performance, including sensitivity, specificity, precision, accuracy and AUC, was evaluated on an additional test dataset. Model interpretation was conducted on the best-performing model.
RESULTS
RESULTS
All the 3D morphological parameters were significantly different between euploid and non-euploid blastocysts. Multivariate analysis revealed that three of the five parameters including trophectoderm cell number, trophectoderm cell size variance and inner cell mass area maintained statistical significance (P < 0.001, aOR = 1.054, 95% CI 1.034-1.073; P = 0.003, aOR = 0.994, 95% CI 0.991-0.998; P = 0.010, aOR = 1.003, 95% CI 1.001-1.006). The accuracy of euploidy prediction by the six machine learning models ranged from 80 to 95.6%, and the AUCs ranged from 0.881 to 0.984. Particularly, the decision tree model achieved the highest accuracy of 95.6% (95% CI 84.9-99.5%) with the AUC of 0.978 (95% CI 0.882-0.999), and the extreme gradient boosting model achieved the highest AUC of 0.984 (95% CI 0.892-1.000) with the accuracy of 93.3% (95% CI 81.7-98.6%). No significant difference was found between different age groups using either decision tree or extreme gradient boosting to predict euploid blastocysts. The quantitative criteria extracted from the decision tree imply that euploid blastocysts have a higher number of trophectoderm cells, larger inner cell mass area, and smaller trophectoderm cell size variance compared to non-euploid blastocysts.
CONCLUSIONS
CONCLUSIONS
Using quantitative morphological parameters obtained by 3D morphology measurement, the decision tree-based machine learning model achieved an accuracy of 95.6% and AUC of 0.978 for predicting euploidy in Day 6 human blastocysts.
TRIAL REGISTRATION
BACKGROUND
N/A.
Identifiants
pubmed: 39468586
doi: 10.1186/s12958-024-01302-x
pii: 10.1186/s12958-024-01302-x
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
132Informations de copyright
© 2024. The Author(s).
Références
Scott RT Jr, Ferry K, Su J, Tao X, Scott K, Treff NR. Comprehensive chromosome screening is highly predictive of the reproductive potential of human embryos: a prospective, blinded, nonselection study. Fertil Steril. 2012;97:870–5.
pubmed: 22305103
doi: 10.1016/j.fertnstert.2012.01.104
Tiegs AW, Tao X, Zhan Y, Whitehead C, Kim J, Hanson B, Osman E, Kim TJ, Patounakis G, Gutmann J, Castelbaum A. A multicenter, prospective, blinded, nonselection study evaluating the predictive value of an aneuploid diagnosis using a targeted next-generation sequencing–based preimplantation genetic testing for aneuploidy assay and impact of biopsy. Fertil Steril. 2021;115:627–37.
pubmed: 32863013
doi: 10.1016/j.fertnstert.2020.07.052
Kushnir VA, Frattarelli JL. Aneuploidy in Abortuses following IVF and ICSI. J Assist Reprod Genet. 2009;26:93–7.
pubmed: 19224361
pmcid: 2654933
doi: 10.1007/s10815-009-9292-z
Kim JW, Lee WS, Yoon TK, Seok HH, Cho JH, Kim YS, Lyu SW, Shim SH. Chromosomal abnormalities in spontaneous abortion after assisted reproductive treatment. BMC Med Genet. 2010;11:1–6.
doi: 10.1186/1471-2350-11-153
Sciorio R, Dattilo M. PGT-A preimplantation genetic testing for aneuploidies and embryo selection in routine ART cycles: time to step back? Clin Genet. 2020;98:107–15.
pubmed: 32141057
doi: 10.1111/cge.13732
Rosenwaks Z, Handyside AH, Fiorentino F, Gleicher N, Paulson RJ, Schattman GL, Scott RT, Summers MC, Treff NR, Xu K. The pros and cons of preimplantation genetic testing for aneuploidy: clinical and laboratory perspectives. Fertil Steril. 2018;110:353–61.
pubmed: 30098682
doi: 10.1016/j.fertnstert.2018.06.002
Belandres D, Shamonki M, Arrach N. Current status of spent embryo media research for preimplantation genetic testing. J Assist Reprod Genet. 2019;36:819–26.
pubmed: 30895497
pmcid: 6541676
doi: 10.1007/s10815-019-01437-6
Cinnioglu C, Glessner H, Jordan A, Bunshaft S. A systematic review of non-invasive preimplantation genetic testing for Aneuploidy. Fertil Steril. 2023;120:235–9.
pubmed: 37356468
doi: 10.1016/j.fertnstert.2023.06.013
Gardner DK, Schoolcraft WB. Culture and transfer of human blastocysts. Curr Opin Obstet Gynecol. 1999;11:307–11.
pubmed: 10369209
doi: 10.1097/00001703-199906000-00013
Alpha Scientists in Reproductive Medicine and ESHRE Special Interest Group of Embryology. The Istanbul consensus workshop on embryo assessment: proceedings of an expert meeting. Hum Reprod. 2011;26:1270–83.
doi: 10.1093/humrep/der037
Alfarawati S, Fragouli E, Colls P, Stevens J, Gutiérrez-Mateo C, Schoolcraft WB, Katz-Jaffe MG, Wells D. The relationship between blastocyst morphology, chromosomal abnormality, and embryo gender. Fertil Steril. 2011;95:520–4.
pubmed: 20537630
doi: 10.1016/j.fertnstert.2010.04.003
Minasi MG, Colasante A, Riccio T, Ruberti A, Casciani V, Scarselli F, Spinella F, Fiorentino F, Varricchio MT, Greco E. Correlation between aneuploidy, standard morphology evaluation and morphokinetic development in 1730 biopsied blastocysts: a consecutive case series study. Hum Reprod. 2016;31:2245–54.
pubmed: 27591227
doi: 10.1093/humrep/dew183
Wang A, Kort J, Behr B, Westphal LM. Euploidy in relation to blastocyst sex and morphology. J Assist Reprod Genet. 2018;35:1565–72.
pubmed: 30030712
pmcid: 6133810
doi: 10.1007/s10815-018-1262-x
Tunis SR, Clarke M, Gorst SL, Gargon E, Blazeby JM, Altman DG, Williamson PR. Improving the relevance and consistency of outcomes in comparative effectiveness research. J Comp Eff Res. 2016;5:193–205.
pubmed: 26930385
pmcid: 4926524
doi: 10.2217/cer-2015-0007
Fordham DE, Rosentraub D, Polsky AL, Aviram T, Wolf Y, Perl O, Devir A, Rosentraub S, Silver DH, Gold Zamir Y, Bronstein AM. Embryologist agreement when assessing blastocyst implantation probability: is data-driven prediction the solution to embryo assessment subjectivity? Hum Reprod. 2022;37:2275–90.
pubmed: 35944167
doi: 10.1093/humrep/deac171
Chawla M, Fakih M, Shunnar A, Bayram A, Hellani A, Perumal V, Divakaran J, Budak E. Morphokinetic analysis of cleavage stage embryos and its relationship to aneuploidy in a retrospective time-lapse imaging study. J Assist Reprod Genet. 2015;32:69–75.
pubmed: 25395178
doi: 10.1007/s10815-014-0372-3
Lee CI, Chen CH, Huang CC, Cheng EH, Chen HH, Ho ST, Lin PY, Lee MS, Lee TH. Embryo morphokinetics is potentially associated with clinical outcomes of single-embryo transfers in preimplantation genetic testing for aneuploidy cycles. Reprod Biomed Online. 2019;39:569–79.
pubmed: 31395516
doi: 10.1016/j.rbmo.2019.05.020
Martin A, Rodrigo L, Beltrán D, Meseguer M, Rubio C, Mercader A, de Los Santos MJ. The morphokinetic signature of mosaic embryos: evidence in support of their own genetic identity. Fertil Steril. 2021;116:165–73.
pubmed: 33766460
doi: 10.1016/j.fertnstert.2020.12.031
Reignier A, Lammers J, Barriere P, Freour T. Can time-lapse parameters predict embryo ploidy? A systematic review. Reprod Biomed Online. 2018;36:380–7.
pubmed: 29398421
doi: 10.1016/j.rbmo.2018.01.001
Bamford T, Barrie A, Montgomery S, Dhillon-Smith R, Campbell A, Easter C, Coomarasamy A. Morphological and morphokinetic associations with aneuploidy: a systematic review and meta-analysis. Hum Reprod Update. 2022;28:656–86.
pubmed: 35613016
doi: 10.1093/humupd/dmac022
Jiang VS, Bormann CL. Non-invasive genetic screening: current advances in Artificial intelligence for embryo Ploidy Prediction. Fertil Steril. 2023;120:228–34.
pubmed: 37394089
doi: 10.1016/j.fertnstert.2023.06.025
Zhan Q, Sierra ET, Malmsten J, Ye Z, Rosenwaks Z, Zaninovic N. Blastocyst score, a blastocyst quality ranking tool, is a predictor of blastocyst ploidy and implantation potential. FandS Reports. 2020;1:133–41.
De Gheselle S, Jacques C, Chambost J, Blank C, Declerck K, De Croo I, Hickman C, Tilleman K. Machine learning for prediction of euploidy in human embryos: in search of the best-performing model and predictive features. Fertil Steril. 2022;117:738–46.
pubmed: 35058042
doi: 10.1016/j.fertnstert.2021.11.029
Zou Y, Pan Y, Ge N, Xu Y, Gu R, Li Z, Fu J, Gao J, Sun X, Sun Y. Can the combination of time-lapse parameters and clinical features predict embryonic ploidy status or implantation? Reprod Biomed Online. 2022;45:643–51.
pubmed: 35918244
doi: 10.1016/j.rbmo.2022.06.007
Kato K, Ueno S, Berntsen J, Kragh MF, Okimura T, Kuroda T. Does embryo categorization by existing artificial intelligence, morphokinetic or morphological embryo selection models correlate with blastocyst euploidy rates? Reprod Biomed Online. 2023;46:274–81.
pubmed: 36470714
doi: 10.1016/j.rbmo.2022.09.010
Bamford T, Easter C, Montgomery S, Smith R, Dhillon-Smith RK, Barrie A, Campbell A, Coomarasamy A. A comparison of 12 machine learning models developed to predict ploidy, using a morphokinetic meta-dataset of 8147 embryos. Hum Reprod. 2023;38:569–81.
pubmed: 36825452
doi: 10.1093/humrep/dead034
Yuan Z, Yuan M, Song X, Huang X, Yan W. Development of an artificial intelligence based model for predicting the euploidy of blastocysts in PGT-A treatments. Sci Rep. 2023;13:2322.
pubmed: 36759639
pmcid: 9911600
doi: 10.1038/s41598-023-29319-z
Chavez-Badiola A, Flores-Saiffe-Farías A, Mendizabal-Ruiz G, Drakeley AJ, Cohen J. Embryo Ranking Intelligent classification algorithm (ERICA): artificial intelligence clinical assistant predicting embryo ploidy and implantation. Reprod Biomed Online. 2020;41:585–93.
pubmed: 32843306
doi: 10.1016/j.rbmo.2020.07.003
Diakiw SM, Hall JM, VerMilyea MD, Amin J, Aizpurua J, Giardini L, Briones YG, Lim AY, Dakka MA, Nguyen TV, Perugini D. Development of an artificial intelligence model for predicting the likelihood of human embryo euploidy based on blastocyst images from multiple imaging systems during IVF. Hum Reprod. 2022;37:1746–59.
pubmed: 35674312
pmcid: 9340116
doi: 10.1093/humrep/deac131
Barnes J, Brendel M, Gao VR, Rajendran S, Kim J, Li Q, Malmsten JE, Sierra JT, Zisimopoulos P, Sigaras A, Khosravi P. A non-invasive artificial intelligence approach for the prediction of human blastocyst ploidy: a retrospective model development and validation study. Lancet Digit Health. 2023;5:e28-40.
pubmed: 36543475
pmcid: 10193126
doi: 10.1016/S2589-7500(22)00213-8
Danardono GB, Handayani N, Louis CM, Polim AA, Sirait B, Periastiningrum G, Afadlal S, Boediono A, Sini I. Embryo ploidy status classification through computer-assisted morphology assessment. AJOG Global Rep. 2023;3:100209.
doi: 10.1016/j.xagr.2023.100209
Lee CI, Su YR, Chen CH, Chang TA, Kuo EE, Zheng WL, Hsieh WT, Huang CC, Lee MS, Liu M. End-to-end deep learning for recognition of ploidy status using time-lapse videos. J Assist Reprod Genet. 2021;38:1655–63.
pubmed: 34021832
pmcid: 8324635
doi: 10.1007/s10815-021-02228-8
Huang B, Tan W, Li Z, Jin L. An artificial intelligence model (euploid prediction algorithm) can predict embryo ploidy status based on time-lapse data. Reproductive Biology Endocrinol. 2021;19:185.
doi: 10.1186/s12958-021-00864-4
Jiang VS, Kandula H, Thirumalaraju P, Kanakasabapathy MK, Cherouveim P, Souter I, Dimitriadis I, Bormann CL, Shafiee H. The use of voting ensembles to improve the accuracy of deep neural networks as a non-invasive method to predict embryo ploidy status. J Assist Reprod Genet. 2023;40:301–8.
pubmed: 36640251
pmcid: 9935776
doi: 10.1007/s10815-022-02707-6
Paya E, Pulgarín C, Bori L, Colomer A, Naranjo V, Meseguer M. Deep learning system for classification of ploidy status using time-lapse videos. F&S Sci. 2023;4:211–8.
doi: 10.1016/j.xfss.2023.06.002
Wang G, Wang K, Gao Y, Chen L, Gao T, Ma Y, Jiang Z, Yang G, Feng F, Zhang S, Gu Y. A generalized AI system for human embryo selection covering the entire IVF cycle via multi-modal contrastive learning. Patterns. 2024;5: 100985.
pubmed: 39081572
pmcid: 11284500
doi: 10.1016/j.patter.2024.100985
Afnan MA, Liu Y, Conitzer V, Rudin C, Mishra A, Savulescu J, Afnan M. Interpretable, not black-box, artificial intelligence should be used for embryo selection. Human Reprod Open. 2021;2021:hoab040.
doi: 10.1093/hropen/hoab040
Shan G, Dai C, Liu H, Wang X, Dou W, Zhang Z, Sun Y. 3D morphology measurement for blastocyst evaluation from all angles. IEEE Trans Biomed Eng. 2023;70:1921–30.
pubmed: 37015494
doi: 10.1109/TBME.2022.3232068
Raschka S. Model evaluation, model selection, and algorithm selection in machine learning. arXiv:1811.12808. 2018.
Zou KH, O’Malley AJ, Mauri L. Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models. Circulation. 2007;115:654–7.
pubmed: 17283280
doi: 10.1161/CIRCULATIONAHA.105.594929
Storr A, Venetis CA, Cooke S, Kilani S, Ledger W. Inter-observer and intra-observer agreement between embryologists during selection of a single day 5 embryo for transfer: a multicenter study. Hum Reprod. 2017;32:307–14.
pubmed: 28031323
doi: 10.1093/humrep/dew330
Adolfsson E, Andershed AN. Morphology vs morphokinetics: a retrospective comparison of inter-observer and intra-observer agreement between embryologists on blastocysts with known implantation outcome. JBRA Assist Reprod. 2018;22:228.
pubmed: 29912521
pmcid: 6106622
Liu H, Zhang Z, Gu Y, Dai C, Shan G, Song H, Li D, Chen W, Lin G, Sun Y. Development and evaluation of a live birth prediction model for evaluating human blastocysts from a retrospective study. Elife. 2023;12: e83662.
pubmed: 36810139
pmcid: 10069866
doi: 10.7554/eLife.83662
Ahlström A, Westin C, Reismer E, Wikland M, Hardarson T. Trophectoderm morphology: an important parameter for predicting live birth after single blastocyst transfer. Hum Reprod. 2011;26:3289–96.
pubmed: 21972253
doi: 10.1093/humrep/der325
Chuang TH, Hsieh JY, Lee MJ, Lai HH, Hsieh CL, Wang HL, Chang YJ, Chen SU. Concordance between different trophectoderm biopsy sites and the inner cell mass of chromosomal composition measured with a next-generation sequencing platform. MHR: Basic Sci Reproductive Med. 2018;24:593–601.
Tšuiko O, Zhigalina DI, Jatsenko T, Skryabin NA, Kanbekova OR, Artyukhova VG, Svetlakov AV, Teearu K, Trošin A, Salumets A, Kurg A. Karyotype of the blastocoel fluid demonstrates low concordance with both trophectoderm and inner cell mass. Fertil Steril. 2018;109:1127–34.
pubmed: 29935648
doi: 10.1016/j.fertnstert.2018.02.008
Victor AR, Griffin DK, Brake AJ, Tyndall JC, Murphy AE, Lepkowsky LT, Lal A, Zouves CG, Barnes FL, McCoy RC, Viotti M. Assessment of aneuploidy concordance between clinical trophectoderm biopsy and blastocyst. Hum Reprod. 2019;34:181–92.
pubmed: 30418565
doi: 10.1093/humrep/dey327
Starostik MR, Sosina OA, McCoy RC. Single-cell analysis of human embryos reveals diverse patterns of aneuploidy and mosaicism. Genome Res. 2020;30:814–25.
pubmed: 32641298
pmcid: 7370883
doi: 10.1101/gr.262774.120
Regin M, Spits C, Sermon K. On the origins and fate of chromosomal abnormalities in human preimplantation embryos: an unsolved riddle. Mol Hum Reprod. 2022;28:gaac011.
pubmed: 35404421
doi: 10.1093/molehr/gaac011
Regin M, Lei Y, De Deckersberg EC, Guns Y, Verdyck P, Verheyen G, Van de Sermon VH, Spits K. Complex aneuploidy triggers autophagy and p53-mediated apoptosis and impairs the second lineage segregation in human preimplantation embryos. eLife. 2023;12:RP88916.
Martin A, Mercader A, Dominguez F, Quiñonero A, Perez M, Gonzalez-Martin R, Delgado A, Mifsud A, Pellicer A, De Los Santos MJ. Mosaic results after preimplantation genetic testing for aneuploidy may be accompanied by changes in global gene expression. Front Mol Biosci. 2023;10:1180689.
pubmed: 37122560
pmcid: 10140421
doi: 10.3389/fmolb.2023.1180689
Santaguida S, Richardson A, Iyer DR, M’Saad O, Zasadil L, Knouse KA, Wong YL, Rhind N, Desai A, Amon A. Chromosome mis-segregation generates cell-cycle-arrested cells with complex karyotypes that are eliminated by the immune system. Dev Cell. 2017;41:638–51.
pubmed: 28633018
pmcid: 5536848
doi: 10.1016/j.devcel.2017.05.022
Williams BR, Prabhu VR, Hunter KE, Glazier CM, Whittaker CA, Housman DE, Amon A. Aneuploidy affects proliferation and spontaneous immortalization in mammalian cells. Science. 2008;322:703–9.
pubmed: 18974345
pmcid: 2701511
doi: 10.1126/science.1160058
Neurohr GE, Terry RL, Lengefeld J, Bonney M, Brittingham GP, Moretto F, Miettinen TP, Vaites LP, Soares LM, Paulo JA, Harper JW. Excessive cell growth causes cytoplasm dilution and contributes to senescence. Cell. 2019;176:1083–97.
pubmed: 30739799
pmcid: 6386581
doi: 10.1016/j.cell.2019.01.018
Nguyen EB, Jacobs EA, Summers KM, Sparks AE, Van Voorhis BJ, Klenov VE, Duran EH. Embryo blastulation and quality between days 5 and 6 of extended embryo culture. J Assist Reprod Genet. 2021;38:2193–8.
pubmed: 33754252
pmcid: 8417162
doi: 10.1007/s10815-021-02156-7
Leigh D, Cram DS, Rechitsky S, Handyside A, Wells D, Munne S, Kahraman S, Grifo J, Katz-Jaffe M, Rubio C, Viotti M. PGDIS position statement on the transfer of mosaic embryos 2021. Reprod Biomed Online. 2022;45:19–25.
pubmed: 35523707
doi: 10.1016/j.rbmo.2022.03.013
Rodrigo L, Clemente-Císcar M, Campos-Galindo I, Peinado V, Simón C, Rubio C. Characteristics of the IVF cycle that Contribute to the incidence of Mosaicism. Genes. 2020;11: 1151.
pubmed: 33007801
pmcid: 7600993
doi: 10.3390/genes11101151
Abhari S, Kawwass JF. Pregnancy and neonatal outcomes after transfer of mosaic embryos: a review. J Clin Med. 2021;10: 1369.
pubmed: 33801687
pmcid: 8037456
doi: 10.3390/jcm10071369
Munné S, Spinella F, Grifo J, Zhang J, Beltran MP, Fragouli E, Fiorentino F. Clinical outcomes after the transfer of blastocysts characterized as mosaic by high resolution next generation sequencing-further insights. Eur J Med Genet. 2020;63: 103741.
pubmed: 31445143
doi: 10.1016/j.ejmg.2019.103741