Feasibility of Deep Learning for Predicting Live Birth from a Blastocyst Image in Patients Classified by Age

Overview

Journal Reprod Med Biol

Specialty Biology

Date 2019 Apr 19

PMID 30996683

Citations 21

Authors

Yasunari Miyagi

Toshihiro Habara

Rei Hirata

Nobuyoshi Hayashi

Affiliations

Soon will be listed here.

Abstract

Purpose: To identify artificial intelligence (AI) classifiers in images of blastocysts to predict the probability of achieving a live birth in patients classified by age. Results are compared to those obtained by conventional embryo (CE) evaluation.

Methods: A total of 5691 blastocysts were retrospectively enrolled. Images captured 115 hours after insemination (or 139 hours if not yet large enough) were classified according to maternal age as follows: <35, 35-37, 38-39, 40-41, and ≥42 years. The classifiers for each category and a classifier for all ages were related to convolutional neural networks associated with deep learning. Then, the live birth functions predicted by the AI and the multivariate logistic model functions predicted by CE were tested. The feasibility of the AI was investigated.

Results: The accuracies of AI/CE for predicting live birth were 0.64/0.61, 0.71/0.70, 0.78/0.77, 0.81/0.83, 0.88/0.94, and 0.72/0.74 for the age categories <35, 35-37, 38-39, 40-41, and ≥42 years and all ages, respectively. The sum value of the sensitivity and specificity revealed that AI performed better than CE ( = 0.01).

Conclusions: AI classifiers categorized by age can predict the probability of live birth from an image of the blastocyst and produced better results than were achieved using CE.

Citing Articles

Predicting IVF live -birth probability using time-lapse data: Implications of including or excluding age in a day 2 embryo transfer model.

Sayed S, Petersen B, Reigstad M, Schwennicke A, Hausken J, Storeng R PLoS One. 2025; 20(2):e0318480.

PMID: 39999051 PMC: 11856505. DOI: 10.1371/journal.pone.0318480.

Predicting implantation by using dual AI system incorporating three-dimensional blastocyst image and conventional embryo evaluation parameters-A pilot study.

Miyagi Y, Habara T, Hirata R, Hayashi N Reprod Med Biol. 2024; 23(1):e12612.

PMID: 39351129 PMC: 11442056. DOI: 10.1002/rmb2.12612.

Quality of IVM ovarian tissue oocytes: impact of clinical, demographic, and laboratory factors.

Kashutina M, Obosyan L, Bunyaeva E, Zhernov Y, Kirillova A J Assist Reprod Genet. 2024; 41(11):3079-3088.

PMID: 39349891 PMC: 11621277. DOI: 10.1007/s10815-024-03234-2.

Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial.

Illingworth P, Venetis C, Gardner D, Nelson S, Berntsen J, Larman M Nat Med. 2024; 30(11):3114-3120.

PMID: 39122964 PMC: 11564097. DOI: 10.1038/s41591-024-03166-5.

Industry 4.0 Technologies in Maternal Health Care: Bibliometric Analysis and Research Agenda.

Sibanda K, Ndayizigamiye P, Twinomurinzi H JMIR Pediatr Parent. 2024; 7:e47848.

PMID: 39116433 PMC: 11342010. DOI: 10.2196/47848.

References

Kudva V, Prasad K, Guruvare S . Automation of Detection of Cervical Cancer Using Convolutional Neural Networks. Crit Rev Biomed Eng. 2018; 46(2):135-145. DOI: 10.1615/CritRevBiomedEng.2018026019. View

Hong Y, Kim S, Moon K, Kim S, Jee B, Lee W . Impact of presence of antiphospholipid antibodies on fertilization outcome. Obstet Gynecol Sci. 2018; 61(3):359-366. PMC: 5956119. DOI: 10.5468/ogs.2018.61.3.359. View

Kroon S, Ravel J, Huston W . Cervicovaginal microbiota, women's health, and reproductive outcomes. Fertil Steril. 2018; 110(3):327-336. DOI: 10.1016/j.fertnstert.2018.06.036. View

Finn A, Scott L, OLeary T, Davies D, Hill J . Sequential embryo scoring as a predictor of aneuploidy in poor-prognosis patients. Reprod Biomed Online. 2010; 21(3):381-90. DOI: 10.1016/j.rbmo.2010.05.004. View

Shirasuna K, Iwata H . Effect of aging on the female reproductive function. Contracept Reprod Med. 2017; 2:23. PMC: 5683335. DOI: 10.1186/s40834-017-0050-9. View

Gleicher N, Metzger J, Croft G, Kushnir V, Albertini D, Barad D . A single trophectoderm biopsy at blastocyst stage is mathematically unable to determine embryo ploidy accurately enough for clinical use. Reprod Biol Endocrinol. 2017; 15(1):33. PMC: 5408377. DOI: 10.1186/s12958-017-0251-8. View

Sato M, Horie K, Hara A, Miyamoto Y, Kurihara K, Tomio K . Application of deep learning to the classification of images from colposcopy. Oncol Lett. 2018; 15(3):3518-3523. PMC: 5795879. DOI: 10.3892/ol.2018.7762. View

Taylor E, Gomel V . The uterus and fertility. Fertil Steril. 2007; 89(1):1-16. DOI: 10.1016/j.fertnstert.2007.09.069. View

Abbod M, Catto J, Linkens D, Hamdy F . Application of artificial intelligence to the management of urological cancer. J Urol. 2007; 178(4 Pt 1):1150-6. DOI: 10.1016/j.juro.2007.05.122. View

10.

Simoes P, Izumi N, Casagrande R, Venson R, Veronezi C, Moretti G . Classification of images acquired with colposcopy using artificial neural networks. Cancer Inform. 2014; 13:119-24. PMC: 4213185. DOI: 10.4137/CIN.S17948. View

11.

Ortiz A, Munilla J, Gorriz J, Ramirez J . Ensembles of Deep Learning Architectures for the Early Diagnosis of the Alzheimer's Disease. Int J Neural Syst. 2016; 26(7):1650025. DOI: 10.1142/S0129065716500258. View

12.

Mnih V, Kavukcuoglu K, Silver D, Rusu A, Veness J, Bellemare M . Human-level control through deep reinforcement learning. Nature. 2015; 518(7540):529-33. DOI: 10.1038/nature14236. View

13.

Bengio Y, Courville A, Vincent P . Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell. 2013; 35(8):1798-828. DOI: 10.1109/TPAMI.2013.50. View

14.

Christ J, Gunning M, Palla G, Eijkemans M, Lambalk C, Laven J . Estrogen deprivation and cardiovascular disease risk in primary ovarian insufficiency. Fertil Steril. 2018; 109(4):594-600.e1. DOI: 10.1016/j.fertnstert.2017.11.035. View

15.

Yu L, Chen H, Dou Q, Qin J, Heng P . Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks. IEEE Trans Med Imaging. 2016; 36(4):994-1004. DOI: 10.1109/TMI.2016.2642839. View

16.

Ben-Bassat M, Klove K, Weil M . Sensitivity analysis in bayesian classification models: multiplicative deviations. IEEE Trans Pattern Anal Mach Intell. 2011; 2(3):261-6. DOI: 10.1109/tpami.1980.4767015. View

17.

Brezina P, Kutteh W . Clinical applications of preimplantation genetic testing. BMJ. 2015; 350:g7611. DOI: 10.1136/bmj.g7611. View

18.

. Female age-related fertility decline. Committee Opinion No. 589. Fertil Steril. 2014; 101(3):633-4. DOI: 10.1016/j.fertnstert.2013.12.032. View

19.

Dreiseitl S, Ohno-Machado L . Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform. 2003; 35(5-6):352-9. DOI: 10.1016/s1532-0464(03)00034-0. View

20.

Eaton J, Hacker M, Harris D, Thornton K, Penzias A . Assessment of day-3 morphology and euploidy for individual chromosomes in embryos that develop to the blastocyst stage. Fertil Steril. 2008; 91(6):2432-6. DOI: 10.1016/j.fertnstert.2008.03.008. View