{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T18:27:24Z","timestamp":1787509644055,"version":"build-2736575974"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T00:00:00Z","timestamp":1755648000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T00:00:00Z","timestamp":1755648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004629","name":"Ministry for Business Innovation and Employment","doi-asserted-by":"publisher","award":["UOAX2112"],"award-info":[{"award-number":["UOAX2112"]}],"id":[{"id":"10.13039\/501100004629","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001537","name":"University of Auckland","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001537","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Assist Reprod Genet"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>The ability to detect, monitor, and precisely time the morphokinetic stages of human pre-implantation embryo development plays a critical role in assessing their viability and potential for successful implantation. Therefore, there is a need for accurate and accessible tools to analyse embryos. This work describes a highly accurate, machine learning model designed to predict 17 morphokinetic stages of pre-implantation human development, an improvement on existing models. This model provides a robust tool for researchers and clinicians, enabling the automation of morphokinetic stage prediction, standardising the process, and reducing subjectivity between clinics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>A computer vision model was built on a publicly available dataset for embryo Morphokinetic stage detection. The dataset contained 273,438 labelled images based on Embryoscope\/\u2009+\u2009\u00a9 embryo images. The dataset was split 70\/10\/20 into training\/validation\/test sets. Two different deep learning architectures were trained and tested, one using EfficientNet-V2-Large and the other using EfficientNet-V2-Large with the addition of fertilisation time as input. A new postprocessing algorithm was developed to reduce noise in the predictions of the deep learning model and detect the exact time of each morphokinetic stage change.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed model reached an overall test F1-score of 0.881 and accuracy of 87% across 17 morphokinetic stages on an independent test set.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed model shows a 17% accuracy improvement, compared to the best models on the same dataset. Therefore, our model can accurately detect morphokinetic stages in static embryo images as well as detecting the exact timings of stage changes in a complete time-lapse video.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s10815-025-03585-4","type":"journal-article","created":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T09:26:09Z","timestamp":1755681969000},"page":"3655-3665","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Accurate machine learning model for human embryo morphokinetic stage detection"],"prefix":"10.1007","volume":"42","author":[{"given":"Hooman","family":"Misaghi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lynsey","family":"Cree","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7022-3352","authenticated-orcid":false,"given":"Nicholas","family":"Knowlton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,20]]},"reference":[{"issue":"10","key":"3585_CR1","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1038\/nbt.1686","volume":"28","author":"CC Wong","year":"2010","unstructured":"Wong CC, et al. Non-invasive imaging of human embryos before embryonic genome activation predicts development to the blastocyst stage. Nat Biotechnol. 2010;28(10):1115\u201321. https:\/\/doi.org\/10.1038\/nbt.1686.","journal-title":"Nat Biotechnol"},{"issue":"10","key":"3585_CR2","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1093\/molehr\/gaw057","volume":"22","author":"DK Gardner","year":"2016","unstructured":"Gardner DK, Balaban B. Assessment of human embryo development using morphological criteria in an era of time-lapse, algorithms and \u2018OMICS\u2019: is looking good still important? Mol Hum Reprod. 2016;22(10):704\u201318. https:\/\/doi.org\/10.1093\/molehr\/gaw057.","journal-title":"Mol Hum Reprod"},{"key":"3585_CR3","unstructured":"Gomez T, et al. Towards deep learning-powered IVF: a large public benchmark for morphokinetic parameter prediction. 2022, [Online]. Available: http:\/\/arxiv.org\/abs\/2203.00531.\u00a0Accessed Oct 2024."},{"key":"3585_CR4","doi-asserted-by":"publisher","unstructured":"Pribenszky C, Nilselid A, Montag M, Se- G. Time-lapse culture with morphokinetic embryo selection improves pregnancy and live birth chances and reduces early pregnancy loss\u202f: a meta-analysis. Reprod Biomed Online. 2017;35(5):511\u201320. https:\/\/doi.org\/10.1016\/j.rbmo.2017.06.022.","DOI":"10.1016\/j.rbmo.2017.06.022"},{"key":"3585_CR5","doi-asserted-by":"publisher","unstructured":"Paulson RJ, et al. Time-lapse imaging\u202f: clearly useful to both laboratory personnel and patient outcomes versus just because we can \u2019 t mean we should. Fertil Steril. 2018;109(4):584\u201391. https:\/\/doi.org\/10.1016\/j.fertnstert.2018.01.042.","DOI":"10.1016\/j.fertnstert.2018.01.042"},{"issue":"10","key":"3585_CR6","doi-asserted-by":"publisher","first-page":"2275","DOI":"10.1093\/humrep\/deac171","volume":"37","author":"DE Fordham","year":"2022","unstructured":"Fordham DE, et al. Embryologist agreement when assessing blastocyst implantation probability: is data-driven prediction the solution to embryo assessment subjectivity? Hum Reprod. 2022;37(10):2275\u201390. https:\/\/doi.org\/10.1093\/humrep\/deac171.","journal-title":"Hum Reprod"},{"key":"3585_CR7","doi-asserted-by":"publisher","unstructured":"Bamford T et al. Association between a morphokinetic ploidy prediction model risk score and miscarriage and live birth: a multicentre cohort study. Fertil Sterilp 2023;108\u2013112 https:\/\/doi.org\/10.1016\/j.fertnstert.2023.06.006","DOI":"10.1016\/j.fertnstert.2023.06.006"},{"issue":"8","key":"3585_CR8","doi-asserted-by":"publisher","DOI":"10.3390\/jcm12082983","volume":"12","author":"C Serrano-Novillo","year":"2023","unstructured":"Serrano-Novillo C, Uroz L, M\u00e1rquez C. Novel time-lapse parameters correlate with embryo ploidy and suggest an improvement in non-invasive embryo selection. J Clin Med. 2023;12(8): 2983. https:\/\/doi.org\/10.3390\/jcm12082983.","journal-title":"J Clin Med"},{"key":"3585_CR9","doi-asserted-by":"publisher","unstructured":"Gazzo E, et al. Original article The Kidscore TM D5 algorithm as an additional tool to morphological assessment and PGT-A in embryo selection : a time-lapse study. JBRA Assist Reprod. 2020;24(1):pp. 55\u201360. https:\/\/doi.org\/10.5935\/1518-0557.20190054.","DOI":"10.5935\/1518-0557.20190054."},{"issue":"3","key":"3585_CR10","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1093\/humrep\/deaa001","volume":"35","author":"M Feyeux","year":"2020","unstructured":"Feyeux M, et al. Development of automated annotation software for human embryo morphokinetics. Hum Reprod. 2020;35(3):557\u201364. https:\/\/doi.org\/10.1093\/humrep\/deaa001.","journal-title":"Hum Reprod"},{"issue":"no. 5","key":"3585_CR11","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1016\/j.fertnstert.2014.07.738","volume":"102","author":"I Rubio","year":"2014","unstructured":"Rubio I, et al. Clinical validation of embryo culture and selection by morphokinetic analysis: a randomized, controlled trial of the EmbryoScope. Fertil Steril. 2014;102(5):1287-1294.e5. https:\/\/doi.org\/10.1016\/j.fertnstert.2014.07.738.","journal-title":"Fertil Steril"},{"issue":"10","key":"3585_CR12","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.1093\/humrep\/dew188","volume":"31","author":"BM Petersen","year":"2016","unstructured":"Petersen BM, Boel M, Montag M, Gardner DK. Development of a generally applicable morphokinetic algorithm capable of predicting the implantation potential of embryos transferred on day 3. Hum Reprod. 2016;31(10):2231\u201344. https:\/\/doi.org\/10.1093\/humrep\/dew188.","journal-title":"Hum Reprod"},{"issue":"3","key":"3585_CR13","doi-asserted-by":"publisher","first-page":"228","DOI":"10.5935\/1518-0557.20180042","volume":"22","author":"E Adolfsson","year":"2018","unstructured":"Adolfsson E, Andershed AN. Morphology vs morphokinetics: a retrospective comparison of interobserver and intra-observer agreement between embryologists on blastocysts with known implantation outcome. J Bras Reprod Assist. 2018;22(3):228\u201337. https:\/\/doi.org\/10.5935\/1518-0557.20180042.","journal-title":"J Bras Reprod Assist"},{"key":"3585_CR14","doi-asserted-by":"publisher","first-page":"2023","DOI":"10.1093\/hropen\/hoad031","volume":"3","author":"M Salih","year":"2023","unstructured":"Salih M, et al. Embryo selection through artificial intelligence versus embryologists: a systematic review. Hum Reprod Open. 2023;3:2023. https:\/\/doi.org\/10.1093\/hropen\/hoad031.","journal-title":"Hum Reprod Open"},{"issue":"2","key":"3585_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0262661","volume":"17","author":"J Berntsen","year":"2022","unstructured":"Berntsen J, Rimestad J, Lassen JT, Tran D, Kragh MF. Robust and generalizable embryo selection based on artificial intelligence and time-lapse image sequences. PLoS One. 2022;17(2):1\u201318. https:\/\/doi.org\/10.1371\/journal.pone.0262661.","journal-title":"PLoS One"},{"issue":"1","key":"3585_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-023-31136-3","volume":"13","author":"J Theilgaard Lassen","year":"2023","unstructured":"Theilgaard Lassen J, Fly Kragh M, Rimestad J, Nyg\u00e5rd Johansen M, Berntsen J. Development and validation of deep learning based embryo selection across multiple days of transfer. Sci Rep. 2023;13(1):1\u20139. https:\/\/doi.org\/10.1038\/s41598-023-31136-3.","journal-title":"Sci Rep"},{"issue":"4","key":"3585_CR17","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1093\/HUMREP\/DEAA013","volume":"35","author":"M Ver Milyea","year":"2021","unstructured":"Ver Milyea M, 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. Hum Reprod. 2021;35(4):770\u201384. https:\/\/doi.org\/10.1093\/HUMREP\/DEAA013.","journal-title":"Hum Reprod"},{"issue":"1","key":"3585_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-019-0096-y","volume":"2","author":"P Khosravi","year":"2019","unstructured":"Khosravi P, et al. Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization. NPJ Digit Med. 2019;2(1):1\u20139. https:\/\/doi.org\/10.1038\/s41746-019-0096-y.","journal-title":"NPJ Digit Med"},{"issue":"2","key":"3585_CR19","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1093\/humrep\/deu331","volume":"30","author":"N Basile","year":"2015","unstructured":"Basile N, et al. The use of morphokinetics as a predictor of implantation: a multicentric study to define and validate an algorithmfor embryo selection. Hum Reprod. 2015;30(2):276\u201383. https:\/\/doi.org\/10.1093\/humrep\/deu331.","journal-title":"Hum Reprod"},{"issue":"4","key":"3585_CR20","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1016\/j.rbmo.2020.07.003","volume":"41","author":"A Chavez-Badiola","year":"2020","unstructured":"Chavez-Badiola A, Flores-Saiffe-Far\u00edas 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(4):585\u201393. https:\/\/doi.org\/10.1016\/j.rbmo.2020.07.003.","journal-title":"Reprod Biomed Online"},{"issue":"6","key":"3585_CR21","doi-asserted-by":"publisher","first-page":"1391","DOI":"10.1007\/s10815-023-02806-y","volume":"40","author":"N Zabari","year":"2023","unstructured":"Zabari N, et al. Delineating the heterogeneity of embryo preimplantation development using automated and accurate morphokinetic annotation. J Assist Reprod Genet. 2023;40(6):1391\u2013406. https:\/\/doi.org\/10.1007\/s10815-023-02806-y.","journal-title":"J Assist Reprod Genet"},{"issue":"1","key":"3585_CR22","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.rbmo.2022.02.012","volume":"45","author":"J Vandame","year":"2022","unstructured":"Vandame J, et al. Investigation of the reliability of semi-automatic annotation by the Geri time-lapse system. Reprod Biomed Online. 2022;45(1):35\u201345. https:\/\/doi.org\/10.1016\/j.rbmo.2022.02.012.","journal-title":"Reprod Biomed Online"},{"key":"3585_CR23","unstructured":"Tan M, Le QV. EfficientNetV2: smaller models and faster training. In: Meil\u0103 M, Zhang T, editors. Proceedings of the 38th International Conference on Machine Learning. vol. 139. PMLR; 2021. pp. 10096\u201310106."},{"key":"3585_CR24","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, editors. Advances in Neural Information Processing Systems. vol. 30. Curran Associates; 2017. pp. 5998\u20136008. https:\/\/doi.org\/10.5555\/3295222.3295349.","DOI":"10.5555\/3295222.3295349"},{"key":"3585_CR25","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. PyTorch: an imperative style, high-performance deep learning library. In: Wallach H, et al., editors. Advances in Neural Information Processing Systems. vol. 32. Vancouver, Canada; 2019. pp. 8024\u20138035."},{"key":"3585_CR26","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125","author":"A Buslaev","year":"2020","unstructured":"Buslaev A, Iglovikov VI, Khvedchenya E, Parinov A, Druzhinin M, Kalinin AA. Albumentations: fast and flexible image augmentations. Information. 2020. https:\/\/doi.org\/10.3390\/info11020125.","journal-title":"Information"},{"issue":"2","key":"3585_CR27","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1016\/j.rbmo.2022.09.010","volume":"46","author":"K Kato","year":"2023","unstructured":"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(2):274\u201381. https:\/\/doi.org\/10.1016\/j.rbmo.2022.09.010.","journal-title":"Reprod Biomed Online"},{"issue":"4","key":"3585_CR28","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1016\/j.fertnstert.2019.12.004","volume":"113","author":"CL Bormann","year":"2020","unstructured":"Bormann CL, et al. Consistency and objectivity of automated embryo assessments using deep neural networks. Fertil Steril. 2020;113(4):781-787.e1. https:\/\/doi.org\/10.1016\/j.fertnstert.2019.12.004.","journal-title":"Fertil Steril"},{"issue":"5","key":"3585_CR29","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.1016\/j.fertnstert.2014.07.1235","volume":"102","author":"Y Liu","year":"2014","unstructured":"Liu Y, Chapple V, Roberts P, Matson P. Prevalence, consequence, and significance of reverse cleavage by human embryos viewed with the use of the Embryoscope time-lapse video system. Fertil Steril. 2014;102(5):1295-1300.e2. https:\/\/doi.org\/10.1016\/j.fertnstert.2014.07.1235.","journal-title":"Fertil Steril"},{"key":"3585_CR30","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. pp. 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Journal of Assisted Reproduction and Genetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10815-025-03585-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10815-025-03585-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10815-025-03585-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T18:04:26Z","timestamp":1764180266000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10815-025-03585-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,20]]},"references-count":30,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["3585"],"URL":"https:\/\/doi.org\/10.1007\/s10815-025-03585-4","relation":{},"ISSN":["1058-0468","1573-7330"],"issn-type":[{"value":"1058-0468","type":"print"},{"value":"1573-7330","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,20]]},"assertion":[{"value":"6 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Ethics was approved by Auckland Health Research Ethics Committee (AHREC) protocol 1033 at the University of Auckland.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}