A Novel System Based on Artificial Intelligence for Predicting Blastocyst Viability and Visualizing the Explanation

Overview

Journal Reprod Med Biol

Specialty Biology

Date 2022 Apr 7

PMID 35386375

Authors

Noritoshi Enatsu

Isao Miyatsuka

Le My An

Miki Inubushi

Kunihiro Enatsu

Junko Otsuki

Toshiroh Iwasaki

Shoji Kokeguchi

Masahide Shiotani

Affiliations

Soon will be listed here.

Abstract

Purpose: The purpose of the study was to invent and evaluate the novel artificial intelligence (AI) system named Fertility image Testing Through Embryo (FiTTE) for predicting blastocyst viability and visualizing the explanations via gradient-based localization.

Methods: The authors retrospectively analyzed 19 342 static blastocyst images with related inspection histories from 9961 infertile patients who underwent in vitro fertilization. Among these data, 17 984 cycles of single-blastocyst transfer were used for training, and data from 1358 cycles were used for testing purposes.

Results: The prediction accuracy for clinical pregnancy achieved by a control model using conventional Gardner scoring system was 59.8%, and area under the curve (AUC) was 0.62. FiTTE improved the prediction accuracy by using blastocyst images to 62.7% and AUC of 0.68. Additionally, the accuracy achieved by an ensemble model using image plus clinical data was 65.2% and AUC was 0.71, representing an improvement in prediction accuracy. The visualization algorithm showed brighter colors with blastocysts that resulted in clinical pregnancy.

Conclusions: The authors invented the novel AI system, FiTTE, which could provide more precise prediction of the probability of clinical pregnancy using blastocyst images secondary to single embryo transfer than the conventional Gardner scoring assessments. FiTTE could also provide explanation of AI prediction using colored blastocyst images.

Citing Articles

Identification of novel COL4A5 variants and prenatal diagnosis in three large families.

Zeng B, Yu Y, Liu C, Li X, Lu Q, Chen Z Sci Rep. 2025; 15(1):8135.

PMID: 40057613 PMC: 11890855. DOI: 10.1038/s41598-025-92649-7.

FertilitY Predictor-a machine learning-based web tool for the prediction of assisted reproduction outcomes in men with Y chromosome microdeletions.

Colaco S, Narad P, Singh A, Gupta P, Choudhury A, Sengupta A J Assist Reprod Genet. 2024; 42(2):473-481.

PMID: 39652237 PMC: 11871245. DOI: 10.1007/s10815-024-03338-9.

Advanced KPI framework for IVF pregnancy prediction models in IVF protocols.

Sergeev S, Diakova I Sci Rep. 2024; 14(1):29477.

PMID: 39604481 PMC: 11603023. DOI: 10.1038/s41598-024-80759-7.

A Combination of Artificial Intelligence with Genetic Algorithms on Static Time-Lapse Images Improves Consistency in Blastocyst Assessment, An Interpretable Tool to Automate Human Embryo Evaluation: A Retrospective Cohort Study.

Toschi M, Bori L, Rocha J, Hickman C, Gouveia Nogueira M, Ferreira A Int J Fertil Steril. 2024; 18(4):378-383.

PMID: 39564830 PMC: 11589968. DOI: 10.22074/ijfs.2024.2008339.1510.

Bovine embryo production : evolution of culture media and commercial perspectives.

Krisher R, Herrick J Anim Reprod. 2024; 21(3):e20240051.

PMID: 39372256 PMC: 11452098. DOI: 10.1590/1984-3143-AR2024-0051.

References

Bi W, Hosny A, Schabath M, Giger M, Birkbak N, Mehrtash A . Artificial intelligence in cancer imaging: Clinical challenges and applications. CA Cancer J Clin. 2019; 69(2):127-157. PMC: 6403009. DOI: 10.3322/caac.21552. View

Patrizio P, Shoham G, Shoham Z, Leong M, Barad D, Gleicher N . Worldwide live births following the transfer of chromosomally "Abnormal" embryos after PGT/A: results of a worldwide web-based survey. J Assist Reprod Genet. 2019; 36(8):1599-1607. PMC: 6707985. DOI: 10.1007/s10815-019-01510-0. View

Tran D, Cooke S, Illingworth P, Gardner D . Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer. Hum Reprod. 2019; 34(6):1011-1018. PMC: 6554189. DOI: 10.1093/humrep/dez064. View

Annan J, Gudi A, Bhide P, Shah A, Homburg R . Biochemical pregnancy during assisted conception: a little bit pregnant. J Clin Med Res. 2013; 5(4):269-74. PMC: 3712881. DOI: 10.4021/jocmr1008w. View

Enatsu N, Miyatsuka I, An L, Inubushi M, Enatsu K, Otsuki J . A novel system based on artificial intelligence for predicting blastocyst viability and visualizing the explanation. Reprod Med Biol. 2022; 21(1):e12443. PMC: 8967284. DOI: 10.1002/rmb2.12443. View

Gardner D, Balaban B . Assessment of human embryo development using morphological criteria in an era of time-lapse, algorithms and 'OMICS': is looking good still important?. Mol Hum Reprod. 2016; 22(10):704-718. DOI: 10.1093/molehr/gaw057. View

Hill M, Richter K, Heitmann R, Graham J, Tucker M, DeCherney A . Trophectoderm grade predicts outcomes of single-blastocyst transfers. Fertil Steril. 2013; 99(5):1283-1289.e1. DOI: 10.1016/j.fertnstert.2012.12.003. View

Burduja M, Ionescu R, Verga N . Accurate and Efficient Intracranial Hemorrhage Detection and Subtype Classification in 3D CT Scans with Convolutional and Long Short-Term Memory Neural Networks. Sensors (Basel). 2020; 20(19). PMC: 7582288. DOI: 10.3390/s20195611. View

Santos Filho E, Noble J, Poli M, Griffiths T, Emerson G, Wells D . A method for semi-automatic grading of human blastocyst microscope images. Hum Reprod. 2012; 27(9):2641-8. DOI: 10.1093/humrep/des219. View

10.

Leaver M, Wells D . Non-invasive preimplantation genetic testing (niPGT): the next revolution in reproductive genetics?. Hum Reprod Update. 2019; 26(1):16-42. DOI: 10.1093/humupd/dmz033. View

11.

Ou Z, Chen Z, Yin M, Deng Y, Liang Y, Wang W . Re-analysis of whole blastocysts after trophectoderm biopsy indicated chromosome aneuploidy. Hum Genomics. 2020; 14(1):3. PMC: 6958758. DOI: 10.1186/s40246-019-0253-z. View

12.

Victor A, Griffin D, Brake A, Tyndall J, Murphy A, Lepkowsky L . Assessment of aneuploidy concordance between clinical trophectoderm biopsy and blastocyst. Hum Reprod. 2018; 34(1):181-192. DOI: 10.1093/humrep/dey327. View

13.

Miyagi Y, Habara T, Hirata R, Hayashi N . Feasibility of artificial intelligence for predicting live birth without aneuploidy from a blastocyst image. Reprod Med Biol. 2019; 18(2):204-211. PMC: 6452008. DOI: 10.1002/rmb2.12267. View

14.

Simon A, Kiehl M, Fischer E, Proctor J, Bush M, Givens C . Pregnancy outcomes from more than 1,800 in vitro fertilization cycles with the use of 24-chromosome single-nucleotide polymorphism-based preimplantation genetic testing for aneuploidy. Fertil Steril. 2018; 110(1):113-121. DOI: 10.1016/j.fertnstert.2018.03.026. View

15.

Gardner D, Lane M . Culture and selection of viable blastocysts: a feasible proposition for human IVF?. Hum Reprod Update. 1997; 3(4):367-82. DOI: 10.1093/humupd/3.4.367. View

16.

Sahlsten J, Jaskari J, Kivinen J, Turunen L, Jaanio E, Hietala K . Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading. Sci Rep. 2019; 9(1):10750. PMC: 6656880. DOI: 10.1038/s41598-019-47181-w. View

17.

Khosravi P, Kazemi E, Zhan Q, Malmsten J, Toschi M, Zisimopoulos P . Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization. NPJ Digit Med. 2019; 2:21. PMC: 6550169. DOI: 10.1038/s41746-019-0096-y. View

18.

Gardner D, Lane M, Stevens J, Schlenker T, Schoolcraft W . Blastocyst score affects implantation and pregnancy outcome: towards a single blastocyst transfer. Fertil Steril. 2000; 73(6):1155-8. DOI: 10.1016/s0015-0282(00)00518-5. View

19.

Sachdev N, McCulloh D, Kramer Y, Keefe D, Grifo J . The reproducibility of trophectoderm biopsies in euploid, aneuploid, and mosaic embryos using independently verified next-generation sequencing (NGS): a pilot study. J Assist Reprod Genet. 2020; 37(3):559-571. PMC: 7125266. DOI: 10.1007/s10815-020-01720-x. View

20.

Cheng C, Ho T, Lee T, Chang C, Chou C, Chen C . Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs. Eur Radiol. 2019; 29(10):5469-5477. PMC: 6717182. DOI: 10.1007/s00330-019-06167-y. View